concept: voice-conversion last_updated: '2026-07-28' paper_count: 87 papers: - id: '2104.00355' published_date: "2021-04-01" entry_date: '2026-07-28' year: 2021 venue: arXiv task: - TTS - VC architecture: - GAN - VAE relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: influential method_family: - gan_adversarial_voice_conversion - vae_latent_voice_conversion claims: - claim_id: ssl_content_representations_that_are_well_disentangled_from_speaker_identity role: supports claim: SSL content representations that are well-disentangled from speaker identity also exhibit stronger voice conversion performance, while representations that entangle speaker information perform worse at conversion but better at pitch reconstruction. source: §4, Table 1, Table 2 evidence: SSL content representations that are well-disentangled from speaker identity also exhibit stronger voice conversion performance, while representations that entangle speaker information perform worse at conversion but better at pitch reconstruction. confidence: high relevance: high - claim_id: discrete_speech_units_learned_by_ssl_models_can_form_the role: supports claim: Discrete speech units learned by SSL models can form the basis of an ultra-low-bitrate speech codec that outperforms classical parametric codecs in subjective quality. source: §4, Figure 2 evidence: Discrete speech units learned by SSL models can form the basis of an ultra-low-bitrate speech codec that outperforms classical parametric codecs in subjective quality. confidence: high relevance: low - claim_id: among_self_supervised_content_encoders_hubert_units_carry_less_speaker role: supports claim: Among self-supervised content encoders, HuBERT units carry less speaker and pitch information than VQ-VAE units, making them better suited for downstream controllable synthesis. source: §4, Table 2 evidence: Among self-supervised content encoders, HuBERT units carry less speaker and pitch information than VQ-VAE units, making them better suited for downstream controllable synthesis. confidence: high relevance: medium - claim_id: pitch_and_speaker_identity_can_be_independently_conditioned_in_a role: supports claim: Pitch and speaker identity can be independently conditioned in a GAN vocoder through separate discrete token streams, enabling controllable F0 manipulation without retraining. source: §3, §4 evidence: Pitch and speaker identity can be independently conditioned in a GAN vocoder through separate discrete token streams, enabling controllable F0 manipulation without retraining. confidence: high relevance: high limitations: - The codec evaluation uses only 20 utterances from 5 VCTK speakers, all unseen during training but from the same corpus. Generalization to out-of-domain speech (conversational, noisy, or non-English) is untested. - The resynthesis MOS scores remain well below ground truth on both LJSpeech (3.66 vs. 4.33) and VCTK (3.41 vs. 4.08), indicating a quality gap the system does not close. Disentanglement is evaluated indirectly through proxy metrics (EER, VDE, FFE) rather than a direct information-theoretic measure. The speaker encoder requires speaker embeddings from training-set speakers for the lookup-table variant; the d-vector approach generalizes but relies on a separately trained verification model. No ablation isolates the contribution of the F0 conditioning stream to final MOS. The MUSHRA scores in Figure 2 are visual only, making exact numerical comparison to baselines difficult to reproduce from the paper text alone. caveats: [] - id: '2310.00704' published_date: "2023-10-01" entry_date: '2026-07-28' year: 2023 venue: arXiv task: - TTS - VC - singing architecture: - autoregressive-LM - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: influential method_family: - autoregressive_token_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: training_a_single_audio_language_model_across_diverse_generation_tasks role: supports claim: Training a single audio language model across diverse generation tasks (TTS, voice conversion, sound synthesis, music, singing) produces consistent performance improvements over task-specific models trained on the same data. source: §3.4.1, Appendix C.1, Table 17 evidence: Training a single audio language model across diverse generation tasks (TTS, voice conversion, sound synthesis, music, singing) produces consistent performance improvements over task-specific models trained on the same data. confidence: high relevance: high - claim_id: the_autoregressive_property_is_critical_for_audio_generation_quality_parallel role: supports claim: 'The autoregressive property is critical for audio generation quality: parallel and delay-based codec prediction approaches yield measurably lower naturalness than fully autoregressive methods when codec quantization levels are held constant.' source: §3.4.2, Tables 4–5 evidence: 'The autoregressive property is critical for audio generation quality: parallel and delay-based codec prediction approaches yield measurably lower naturalness than fully autoregressive methods when codec quantization levels are held constant.' confidence: high relevance: low - claim_id: hierarchical_factorisation_of_rvq_codec_token_sequences_into_inter_frame role: supports claim: Hierarchical factorisation of RVQ codec token sequences into inter-frame and intra-frame modeling substantially reduces training memory and time relative to flat-sequence autoregressive prediction, with comparable generation quality. source: §2.3, §3.4.2, Table 4 evidence: Hierarchical factorisation of RVQ codec token sequences into inter-frame and intra-frame modeling substantially reduces training memory and time relative to flat-sequence autoregressive prediction, with comparable generation quality. confidence: high relevance: low - claim_id: pre_training_on_a_broad_multi_task_audio_corpus_enables role: supports claim: Pre-training on a broad multi-task audio corpus enables strong adaptation to unseen audio generation tasks via fine-tuning on small datasets, outperforming task-specific models trained from scratch on those tasks. source: §3.3, Appendix B.5–B.8, Table 17 evidence: Pre-training on a broad multi-task audio corpus enables strong adaptation to unseen audio generation tasks via fine-tuning on small datasets, outperforming task-specific models trained from scratch on those tasks. confidence: high relevance: medium - claim_id: signal_level_metrics_such_as_pesq_are_poorly_suited_for role: supports claim: 'Signal-level metrics such as PESQ are poorly suited for evaluating generative audio models: systems achieving higher perceptual MOS scores routinely score lower on PESQ than discriminative baselines.' source: §3.2, §3.4.2, Table 11 evidence: 'Signal-level metrics such as PESQ are poorly suited for evaluating generative audio models: systems achieving higher perceptual MOS scores routinely score lower on PESQ than discriminative baselines.' confidence: high relevance: medium limitations: - Model checkpoints are not released due to misuse concerns, limiting reproducibility. Only code and demos are public. Researchers cannot directly reproduce the full 165K-hour training run or perform ablations at scale. - 'UniAudio does not handle all known audio tasks: noise removal, noisy speech editing, and speech-to-speech translation are explicitly excluded. New modalities cannot be introduced during fine-tuning, only new combinations of modalities already seen at training time. The system relies entirely on labeled data; self-supervised or weakly supervised pre-training from unlabeled audio, which could substantially increase coverage, is left as future work.' - The multi-task benefit is empirically demonstrated but mechanistically underexplained. The paper offers informal hypotheses (shared codec token space, data augmentation equivalences between TTS and VC conditions) but no formal analysis. It is unclear whether the gains stem from better codec representations, increased effective data volume per task, or genuine cross-task transfer. caveats: [] - id: '2312.01479' published_date: "2023-12-03" entry_date: '2026-07-28' year: 2023 venue: arXiv task: - TTS architecture: - GAN - VAE relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence - evaluation_caution current_role: active_evidence method_family: - gan_adversarial_voice_conversion - vae_latent_voice_conversion claims: - claim_id: decoupling_tone_color_transfer_from_style_and_language_generation_enables role: supports claim: Decoupling tone color transfer from style and language generation enables flexible post-cloning control over emotion, accent, and rhythm without requiring paired multi-attribute training data. source: §2.1, §2.2 evidence: Decoupling tone color transfer from style and language generation enables flexible post-cloning control over emotion, accent, and rhythm without requiring paired multi-attribute training data. confidence: high relevance: medium - claim_id: using_ipa_as_a_universal_phoneme_representation_in_a_normalising role: supports claim: Using IPA as a universal phoneme representation in a normalising flow allows voice cloning to generalise to unseen languages without retraining on massive multilingual speaker data. source: §2.3, §3 "Importance of IPA" evidence: Using IPA as a universal phoneme representation in a normalising flow allows voice cloning to generalise to unseen languages without retraining on massive multilingual speaker data. confidence: high relevance: high - claim_id: feed_forward_voice_cloning_pipelines_encoder_flow_decoder_without_autoregressive role: supports claim: Feed-forward voice cloning pipelines (encoder-flow-decoder without autoregressive or diffusion components) achieve real-time or faster inference, making large-scale commercial deployment feasible. source: §3 "Fast Inference with Low Cost" evidence: Feed-forward voice cloning pipelines (encoder-flow-decoder without autoregressive or diffusion components) achieve real-time or faster inference, making large-scale commercial deployment feasible. confidence: high relevance: high - claim_id: cross_study_quantitative_comparison_of_voice_cloning_systems_is_systematically role: supports claim: Cross-study quantitative comparison of voice cloning systems is systematically confounded by differences in test set composition, training data scale, and evaluation protocol. source: §3 evidence: Cross-study quantitative comparison of voice cloning systems is systematically confounded by differences in test set composition, training data scale, and evaluation protocol. confidence: high relevance: high limitations: - The paper reports no quantitative metrics anywhere. All evaluation is qualitative, with audio samples hosted on a demo website. This makes it impossible to independently verify the claimed advantages over VALL-E, XTTS, YourTTS, or Voicebox on any standard benchmark. - The base TTS model is trained on only four speakers across English, Chinese, and Japanese. Adding support for additional languages requires collecting at least one native single-speaker dataset, which while much cheaper than a full MSML system, still represents a non-trivial data acquisition effort. Style preservation through the tone color converter is imperfect for highly expressive inputs, with emotion occasionally being neutralised. The proprietary training data for both the base model and the MSML converter set cannot be replicated by the research community despite the open-source code and weights release. caveats: [] - id: '2403.03100' published_date: "2024-03-05" entry_date: '2026-07-28' year: 2024 venue: arXiv task: - TTS - VC architecture: - diffusion - hybrid relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: influential method_family: - diffusion_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: explicit_disentanglement_of_speech_attributes_in_the_codec_representation_reduces role: supports claim: Explicit disentanglement of speech attributes in the codec representation reduces the complexity of zero-shot generation and improves speaker similarity, quality, and prosody simultaneously. source: §3, §4.2, Table 1, Table 2 evidence: Explicit disentanglement of speech attributes in the codec representation reduces the complexity of zero-shot generation and improves speaker similarity, quality, and prosody simultaneously. confidence: high relevance: low - claim_id: gradient_reversal_combined_with_attribute_specific_supervised_losses_is_an role: supports claim: Gradient reversal combined with attribute-specific supervised losses is an effective mechanism for suppressing cross-attribute information leakage in neural codec quantization. source: §3.2.2, Appendix B.4 evidence: Gradient reversal combined with attribute-specific supervised losses is an effective mechanism for suppressing cross-attribute information leakage in neural codec quantization. confidence: high relevance: low - claim_id: the_factorization_paradigm_for_codec_representations_is_architecture_agnostic_and role: supports claim: The factorization paradigm for codec representations is architecture-agnostic and improves both autoregressive and non-autoregressive generators when applied. source: §4.3.2, Table 6 evidence: The factorization paradigm for codec representations is architecture-agnostic and improves both autoregressive and non-autoregressive generators when applied. confidence: high relevance: low - claim_id: discrete_masked_diffusion_over_disentangled_codec_tokens_is_faster_than role: supports claim: Discrete masked diffusion over disentangled codec tokens is faster than autoregressive LM-based codec generation at comparable or better quality. source: Appendix A.5, Table 10 evidence: Discrete masked diffusion over disentangled codec tokens is faster than autoregressive LM-based codec generation at comparable or better quality. confidence: high relevance: low - claim_id: performance_on_zero_shot_tts_scales_predictably_with_both_training role: supports claim: Performance on zero-shot TTS scales predictably with both training data volume and model size when the underlying speech representation captures disentangled attributes. source: §4.4, Tables 7, 8 evidence: Performance on zero-shot TTS scales predictably with both training data volume and model size when the underlying speech representation captures disentangled attributes. confidence: high relevance: medium limitations: - FACodec requires phoneme-level transcriptions for content supervision during training, constraining its applicability to languages and settings where reliable alignments are unavailable. The zero-shot TTS evaluation is English-only; multilingual generalisation is stated as future work but not demonstrated. - 'Additional limitations: the attribute factorization is incomplete (background sounds, energy, and other fine-grained characteristics are not captured, as noted in Appendix C); the acoustic detail subspace retains some content and prosody leakage without gradient reversal (verified qualitatively in Appendix B.4); and the prosody evaluation relies on MCD and emotion classifiers on the RAVDESS dataset, which assesses a narrow range of acted emotions rather than naturalistic prosodic variation.' - Open questions include whether factorized disentanglement continues to improve at larger scales and whether supervision-free disentanglement is achievable without degrading reconstruction quality. caveats: [] - id: '2406.02430' published_date: "2024-06-04" entry_date: '2026-07-28' year: 2024 venue: arXiv task: - TTS - VC architecture: - autoregressive-LM - diffusion - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence current_role: influential method_family: - autoregressive_token_voice_conversion - diffusion_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: autoregressive_codec_language_models_trained_at_sufficient_scale_can_generate role: supports claim: Autoregressive codec language models trained at sufficient scale can generate zero-shot speech with naturalness and speaker similarity indistinguishable from human speech as measured by CMOS. source: §3.1, Table 1 evidence: Autoregressive codec language models trained at sufficient scale can generate zero-shot speech with naturalness and speaker similarity indistinguishable from human speech as measured by CMOS. confidence: high relevance: low - claim_id: self_distillation_on_perturbation_generated_pairs_is_an_effective_method role: supports claim: Self-distillation on perturbation-generated pairs is an effective method for timbre disentanglement in TTS systems, achieving large speaker similarity gains in voice conversion without modifying model architecture or loss functions. source: §4.1, Table 6 evidence: Self-distillation on perturbation-generated pairs is an effective method for timbre disentanglement in TTS systems, achieving large speaker similarity gains in voice conversion without modifying model architecture or loss functions. confidence: high relevance: high - claim_id: reinforcement_learning_post_training_with_objective_speech_quality_rewards_improves role: supports claim: Reinforcement learning post-training with objective speech quality rewards improves robustness and speaker similarity in autoregressive TTS while introducing reward hacking that must be carefully managed. source: §4.2, Tables 7, 8 evidence: Reinforcement learning post-training with objective speech quality rewards improves robustness and speaker similarity in autoregressive TTS while introducing reward hacking that must be carefully managed. confidence: high relevance: medium - claim_id: end_to_end_diffusion_models_that_predict_total_duration_and role: supports claim: End-to-end diffusion models that predict total duration and learn local text-audio alignment implicitly can match or exceed the quality of autoregressive codec LM systems without per-phoneme duration supervision. source: §4.3, Table 10 evidence: End-to-end diffusion models that predict total duration and learn local text-audio alignment implicitly can match or exceed the quality of autoregressive codec LM systems without per-phoneme duration supervision. confidence: high relevance: low - claim_id: synthetic_speech_generated_by_a_high_quality_zero_shot_tts role: supports claim: Synthetic speech generated by a high-quality zero-shot TTS system can train ASR models that approach real-data performance on clean test sets, though a gap persists on noisy sets due to background noise smoothing. source: §3.1, Table 2 evidence: Synthetic speech generated by a high-quality zero-shot TTS system can train ASR models that approach real-data performance on clean test sets, though a gap persists on noisy sets due to background noise smoothing. confidence: high relevance: medium limitations: - '- Model weights not released; no reported parameter count. - Zero-shot ICL struggles with speakers having strong accents or unique styles not captured in a short (15s) prompt — the fine-tuned model is still preferred for ''hard'' speakers. - Synthesized speech slightly over-smooths background noise (ASR degrades on noisy test sets). - Does not handle singing or speech with background music well. - Reward hacking (over-slow, over-articulated speech) in RL post-training requires careful tuning. - Multi-shot ICL for long-form generation not yet demonstrated.' caveats: [] - id: '2411.09943' published_date: "2024-11-15" entry_date: '2026-07-28' year: 2024 venue: arXiv task: - VC architecture: - diffusion - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion - transformer_encoder_decoder_voice_conversion claims: - claim_id: using_an_imperfect_external_vc_model_as_a_timbre_shifting role: supports claim: Using an imperfect external VC model as a timbre-shifting augmentation device during training reduces timbre leakage in content representations without requiring discrete bottlenecking, preserving intelligibility. source: §3.3, Table 1 evidence: Using an imperfect external VC model as a timbre-shifting augmentation device during training reduces timbre leakage in content representations without requiring discrete bottlenecking, preserving intelligibility. confidence: high relevance: high - claim_id: conditioning_a_generative_vc_model_on_the_full_reference_utterance role: supports claim: Conditioning a generative VC model on the full reference utterance via in-context learning yields higher speaker similarity than conditioning on a single speaker embedding alone. source: §3.4, Table 1 evidence: Conditioning a generative VC model on the full reference utterance via in-context learning yields higher speaker similarity than conditioning on a single speaker embedding alone. confidence: high relevance: high - claim_id: the_speaker_similarity_versus_intelligibility_trade_off_that_limits_bottleneck role: complicates claim: The speaker similarity versus intelligibility trade-off that limits bottleneck-based zero-shot VC approaches can be mitigated by separating timbre perturbation from content feature extraction. source: §1, §3.3.1 evidence: The speaker similarity versus intelligibility trade-off that limits bottleneck-based zero-shot VC approaches can be mitigated by separating timbre perturbation from content feature extraction. confidence: high relevance: high - claim_id: f0_conditioning_enables_diffusion_transformer_vc_models_to_extend_to role: supports claim: F0 conditioning enables diffusion transformer VC models to extend to zero-shot singing voice conversion with competitive pitch preservation and improved lyric intelligibility over per-speaker trained baselines. source: §3.5, Table 2 evidence: F0 conditioning enables diffusion transformer VC models to extend to zero-shot singing voice conversion with competitive pitch preservation and improved lyric intelligibility over per-speaker trained baselines. confidence: high relevance: high limitations: - No subjective listening tests (MOS or MUSHRA) are reported. All quality comparisons rely on DNSMOS P.835, an automatic metric; naturalness conclusions should be treated with caution. - The training data advantage is substantial (Emilia-101k vs. unspecified but likely smaller datasets for OpenVoice and CosyVoice), and the authors acknowledge that a dataset-controlled comparison is future work. The timbre-shifter used during training is OpenVoice V2, a proprietary-trained model, which may limit reproducibility for researchers without access to a comparable off-the-shelf VC system. The DNSMOS scores indicate that Seed-VC's naturalness is slightly below OpenVoice despite its higher speaker similarity, suggesting the model may benefit from vocoder-level refinements. Real-time deployment is identified as an open direction; the current system's latency is not characterised. caveats: [] - id: '2412.04724' published_date: "2024-12-06" entry_date: '2026-07-28' year: 2024 venue: arXiv task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: influential method_family: - flow_matching_voice_conversion claims: - claim_id: independent_timbre_and_style_transfer_from_distinct_unseen_speakers_can role: supports claim: Independent timbre and style transfer from distinct unseen speakers can be achieved without degrading either attribute when conditioning streams are separated via parallel cross-attention with adaptive gating. source: §DualAGC, Table 2 evidence: Independent timbre and style transfer from distinct unseen speakers can be achieved without degrading either attribute when conditioning streams are separated via parallel cross-attention with adaptive gating. confidence: high relevance: high - claim_id: flow_matching_enables_zero_shot_voice_conversion_that_surpasses_diffusion role: supports claim: Flow matching enables zero-shot voice conversion that surpasses diffusion baselines in both sample quality and inference speed, with quality stabilising in as few as 10 ODE steps. source: §Conditional Flow Matching, Table 1, Table 3 evidence: Flow matching enables zero-shot voice conversion that surpasses diffusion baselines in both sample quality and inference speed, with quality stabilising in as few as 10 ODE steps. confidence: high relevance: high - claim_id: timbre_leakage_into_style_representations_is_a_failure_mode_in role: supports claim: Timbre leakage into style representations is a failure mode in jointly trained VC systems, and adversarial disentanglement via gradient reversal measurably reduces this cross-contamination. source: §Training Objectives, Table 4 evidence: Timbre leakage into style representations is a failure mode in jointly trained VC systems, and adversarial disentanglement via gradient reversal measurably reduces this cross-contamination. confidence: high relevance: high - claim_id: using_multiple_reference_utterances_alongside_a_pre_trained_speaker_verification role: supports claim: Using multiple reference utterances alongside a pre-trained speaker verification prior as the timbre attention key dramatically improves intelligibility in cross-attention-based timbre modeling, as its removal causes WER to collapse from 2% to over 22%. source: §DualAGC, Table 4 evidence: Using multiple reference utterances alongside a pre-trained speaker verification prior as the timbre attention key dramatically improves intelligibility in cross-attention-based timbre modeling, as its removal causes WER to collapse from 2% to over 22%. confidence: high relevance: high - claim_id: non_autoregressive_vc_generation_maintains_near_constant_latency_regardless_of role: supports claim: Non-autoregressive VC generation maintains near-constant latency regardless of utterance length, a qualitative advantage over token-by-token autoregressive decoding that is not captured by fixed-length RTF comparisons. source: §Experimental Results on Zero-shot VC evidence: Non-autoregressive VC generation maintains near-constant latency regardless of utterance length, a qualitative advantage over token-by-token autoregressive decoding that is not captured by fixed-length RTF comparisons. confidence: high relevance: low limitations: - The factorized codec used as the style extractor is referenced as a public tool but not described in detail in the paper, which restricts exact reproducibility of the style extraction stage. - The evaluation covers English speakers only (VCTK for timbre, ESD for style), leaving cross-lingual style transfer untested. The style space is effectively bounded by the factorized codec's subspace representation, and it is unclear how fine-grained or compositional the style control is in practice beyond the five ESD emotion categories. The system uses HiFi-GAN as vocoder rather than a codec-based decoder, which may limit audio bandwidth compared to neural codec approaches. Results on real-world noisy conditions are not reported; training was filtered by DNSMOS quality, so robustness to in-the-wild speech is assumed but unverified. caveats: [] - id: '2409.09098' published_date: "2025-01-09" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - transformer_encoder_decoder_voice_conversion claims: - claim_id: speaker_accent_entanglement_in_accent_identification_models_causes_poor_generalisation role: supports claim: Speaker-accent entanglement in accent identification models causes poor generalisation to unseen speakers and limits the utility of accent embeddings for conditioning TTS systems. source: §III.A, §IV.A, Table IV evidence: The CommonAccent baseline achieves 0.96 accuracy on seen speakers but only 0.43 on unseen speakers (gap 0.53), and has a high SCSC of 0.236, indicating that it memorises speaker-to-accent mappings. GenAID with information bottleneck and adversarial training reduces the gap to 0.06 and SCSC to 0.079. confidence: high relevance: medium - claim_id: continuous_accent_embeddings_extracted_from_a_speaker_agnostic_model_provide role: supports claim: Continuous accent embeddings extracted from a speaker-agnostic model provide stronger accent conditioning for zero-shot TTS than discrete one-hot accent labels. source: §IV.B, Tables V–VII evidence: AccentBox conditioned on continuous GenAID embeddings achieves higher accent cosine similarity than the Accent_ID system using one-hot accent embeddings in both inherent and cross accent generation, and is preferred by listeners in subjective accent similarity tests. confidence: high relevance: medium - claim_id: zero_shot_accent_generation_introduces_a_trade_off_between_accent role: complicates claim: Zero-shot accent generation introduces a trade-off between accent fidelity and naturalness that varies with accent data coverage. source: §IV.B, Table VI evidence: AccentBox shows higher naturalness preference for American accent (60.0% preferred over Baseline, p=0.011) but lower preference for Irish accent (33.9%), where limited training data and sensitivity to monotonic prosody in reference speech cause degradation. confidence: high relevance: medium - claim_id: objective_speaker_similarity_metrics_may_not_align_with_subjective_listener role: complicates claim: Objective speaker similarity metrics may not align with subjective listener perception when accent and speaker identity are jointly manipulated. source: §IV.B, Tables V–VI evidence: For inherent accent generation, AccentBox achieves lower SpkCos (0.8293) than Baseline (0.8413) and VALL-E X (0.8605) in objective evaluation, yet listeners subjectively prefer AccentBox for speaker similarity (70.0%, p=0.002 for American accent), suggesting the speaker verification model is biased toward common accent patterns. confidence: high relevance: high - claim_id: standard_zs_tts_evaluations_based_on_naturalness_and_speaker_similarity role: refines claim: Standard ZS-TTS evaluations based on naturalness and speaker similarity fail to detect accent hallucination, underrepresenting the accent fidelity gap between TTS systems trained predominantly on American English and target accented speakers. source: §I, §III.B evidence: The paper demonstrates that current SOTA ZS-TTS systems (including VALL-E X) generate a default American-English accent regardless of the target speaker's accent, an artefact not captured by conventional MOS or speaker-similarity metrics. Accent cosine similarity and subjective accent preference tests are introduced as complementary metrics. confidence: high relevance: medium limitations: - Subjective listening tests are restricted to two accents (American and Irish) due to budget constraints; the cross-accent and unseen-accent generation results lack systematic subjective evaluation. The Irish accent results show degraded naturalness, indicating the system is sensitive to data volume and reference speech quality in ways that may not generalise across all 13 accents. - The TTS backbone (YourTTS, VITS-based) is several generations behind current LLM-based and flow-matching ZS-TTS systems. The authors chose YourTTS for stability and compute efficiency, but the quality ceiling limits competitiveness with current state-of-the-art naturalness. The paper does not evaluate WER, arguing that ASR models are biased against accented speech; this is a reasonable methodological choice but limits comparability with other work. Unseen accent generation is demonstrated only via audio samples on the demo page, with no quantitative evaluation. caveats: [] - id: '2502.07243' published_date: "2025-02-11" entry_date: '2026-07-28' year: 2025 venue: ICLR task: - TTS - VC architecture: - autoregressive-LM - flow-matching - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence current_role: influential method_family: - autoregressive_token_voice_conversion - flow_matching_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: the_vq_vae_codebook_vocabulary_size_can_function_as_a role: supports claim: The VQ-VAE codebook vocabulary size can function as a self-supervised information bottleneck for progressive disentanglement of timbre, style, and linguistic content in self-supervised speech representations. source: §3.1, Table 2 evidence: The VQ-VAE codebook vocabulary size can function as a self-supervised information bottleneck for progressive disentanglement of timbre, style, and linguistic content in self-supervised speech representations. confidence: high relevance: high - claim_id: zero_shot_style_imitation_accent_and_emotion_conversion_without_annotation role: supports claim: Zero-shot style imitation (accent and emotion conversion) without annotation can match or exceed supervised baselines that rely on parallel corpora and style labels. source: §4.3, Table 4 evidence: Zero-shot style imitation (accent and emotion conversion) without annotation can match or exceed supervised baselines that rely on parallel corpora and style labels. confidence: high relevance: medium - claim_id: hybrid_two_stage_pipelines_combining_autoregressive_style_modeling_with_flow role: supports claim: Hybrid two-stage pipelines combining autoregressive style modeling with flow-matching acoustic generation can decouple style and timbre control more effectively than single-stage approaches that use in-context learning to mimic all speech attributes jointly. source: §3.4, Tables 3–5 evidence: Hybrid two-stage pipelines combining autoregressive style modeling with flow-matching acoustic generation can decouple style and timbre control more effectively than single-stage approaches that use in-context learning to mimic all speech attributes jointly. confidence: high relevance: high - claim_id: autoregressive_models_in_zero_shot_tts_consistently_trade_intelligibility_higher role: supports claim: Autoregressive models in zero-shot TTS consistently trade intelligibility (higher WER) for stronger style imitation compared to non-autoregressive alternatives trained on the same data. source: §4.4, Tables 5, 9 evidence: Autoregressive models in zero-shot TTS consistently trade intelligibility (higher WER) for stronger style imitation compared to non-autoregressive alternatives trained on the same data. confidence: high relevance: medium - claim_id: duration_reduction_on_content_tokens_improves_style_transfer_fidelity_by role: supports claim: Duration reduction on content tokens improves style transfer fidelity by removing unit-level duration patterns that encode source speaking style. source: §4.5, Table 6 evidence: Duration reduction on content tokens improves style transfer fidelity by removing unit-level duration patterns that encode source speaking style. confidence: high relevance: medium limitations: - Style imitation evaluations (Table 4) use demo website samples from baseline systems as the test set, meaning evaluation conditions (recording environment, speaker demographics, utterance content) differ between Vevo and baselines. These comparisons are suggestive but not controlled, and the reported improvements should be treated as approximate. - Training is restricted to English audiobook speech (clean, single-domain), and no multilingual or expressive speech experiments are reported. The content-style token vocabulary size (K_s = 4096) and content token vocabulary size (K_c = 32) are empirically selected; the authors note these may not be globally optimal. The AR content-style model has 463M parameters and requires sequential decoding, introducing latency that could be problematic for streaming applications. The self-supervised disentanglement quality depends on HuBERT-Large features, requiring a large pre-trained SSL model as a prerequisite. Style controllability through a single reference utterance may be brittle for rare or highly expressive speaking styles not represented in the audiobook training distribution. caveats: [] - id: 2025.naacl-short.65 published_date: "2025-04-29" entry_date: '2026-07-28' year: 2025 venue: NAACL task: - TTS architecture: - hybrid - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - hybrid_semantic_acoustic_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: ssl_feature_spaces_from_pre_trained_models_encode_cross_speaker role: supports claim: SSL feature spaces from pre-trained models encode cross-speaker structure that enables zero-shot voice transfer through nearest-neighbor retrieval, without speaker-specific training data. source: §2.1, Table 1 evidence: kNN-TTS uses WavLM-Large layer 6 features, where frames from different speakers that are linearly close share phonetic information while preserving speaker identity; kNN retrieval over these features achieves SECS 0.72 and competitive MOS scores trained only on 24h of single-speaker LJSpeech data. confidence: high relevance: medium - claim_id: zero_shot_multi_speaker_tts_competitive_with_large_multi_speaker role: supports claim: Zero-shot multi-speaker TTS competitive with large multi-speaker end-to-end systems can be achieved with single-speaker transcribed training data by delegating speaker identity to inference-time retrieval. source: §4, Table 1 evidence: GlowkNN-TTS (24h training, single speaker) achieves N-MOS and S-MOS within the confidence intervals of HierSpeech++ (2,796h, 7299 speakers) and XTTS (27,282h, multi-speaker) on LibriSpeech test-clean. confidence: high relevance: high - claim_id: retrieval_based_zero_shot_tts_requires_substantially_more_reference_audio role: complicates claim: Retrieval-based zero-shot TTS requires substantially more reference audio from the target speaker than embedding-based approaches to achieve sufficient quality. source: §Limitations, Figure 3b evidence: kNN-TTS requires approximately 30 seconds of target speaker audio for suitable intelligibility and around 1 minute for speaker similarity to plateau, whereas competing embedding-based systems show diminishing returns beyond 10-30 seconds of reference audio. confidence: high relevance: high - claim_id: frame_level_knn_speaker_transfer_does_not_address_speaker_specific role: complicates claim: Frame-level kNN speaker transfer does not address speaker-specific duration and rhythm, leaving prosodic timing patterns fixed to the training speaker. source: §Limitations "Rhythmic variations" evidence: In kNN-TTS, utterance duration is determined entirely by the single-speaker Text-to-SSL model; frame-by-frame retrieval substitutes voice quality but does not adapt speaking rate or rhythm to the target speaker. confidence: high relevance: medium limitations: - 'The reference audio requirement is a practical limitation: kNN-TTS needs approximately 30 seconds of target speaker audio for usable intelligibility, which is notably higher than embedding-based competitors that can function with shorter clips. This restricts applicability in truly few-shot or single-utterance zero-shot scenarios.' - Duration adaptation to the target speaker is not addressed; the speaking rate and rhythm of the output always reflect the training speaker (LJSpeech). The paper proposes Urhythmic-style rhythm modeling as future work. Evaluation is English-only, and while the authors note potential for cross-lingual transfer (via kNN-VC cross-lingual capabilities), this is not demonstrated. Using mel-spectrogram features as an alternative to SSL features was ablated and found completely ineffective, confirming the dependency on WavLM's particular representational structure. caveats: [] - id: '2507.02176' published_date: "2025-07-02" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: [] claims: - claim_id: asv_embeddings_encode_static_anatomical_speech_features_but_systematically_fail role: supports claim: ASV embeddings encode static anatomical speech features but systematically fail to represent dynamic behavioral identity markers such as rhythm and timing patterns. source: §3.2, Figure 1 evidence: Lasso regression predicting handcrafted features from ASV embeddings across LibriSpeech, ARCTIC, and L2-ARCTIC shows high r² for mean pitch, HNR, shimmer, and α-ratio, but near-zero r² for speech rate, voiced and unvoiced segment lengths, and pitch standard deviation across all seven tested ASV models. confidence: high relevance: medium - claim_id: eer_based_speaker_similarity_measurements_in_speech_synthesis_evaluation_are role: complicates claim: EER-based speaker similarity measurements in speech synthesis evaluation are susceptible to confounding factors unrelated to voice identity, which can invalidate comparisons between synthesis systems. source: §3.3, Table 2 evidence: Duration-sorting same-speaker utterances depresses EER from 50% to 30–39% across all ASV models; SNR 20 dB noise reduces EER to 15–38%; equalization shifts cause near-total failure in GE2E. Re-equalization and duration matching restore correct EER. confidence: high relevance: low - claim_id: characterizing_speaker_rhythm_for_identity_assessment_requires_modeling_phoneme_duration role: supports claim: Characterizing speaker rhythm for identity assessment requires modeling phoneme-duration distributions rather than aggregate measures such as mean speech rate. source: §3.4, Figure 2, Table 3 evidence: Many L2-ARCTIC speakers share similar syllable rates but show substantially different voiced segment duration patterns; U3D Wasserstein distances clearly separate same-speaker pairs (avg. 2.15) from nearest-by-speech-rate pairs (18.40) and random pairs (21.53). confidence: high relevance: medium - claim_id: self_supervised_speech_unit_representations_serve_as_language_agnostic_substitutes role: refines claim: Self-supervised speech unit representations serve as language-agnostic substitutes for phoneme labels in rhythm analysis, avoiding the need for forced alignment. source: §3.4, Table 3 evidence: 'U3D using HuBERT-derived unsupervised clusters achieves Wasserstein distance separation between speaker conditions nearly identical to forced-alignment-based phoneme rhythm analysis (same: 2.15 vs. 2.48; nearest: 18.40 vs. 18.37; random: 21.53 vs. 24.43).' confidence: high relevance: medium limitations: - U3D is validated as a discriminative metric (separating speaker pairs) but has not been validated against human perceptual judgments of rhythm similarity. Whether Wasserstein distances correlate with listeners' perception of rhythmic difference between voices remains untested. - The paper is limited to neutral speech, with the authors explicitly noting extension to expressive or conversational speech as future work. Experiments use clean studio-quality recordings (ARCTIC, L2-ARCTIC), so the behavior of confounding factors in in-the-wild multi-condition data remains untested. Recommended mitigation strategies (duration matching, re-equalization) assume access to the same text prompts used in genuine recordings, which may not be feasible in all evaluation settings. U3D's language-agnosticism is argued theoretically but not empirically tested on non-English languages. caveats: [] - id: '2507.04817' published_date: "2025-07-07" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: explicit_interpretable_prosodic_conditioning_in_voice_conversion_can_match_the role: supports claim: Explicit, interpretable prosodic conditioning in voice conversion can match the intelligibility and speaker similarity of systems using implicit or disentangled representations, at a fraction of the parameter cost. source: §5.1.1, Table 2 evidence: Fast-VGAN (~3.2M params) achieves WER of 0.000% and cosine similarity 0.648, competitive with ControlVC (~20M params, WER 0.089%, similarity 0.652) and superior to HiFi-VC (~14M params, WER 2.857%) on seen-speaker VCTK conversion. confidence: high relevance: high - claim_id: adapting_target_speaker_specific_prosodic_parameters_pitch_ambitus_speech_rate role: complicates claim: Adapting target-speaker-specific prosodic parameters (pitch ambitus, speech rate) during voice conversion does not reliably improve perceived speaker identity, and combining multiple prosodic adaptations simultaneously degrades both naturalness and similarity. source: §5.2.1, Table 4 evidence: When ambitus and speech rate dilation are applied jointly, subjective MOS naturalness drops from 3.63 to 3.13 and speaker similarity from 3.47 to 2.99, compared to baseline Fast-VGAN conversion without prosodic parameter adaptation. confidence: high relevance: high - claim_id: neutral_to_expressive_speech_resynthesis_can_be_achieved_by_applying role: supports claim: Neutral-to-expressive speech resynthesis can be achieved by applying prosodic contours from expressive reference recordings to a model trained exclusively on neutral speech, without requiring expressive training data. source: §4.3, §5.1.3, Table 3 evidence: Fast-VGAN trained only on neutral Expresso speaker utterances achieves 0.867 ± 0.029 cosine speaker similarity on expressive resynthesis across confused, happy, and sad conditions, with WER (19.46%) comparable to real recordings (19.38%). confidence: high relevance: medium - claim_id: extreme_prosodic_transformations_in_gan_based_voice_conversion_degrade_naturalness role: complicates claim: Extreme prosodic transformations in GAN-based voice conversion degrade naturalness and speaker similarity, with performance falling off on both sides of the neutral setting in a bell-shaped pattern. source: §5.2.2, Figure 3 evidence: MOS scores for naturalness and speaker similarity peak at unmodified (neutral) settings and decline for both compression and expansion of duration (up to 3x/0.33x), ambitus (up to ±1 octave), and F0 transposition (up to ±1 octave), as measured in subjective listening tests with approximately 20 participants per condition. confidence: high relevance: high limitations: - 'Speaker generalisation is restricted to seen speakers: speaker identity is encoded as a learned lookup embedding, so the model cannot convert to unseen target speakers without retraining. The evaluation uses only 8 VCTK speakers with 2 utterances per speaker pair -- a narrow test set that may not reflect performance across the full VCTK diversity or cross-corpus speakers.' - No demo or code is reported, limiting reproducibility. The speaker similarity metric uses Resemblyzer cosine embeddings, which may not correlate well with human speaker identity judgements; the subjective similarity results already show some misalignment (Fast-VGAN subjective similarity 3.47 vs ControlVC 2.82, while objective cosine similarity is nearly tied at 0.648 vs 0.652). The expressive synthesis experiment uses only 4 Expresso speakers (2M, 2F) and 3 emotions, leaving generalisation to other speakers and emotional categories open. The MBExWN vocoder introduces its own quality ceiling, and the combined system has not been evaluated on noisy or telephony-quality input speech. caveats: [] - id: '2507.01348' published_date: "2025-07-08" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC - TTS architecture: - autoregressive-LM - VAE - GAN relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - autoregressive_token_voice_conversion - vae_latent_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: ctc_regularization_applied_before_vector_quantization_improves_the_temporal_locality role: supports claim: CTC regularization applied before vector quantization improves the temporal locality and temporal robustness of discrete speech content tokens. source: §5.2, Table 2 evidence: SpeechCodeVAE achieves 59% higher De-duplication Efficiency and approximately 9 times better Speed Robustness than CosyVoice-50Hz; ablation without CTC loss collapses Speed Robustness from 0.219 to 0.009, identifying CTC as the critical factor. confidence: high relevance: medium - claim_id: multi_task_learning_with_tts_as_an_auxiliary_objective_compensates role: supports claim: Multi-task learning with TTS as an auxiliary objective compensates for data scarcity in foreign accent conversion, improving both convergence and output quality. source: §3, §5.1, Table 1 evidence: Joint FAC+TTS training on 370 hours of TTS data alongside 9.3 hours of FAC data yields 25% accentedness reduction and WER improvement from 14.4% to 9.1% relative to a standalone FAC baseline. confidence: high relevance: high - claim_id: bert_style_masked_token_restoration_can_correct_stochastic_local_substitution role: supports claim: BERT-style masked token restoration can correct stochastic local substitution errors introduced by autoregressive speech token decoding, improving acoustic continuity. source: §5.3, Table 4 evidence: Removing SpeechRestorer decreases TTS CMOS from 3.850 to 3.629, with the paper attributing the gain to error-correction of spurious token substitutions that cause acoustic discontinuities. confidence: high relevance: medium - claim_id: token_level_post_processing_for_llm_speech_generation_can_correct role: complicates claim: Token-level post-processing for LLM speech generation can correct local substitution errors but fails to address higher-level failure modes such as word skipping and repetition. source: §6 evidence: The paper explicitly states that SpeechRestorer cannot fix skipped words or repetitions, as these require sequence-level rather than token-level correction. confidence: high relevance: medium - claim_id: training_data_scale_rather_than_architectural_design_is_the_primary role: refines claim: Training data scale, rather than architectural design, is the primary driver of quality gaps between LLM-based TTS systems at different performance levels. source: §5.3, Table 4 evidence: SpeechAccentLLM trails NaturalSpeech2 in TTS naturalness (CMOS 3.850 vs. 3.944) despite comparable architecture; the gap is attributed to NS2 training on approximately two orders of magnitude more data. confidence: high relevance: medium limitations: - The FAC evaluation is restricted to four L1 backgrounds from L2-ARCTIC and uses a single TTS model (LJSpeech-trained VITS) to generate native accent counterparts. Generalisation to other accents, speaking styles, or higher-quality native reference speech is untested. - Prosody modelling is acknowledged as incomplete; the Variance Adapter models f0 only and does not capture rhythm, duration patterns, or prosodic phrasing beyond pitch. Timbre reconstruction quality is bounded by the frozen ECAPA-TDNN speaker encoder, which was not trained for the L2/accented-speech domain. SpeechRestorer cannot resolve sequence-level decoding failures (word skipping, repetition), leaving a category of LLM-generated errors unaddressed. The paper does not report total parameter counts for any module, which complicates direct comparison with other systems. caveats: [] - id: '2507.09070' published_date: "2025-07-11" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - autoregressive-LM - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion - flow_matching_voice_conversion claims: - claim_id: audio_codec_and_self_supervised_speech_representations_inherently_encode_speaker role: supports claim: Audio codec and self-supervised speech representations inherently encode speaker identity, making timbre leakage a structural challenge in codec-based voice conversion. source: §4.1, Table 1 evidence: Speaker classification accuracy on LibriHeavy using EnCodec token IDs reaches 96.7%, HuBERT layer 9 discrete tokens 71.7%, and the authors' BEST-RQ tokenizer 82.05%, all substantially above chance. confidence: high relevance: high - claim_id: aligning_audio_encoder_outputs_to_speaker_independent_text_embeddings_via role: supports claim: Aligning audio encoder outputs to speaker-independent text embeddings via monotonic alignment search produces representations with negligible residual speaker identity. source: §4.1, §5, Table 1 evidence: The SemAlign-trained semantic encoder Q_ϕ achieves 2.84% speaker classification accuracy on LibriHeavy, versus 82.05% for the same encoder's raw tokenizer, confirming that the alignment objective removes speaker information that CTC loss alone cannot. confidence: high relevance: high - claim_id: zero_shot_voice_conversion_without_explicit_speaker_verification_embeddings_can role: supports claim: Zero-shot voice conversion without explicit speaker verification embeddings can achieve higher speaker similarity than systems that rely on them. source: §4.2, Tables 2-3 evidence: SemAlignVC achieves the highest SMOS (3.29), WavLM speaker similarity (0.95), ECAPA-TDNN (0.82), and Resemblyzer (0.89) among KNNVC, HierSpeech++, and UniAudio on VCTK and LibriHeavy evaluations, despite using only a reference mel spectrogram excerpt rather than a speaker embedding. confidence: high relevance: high - claim_id: aggressive_timbre_disentanglement_via_text_embedding_alignment_introduces_intelligibility_trade role: complicates claim: Aggressive timbre disentanglement via text-embedding alignment introduces intelligibility trade-offs when BERT-derived representations replace phoneme-based encodings. source: §5, Table 3 evidence: SemAlignVC achieves 12.31% WER on LibriHeavy, compared to HierSpeech++'s 8.24%, with the authors attributing the gap to occasional word substitutions caused by the semantic ambiguity of BERT token representations during generation. confidence: high relevance: high limitations: - The audio tokenizer is trained on a proprietary internal dataset and is described as interchangeable, but its interaction with SemAlign has not been tested with public codecs. Results may not transfer directly to systems using EnCodec, SpeechTokenizer, or other publicly available tokenizers. - The evaluation is English-only and uses VCTK and LibriHeavy, which are relatively clean audiobook and read-speech corpora. Performance on spontaneous speech, accented speech, or noisy conditions is not assessed. The baseline set is modest (three systems), and no ablation isolates the contribution of the flow matching acoustic model relative to SemAlign itself. The WER gap relative to HierSpeech++ remains unexplained beyond the synonym-substitution hypothesis, which is not directly tested. caveats: [] - id: '2507.09282' published_date: "2025-07-12" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS architecture: - autoregressive-LM - diffusion - VAE relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion - diffusion_voice_conversion - vae_latent_voice_conversion claims: - claim_id: the_normalising_tendency_of_zero_shot_tts_models_can_be role: supports claim: The normalising tendency of zero-shot TTS models can be deliberately exploited to filter atypical speech characteristics while preserving general voice timbre. source: §2.2, §4, Table 1 evidence: ClaritySpeech applies XTTSv2 to dementia-affected speech without fine-tuning, reducing adversarial dementia detection F1 by 16% on ADReSS (total mean 0.70 to 0.59) while maintaining speaker similarity of 0.50, as the model smooths prosodic irregularities learned from diverse fluent training data. confidence: high relevance: high - claim_id: speaker_identity_preservation_and_speech_naturalness_trade_off_against_each role: complicates claim: Speaker identity preservation and speech naturalness trade off against each other when zero-shot TTS is applied to atypical speech. source: §4, Table 1 evidence: StyleTTS2 achieves UTMOS 2.86 and WER 0.04 on ADReSS but speaker similarity of only 0.36, while XTTSv2 achieves UTMOS 2.15 and speaker similarity 0.50, showing that models that normalise most aggressively sacrifice voice fidelity. confidence: high relevance: high - claim_id: text_level_content_correction_and_acoustic_re_synthesis_provide_complementary role: supports claim: Text-level content correction and acoustic re-synthesis provide complementary privacy protection that neither provides alone in disordered speech obfuscation. source: §4, Table 2 evidence: Ablation on ADReSS shows that removing text obfuscation raises text-modality F1 by 10% (0.59 to 0.68), while removing zero-shot TTS collapses speaker similarity to 0.12 and degrades privacy protection; the full pipeline requires both components. confidence: high relevance: medium - claim_id: pipeline_based_speech_obfuscation_systems_that_chain_asr_text_processing role: complicates claim: Pipeline-based speech obfuscation systems that chain ASR, text processing, and TTS carry latency that precludes real-time deployment on standard hardware. source: §4, Table 4 evidence: ClaritySpeech achieves a mean real-time factor of 6.07 on CPU for 3-6 second audio samples; ASR alone contributes RTF 3.01 and TTS contributes RTF 1.71, making live speech obfuscation impractical without GPU acceleration. confidence: high relevance: low limitations: - 'Evaluation uses small, low-diversity datasets (ADReSS: 690 samples, ADReSSo: 947 samples) from a single task (cookie-theft description). Generalisability to other dementia types, languages, or conversational speech is untested.' - The adaptive adversary setting, in which the detection model trains on both original and obfuscated samples, remains difficult to defeat — mean F1 drops are modest (roughly 5 percentage points) under adaptive conditions. No comparison with speaker-dependent fine-tuned TTS models is provided, leaving open whether fine-tuning would offer a better privacy-utility trade-off despite the privacy risks. The system is English-only. Latency (RTF 6.07) rules out real-time applications without hardware acceleration. The effect on the speaker's perceived identity from the listener's perspective is measured only automatically via ECAPA-TDNN embeddings, not through subjective listening tests. caveats: [] - id: '2507.09310' published_date: "2025-07-12" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC - TTS architecture: - VAE relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: minor method_family: - vae_latent_voice_conversion claims: - claim_id: implicit_style_modeling_via_an_auxiliary_reconstruction_loss_can_preserve role: supports claim: Implicit style modeling via an auxiliary reconstruction loss can preserve speaking style characteristics in voice conversion without requiring explicit acoustic feature extraction. source: §3.3, §3.4, Table 2 evidence: A style reconstruction loss using a frozen Lombard/neutral classifier achieves SIIB scores comparable to explicit conditioning on f0, mgc0, and mgc1 across male and female target speakers, with no statistically significant differences in most conditions. confidence: high relevance: high - claim_id: the_effectiveness_of_explicit_prosodic_features_for_style_preserving_voice role: complicates claim: The effectiveness of explicit prosodic features for style-preserving voice conversion depends on speaker gender, limiting the generalizability of feature-based conditioning approaches. source: §3.4, Table 2 evidence: F0 conditioning improves SIIB for male target speakers but is detrimental for female target speakers at both SNR-1 and SNR-3; spectral tilt and energy (mgc0+mgc1) are beneficial across genders. confidence: high relevance: high - claim_id: speaker_identity_remains_perceptible_to_listeners_in_noisy_conditions_confirming role: supports claim: Speaker identity remains perceptible to listeners in noisy conditions, confirming that speaker similarity is a relevant evaluation dimension for intelligibility-enhancing voice conversion. source: §2.3, Figure 1, §3.4, Figure 6 evidence: Pilot study results show that listeners maintain consistent similarity rankings between speakers at SNR-1 and SNR-3 noise levels, and the implicit conditioning VC model preserves speaker similarity comparably to the CopyCat baseline. confidence: high relevance: high - claim_id: combining_implicit_and_explicit_style_conditioning_does_not_consistently_improve role: complicates claim: Combining implicit and explicit style conditioning does not consistently improve intelligibility over either approach alone, and can degrade performance in some configurations. source: §3.4, Figure 5, Table 2 evidence: Fusion of Ls with individual explicit features (e.g., Ls+f0 for female targets) reduces SIIB compared to Ls alone; only Ls+mgc0+mgc1 reliably improves over Ls in most conditions, and gains are inconsistent across genders. confidence: high relevance: medium limitations: - The model does not modify duration, which is an observed acoustic correlate of the Lombard effect, potentially leaving an intelligibility benefit unexploited. The dataset is small (54 speakers, 100 short utterances each) and recorded under a constrained sentence task that produces somewhat robotic prosody, limiting the naturalness of synthesised samples. Only two target speakers are evaluated in the VC experiments, making it difficult to assess robustness across a wider voice population. The authors propose extending to larger conversational datasets, evaluating downstream Lombard TTS intelligibility using transcriptions and hearing-loss-targeted metrics, and exploring adversarial disentanglement to control Lombard intensity independently of speaker identity. caveats: [] - id: '2506.18296' published_date: "2025-07-15" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - TTS - VC - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: [] claims: - claim_id: non_anonymous_speaker_corpora_with_publicly_identifiable_voices_enable_more role: supports claim: Non-anonymous speaker corpora with publicly identifiable voices enable more rigorous subjective evaluations of speaker similarity in TTS and VC systems. source: §1, §3.1 evidence: JIS assigns stage names to 169 Japanese live idol speakers, allowing experiment designers to recruit listeners familiar with the speakers, enabling discrimination of subtle voice characteristics that anonymous corpus evaluations cannot capture. confidence: high relevance: medium - claim_id: automatic_mos_predictors_trained_on_tts_generated_speech_may_underestimate role: complicates claim: Automatic MOS predictors trained on TTS-generated speech may underestimate audio quality when applied to recordings of non-professional speakers, even under studio conditions. source: §4.2.1 evidence: JIS Speech A (studio-recorded) achieves a mean UTMOS of 3.4 compared to JVS parallel100's 3.7, with the gap attributed to linguistic mismatch in UTMOS training data and speech hesitations inherent to non-professional speakers rather than recording quality differences. confidence: high relevance: medium - claim_id: speaking_style_and_communicative_context_introduce_systematic_variation_in_speaker role: supports claim: Speaking style and communicative context introduce systematic variation in speaker embeddings that interacts with speaker identity, presenting a challenge for style-robust speaker representation. source: §4.2.2 evidence: ECAPA-TDNN embeddings of JIS speakers show that specific speaking styles (energetic post-performance greetings, intimate photo-session speech) produce cross-speaker clusters in t-SNE, partially overriding individual speaker identity, while speech expressing personal individuality is more dispersed. confidence: high relevance: high limitations: - The corpus is small (17 hours, 169 speakers) and covers only young Japanese female voices, restricting direct use for general-purpose or multilingual TTS training. Distribution requires a signed agreement and is limited to non-commercial basic research. Speech B recording conditions are unspecified and variable across groups, introducing inconsistencies in audio quality. No TTS or VC model is trained on JIS in this work, leaving empirical validation of the corpus's utility for model development open. caveats: [] - id: '2507.10985' published_date: "2025-07-15" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence current_role: minor method_family: [] claims: - claim_id: acoustic_deviation_between_a_learner_utterance_and_a_personalized_voice role: supports claim: Acoustic deviation between a learner utterance and a personalized voice-cloned reference correlates with mispronunciation at the word level. source: §4, Table 2 evidence: MFCC-DTW distances are consistently higher for mispronounced words than correctly pronounced words across all four L2-ARCTIC speakers tested (mean deviation of 0.027–0.028 units on average), confirming the core deviation hypothesis. confidence: high relevance: medium - claim_id: acoustic_deviation_metrics_derived_from_voice_cloning_exhibit_high_per role: complicates claim: Acoustic deviation metrics derived from voice cloning exhibit high per-speaker variability, making universal calibration insufficient for reliable mispronunciation detection. source: §4, Table 1 evidence: Classification accuracy ranges from 0.461 to 0.646 across four speakers; the authors note that per-individual models would likely improve results. confidence: high relevance: high - claim_id: mispronunciation_detection_systems_based_on_acoustic_distance_alone_require_an role: complicates claim: Mispronunciation detection systems based on acoustic distance alone require an explicit ambiguity class when threshold-based decision rules cannot confidently separate correct from incorrect pronunciations. source: §3.6 evidence: The system defines an AMBIGUOUS output for samples falling between class-specific KDE thresholds, but the paper does not report how frequently this category occurs in practice. confidence: high relevance: medium limitations: - No comparison against established CAPT baselines (e.g., GOP scoring, end-to-end neural classifiers) is provided, making it impossible to assess whether the proposed approach is competitive. All experiments use only four speakers from L2-ARCTIC, and the reliance on the proprietary ElevenLabs API prevents reproducibility. - The system produces an AMBIGUOUS output category but does not quantify its frequency, leaving the practical coverage of the detector unclear. Precision and recall trade-offs across speakers suggest that a single model calibrated on all speakers is suboptimal; speaker-specific models are proposed as future work. Extension to under-resourced languages and real-time implementation remain open. caveats: [] - id: 2025.acl-demo.37 published_date: "2025-07-27" entry_date: '2026-07-28' year: 2025 venue: ACL task: - VC architecture: - hybrid relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence - evaluation_caution current_role: active_evidence method_family: - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: articulatory_feature_spaces_enable_interpretable_content_speaker_disentanglement_in_voice role: supports claim: Articulatory feature spaces enable interpretable content-speaker disentanglement in voice conversion without sacrificing intelligibility relative to SSL-based approaches. source: §5.3, Table 1 evidence: Articulatory feature spaces enable interpretable content-speaker disentanglement in voice conversion without sacrificing intelligibility relative to SSL-based approaches. confidence: high relevance: high - claim_id: real_time_zero_shot_voice_conversion_on_cpu_hardware_is role: supports claim: Real-time zero-shot voice conversion on CPU hardware is achievable below 70 ms end-to-end latency while maintaining naturalness MOS above 3.8. source: §3.6, Table 1 evidence: Real-time zero-shot voice conversion on CPU hardware is achievable below 70 ms end-to-end latency while maintaining naturalness MOS above 3.8. confidence: high relevance: high - claim_id: causal_ddsp_vocoders_conditioned_on_articulatory_features_provide_competitive_synthesis role: supports claim: Causal DDSP vocoders conditioned on articulatory features provide competitive synthesis quality compared to GAN-based alternatives at substantially lower computational cost. source: §2.3, §3.5 evidence: Causal DDSP vocoders conditioned on articulatory features provide competitive synthesis quality compared to GAN-based alternatives at substantially lower computational cost. confidence: high relevance: medium - claim_id: voice_conversion_systems_trained_with_static_noise_augmentation_degrade_gracefully role: complicates claim: Voice conversion systems trained with static noise augmentation degrade gracefully down to approximately 20 dB SNR input but fail at 10 dB, suggesting a practical noise floor for real-time deployment. source: §5.4 evidence: Voice conversion systems trained with static noise augmentation degrade gracefully down to approximately 20 dB SNR input but fail at 10 dB, suggesting a practical noise floor for real-time deployment. confidence: high relevance: high limitations: - '- EMA representation omits nasal cavity and laryngeal dynamics, limiting modeling of nasal sounds and vocal fry. - Pseudo-EMA labels come from a WavLM model pretrained on English; cross-lingual performance is limited. - Sensitivity to input quality below 20 dB SNR, especially for white noise. - Model weights will not be open-sourced due to misuse concerns. - Future work: prompt-free conversion by offline target speaker design (gender, age, emotion, accent).' caveats: [] - id: 2025.acl-long.790 published_date: "2025-07-27" entry_date: '2026-07-28' year: 2025 venue: ACL task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: self_consistency_training_enables_shortcut_flow_matching_to_match_full role: supports claim: Self-consistency training enables shortcut flow matching to match full-step quality in voice conversion with as few as two inference steps. source: §4.2, Table 1 evidence: R-VC at NFE=2 matches NFE=10 across all quality metrics (SECS 0.930 vs 0.931, UTMOS 4.1 vs 4.1, QMOS 4.03 vs 4.05, SMOS 4.11 vs 4.12) while reducing inference time by 2.83x; vanilla CFM degrades sharply below 10 steps. confidence: high relevance: high - claim_id: explicit_rhythm_modeling_via_a_target_conditioned_duration_model_substantially role: supports claim: Explicit rhythm modeling via a target-conditioned duration model substantially improves emotion style transfer in zero-shot VC. source: §4.3, §4.5, Table 2, Table 4 evidence: Removing the duration module from R-VC drops the emotion score from 0.59 to 0.425 on the ESD dataset, while also increasing WER slightly; baselines that preserve source rhythm score 0.395-0.489. confidence: high relevance: high - claim_id: fine_grained_duration_prediction_in_non_autoregressive_models_introduces_instability role: complicates claim: Fine-grained duration prediction in non-autoregressive models introduces instability in voice conversion that coarser duration strategies do not fully resolve. source: §7, Table 4 evidence: R-VC's masked transformer duration model produces occasional over-extended pronunciations; sentence-level duration as a fallback yields worse WER (9.86 vs 6.95) and UTMOS (3.58 vs 3.85), offering no stability improvement in practice. confidence: high relevance: high - claim_id: data_perturbation_before_discrete_content_tokenisation_reduces_timbre_leakage_more role: supports claim: Data perturbation before discrete content tokenisation reduces timbre leakage more effectively than relying on the self-supervised representation alone. source: §4.5, Table 4 evidence: Removing pitch perturbation before HuBERT token extraction degrades WER from 3.51 to 7.28 and speaker similarity from 0.930 to 0.869, confirming that perturbation actively suppresses content-irrelevant speaker information. confidence: high relevance: high limitations: - 'The masked transformer duration model has a known instability: inaccurate predictions cause over-extended pronunciations. Sentence-level duration as an alternative proved worse in both stability and quality, leaving robust duration modeling as an unresolved challenge.' - The system is evaluated only on English (MLS, LibriSpeech, ESD) and English Seed-TTS subsets; generalisation to cross-lingual or multilingual VC is untested. Training data (20k hours) is smaller than top competitors such as CosyVoice-VC (171k hours), which makes speaker similarity comparisons somewhat favourable to R-VC but also means that high-similarity performance on out-of-distribution accents or recording conditions is unknown. The RTF of 0.12 using 2-step inference is faster than most flow-matching competitors but still 20% slower than non-diffusion methods (FACodec-VC RTF 0.10). caveats: [] - id: 2025.acl-long.87 published_date: "2025-07-27" entry_date: '2026-07-28' year: 2025 venue: ACL task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: combining_asr_derived_phonetic_features_and_quantized_self_supervised_representations role: supports claim: Combining ASR-derived phonetic features and quantized self-supervised representations via adaptive fusion reduces timbre leakage while preserving paralinguistic content in zero-shot voice conversion. source: §5.3, Table 3 evidence: Removing the PPG branch (WavLM-only) causes SMOS to drop from 4.11 to 3.07 and SECS from 0.71 to 0.45 on LibriTTS, indicating that SSL features alone carry substantial timbre leakage; removing the SSL branch degrades NMOS and WER, confirming PPGs alone lose paralinguistic richness. confidence: high relevance: high - claim_id: flow_matching_provides_faster_inference_than_diffusion_based_voice_conversion role: supports claim: Flow matching provides faster inference than diffusion-based voice conversion systems without sacrificing speaker similarity or naturalness. source: §5.1, Table 1 evidence: Takin-VC achieves RTF 0.154, lower than DiffVC (0.294), NS2VC (0.347), and SeedVC (0.341), while simultaneously outperforming these baselines on NMOS, SMOS, and SECS. confidence: high relevance: high - claim_id: global_time_invariant_speaker_embeddings_are_insufficient_for_robust_timbre role: complicates claim: Global, time-invariant speaker embeddings are insufficient for robust timbre modeling in expressive zero-shot voice conversion. source: §5.3, Table 4 evidence: Removing the context-aware cross-attention module (which aligns source content with target timbre dynamically) drops SMOS from 4.11 to 3.61 and SECS from 0.71 to 0.58, while the memory-augmented module removal drops SECS to 0.52. Both modules provide content-sensitive timbre conditioning beyond a static speaker embedding alone. confidence: high relevance: high - claim_id: cross_gender_voice_conversion_consistently_yields_lower_speaker_similarity_than role: complicates claim: Cross-gender voice conversion consistently yields lower speaker similarity than same-gender conversion even in well-trained systems. source: §5.2, Table 2 evidence: 'On the large-scale multilingual dataset, same-gender pairs (F2F: SECS 0.74; M2M: 0.73) outperform cross-gender pairs (F2M: 0.71; M2F: 0.70) in speaker embedding cosine similarity, a gap that persists across all conversion directions.' confidence: high relevance: high - claim_id: quantizing_self_supervised_speech_features_before_content_encoding_reduces_timbre role: refines claim: Quantizing self-supervised speech features before content encoding reduces timbre leakage more effectively than using continuous SSL representations directly. source: §3.2, §5.3, Table 3 evidence: The RVQ quantizer (codebook size 8,200) applied to WavLM features is the key mechanism for timbre suppression in the hybrid encoder; ablation with WavLM-only (continuous features without adaptive fusion) shows SECS drops to 0.45 compared to 0.71 for the full model, consistent with timbre leakage from unquantized SSL features. confidence: high relevance: high limitations: - All large-scale training data (500k hours) and the 100-speaker evaluation set are proprietary and not publicly available. The large-scale results cannot be reproduced by external researchers, and it is unclear how much of the gain over competitive baselines is attributable to data scale rather than the proposed modules. - The paper does not include targeted evaluation of paralinguistic preservation (breathing, crying, emotion transfer), despite listing this as a primary contribution. NMOS and SMOS measure general naturalness and speaker similarity but are not designed to capture expressive fidelity specifically. Speech editing under zero-shot conditions is acknowledged as out of scope and a direction for future work. Ethical risks from voice impersonation are noted but no technical mitigations are proposed. caveats: [] - id: '2508.00317' published_date: "2025-08-01" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - evaluation_caution current_role: active_evidence method_family: [] claims: - claim_id: fine_tuning_self_supervised_speech_representations_is_sufficient_to_achieve role: supports claim: Fine-tuning self-supervised speech representations is sufficient to achieve high MOS prediction correlation in-domain, even with small labeled datasets, but this does not transfer reliably to out-of-domain evaluation settings. source: §II.A evidence: Fine-tuning self-supervised speech representations is sufficient to achieve high MOS prediction correlation in-domain, even with small labeled datasets, but this does not transfer reliably to out-of-domain evaluation settings. confidence: high relevance: low - claim_id: automatic_mos_predictors_consistently_fail_to_discriminate_among_high_quality role: complicates claim: Automatic MOS predictors consistently fail to discriminate among high-quality speech generation systems whose naturalness approaches human levels, indicating a ceiling effect in current SQA methodology. source: §II.C evidence: Automatic MOS predictors consistently fail to discriminate among high-quality speech generation systems whose naturalness approaches human levels, indicating a ceiling effect in current SQA methodology. confidence: high relevance: medium - claim_id: community_challenges_with_well_documented_baselines_and_open_datasets_accelerate role: supports claim: Community challenges with well-documented baselines and open datasets accelerate research progress in evaluation methodology more reliably than individual paper contributions. source: §I, §II.E evidence: Community challenges with well-documented baselines and open datasets accelerate research progress in evaluation methodology more reliably than individual paper contributions. confidence: high relevance: low - claim_id: expanding_automatic_quality_assessment_beyond_speech_to_music_and_general role: supports claim: Expanding automatic quality assessment beyond speech to music and general audio requires rethinking evaluation dimensions beyond MOS, as production quality, content enjoyment, and textual alignment reflect distinct perceptual dimensions that do not collapse to a single score. source: §II.D, §IV evidence: Expanding automatic quality assessment beyond speech to music and general audio requires rethinking evaluation dimensions beyond MOS, as production quality, content enjoyment, and textual alignment reflect distinct perceptual dimensions that do not collapse to a single score. confidence: high relevance: low limitations: - The paper's central argument — that challenges and open-source toolkits drive progress — is supported by citation count trends rather than a controlled study. Alternative explanations (larger models, more data, general SSL pre-training improvements) are not ruled out. - The paper does not provide an empirical comparison of SQA toolkit accuracy or calibration quality. The survey of toolkits (Table II) covers feature availability but not predictive performance on held-out data. Several tracks across the challenge series were identified as too easy (in-domain, strong baseline), raising questions about how to design more discriminative future tracks. The extension to music and general audio quality opens fundamentally different perceptual dimensions that MOS-style scales may not adequately capture. The authors acknowledge that expressive TTS, multilingual speech, and prompt-based TTS remain underserved by current SQA benchmarks. caveats: [] - id: '2508.02038' published_date: "2025-08-04" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - VC architecture: - autoregressive-LM - flow-matching - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion - flow_matching_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: difference_in_means_emotion_embeddings_computed_from_paired_emotional_and role: supports claim: Difference-in-means emotion embeddings, computed from paired emotional and neutral speech, enable speaker-independent emotion representations that generalise across speakers. source: §2.2 evidence: Difference-in-means emotion embeddings, computed from paired emotional and neutral speech, enable speaker-independent emotion representations that generalise across speakers. confidence: high relevance: high - claim_id: enforcing_orthogonality_between_speaker_and_emotion_embedding_spaces_via_a role: supports claim: Enforcing orthogonality between speaker and emotion embedding spaces via a cross-dot-product loss enables independent control of voice identity and emotional style without degrading either. source: §2.3, Table 1 evidence: Enforcing orthogonality between speaker and emotion embedding spaces via a cross-dot-product loss enables independent control of voice identity and emotional style without degrading either. confidence: high relevance: medium - claim_id: unified_joint_modeling_of_voice_cloning_and_emotion_control_produces role: supports claim: Unified joint modeling of voice cloning and emotion control produces higher speaker similarity and emotional naturalness than systems that address the two capabilities separately. source: §4.1, §4.2, Tables 1–2 evidence: Unified joint modeling of voice cloning and emotion control produces higher speaker similarity and emotional naturalness than systems that address the two capabilities separately. confidence: high relevance: high - claim_id: expressive_emotional_tts_systems_that_include_naturalistic_vocalized_fillers_exhibit role: supports claim: Expressive emotional TTS systems that include naturalistic vocalized fillers exhibit higher word error rates on clean-transcript benchmarks, even when perceived speech quality is high. source: §4.4, Table 4–5 evidence: Expressive emotional TTS systems that include naturalistic vocalized fillers exhibit higher word error rates on clean-transcript benchmarks, even when perceived speech quality is high. confidence: high relevance: medium - claim_id: gender_imbalance_in_emotional_speech_training_data_produces_systematic_differences role: supports claim: Gender imbalance in emotional speech training data produces systematic differences in emotion recognition accuracy, with male speakers underperforming female speakers across most emotion categories. source: §4.4, Figure 6 evidence: Gender imbalance in emotional speech training data produces systematic differences in emotion recognition accuracy, with male speakers underperforming female speakers across most emotion categories. confidence: high relevance: medium limitations: - '- Requires paired emotional/neutral speech data from the same speaker for emotion embedding extraction, which limits scalability and language coverage. - Higher WER on Mandarin AISHELL-3 relative to the CosyVoice1 baseline: the system inserts vocalized fillers (ah, um) that are natural in expressive speech but inflate WER against clean transcripts. - Model size not reported; training efficiency uncharacterized. - Evaluation is limited to 7 emotions — more naturalistic, multi-emotion or low-intensity affects are not tested. - No streaming or latency evaluation.' caveats: [] - id: '2508.04996' published_date: "2025-08-07" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: ssl_features_improve_paralinguistic_expressiveness_in_voice_conversion_but_introduce role: supports claim: SSL features improve paralinguistic expressiveness in voice conversion but introduce timbre leakage and noise sensitivity that require explicit mitigation. source: §I, §II.B evidence: SSL features improve paralinguistic expressiveness in voice conversion but introduce timbre leakage and noise sensitivity that require explicit mitigation. confidence: high relevance: high - claim_id: random_feature_erasure_at_training_time_can_reduce_a_model role: supports claim: Random feature erasure at training time can reduce a model's over-reliance on information-rich but noise-sensitive representations without information bottleneck machinery. source: §II.B evidence: Random feature erasure at training time can reduce a model's over-reliance on information-rich but noise-sensitive representations without information bottleneck machinery. confidence: high relevance: medium - claim_id: implicit_alignment_borrowed_from_non_autoregressive_tts_can_improve_noise role: supports claim: Implicit alignment borrowed from non-autoregressive TTS can improve noise robustness in voice conversion by preventing the model from over-reconstructing noise-carrying source frames. source: §II.C evidence: Implicit alignment borrowed from non-autoregressive TTS can improve noise robustness in voice conversion by preventing the model from over-reconstructing noise-carrying source frames. confidence: high relevance: high - claim_id: shortcut_models_reduce_flow_matching_inference_steps_by_an_order role: supports claim: Shortcut Models reduce flow-matching inference steps by an order of magnitude with only marginal quality loss in voice conversion. source: §II.D, Table I evidence: Shortcut Models reduce flow-matching inference steps by an order of magnitude with only marginal quality loss in voice conversion. confidence: high relevance: high - claim_id: asr_based_bottleneck_features_and_ssl_representations_are_complementary_the role: supports claim: 'ASR-based bottleneck features and SSL representations are complementary: the former provides noise-robust linguistic content, the latter contributes paralinguistic fidelity that ASR training suppresses.' source: §I, §II.A evidence: 'ASR-based bottleneck features and SSL representations are complementary: the former provides noise-robust linguistic content, the latter contributes paralinguistic fidelity that ASR training suppresses.' confidence: high relevance: medium limitations: - The model cannot synthesise arbitrarily long utterances. The implicit alignment mechanism introduces a maximum-length constraint analogous to that in E2TTS-style TTS systems. The authors flag this as a known limitation without providing an upper bound or workaround. - 'Evaluation scale is small: 100 clean and 50 noisy test utterances is insufficient to draw strong conclusions about generalisation across noise types or speaking styles. The noisy set recording conditions are not fully documented. Comparison to other noise-robust VC systems such as NORO ([[2411.19770|NORO]]) is absent — only Seed-VC and a VITS-VC internal baseline are used.' - 'The prosody preservation trade-off is acknowledged: REF-VC preserves source prosody well, but users may prefer target speaker style transfer instead. Future work is needed to support simultaneous prosody preservation and style transfer.' - Singing voice conversion is mentioned as a capability but receives no quantitative evaluation. caveats: [] - id: '2508.06890' published_date: "2025-08-09" entry_date: '2026-07-28' year: 2025 venue: ASRU task: - VC architecture: - GAN - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion - transformer_encoder_decoder_voice_conversion claims: - claim_id: frame_level_emotion_representations_improve_speaker_emotion_classification_accuracy_and role: supports claim: Frame-level emotion representations improve speaker emotion classification accuracy and prosody transfer fidelity over utterance-level representations in voice conversion. source: §IV.C, Table I evidence: Frame-level emotion representations improve speaker emotion classification accuracy and prosody transfer fidelity over utterance-level representations in voice conversion. confidence: high relevance: high - claim_id: adversarial_disentanglement_via_gradient_reversal_layers_reduces_phonetic_leakage_into role: supports claim: Adversarial disentanglement via gradient reversal layers reduces phonetic leakage into emotion embeddings, improving intelligibility under cross-linguistic-content conversion. source: §IV.C, Table I evidence: Adversarial disentanglement via gradient reversal layers reduces phonetic leakage into emotion embeddings, improving intelligibility under cross-linguistic-content conversion. confidence: high relevance: medium - claim_id: explicit_conditioning_on_extracted_prosodic_features_f0_and_energy_from role: supports claim: Explicit conditioning on extracted prosodic features (F0 and energy) from an emotion reference transfers temporal dynamics more faithfully than implicit prediction from latent codes. source: §IV.A, Table I evidence: Explicit conditioning on extracted prosodic features (F0 and energy) from an emotion reference transfers temporal dynamics more faithfully than implicit prediction from latent codes. confidence: high relevance: medium - claim_id: training_time_prosody_augmentation_through_temporal_shifting_and_warping_improves role: supports claim: Training-time prosody augmentation through temporal shifting and warping improves robustness of prosody transfer under mismatched reference conditions without sacrificing naturalness. source: §IV.C, Table I evidence: Training-time prosody augmentation through temporal shifting and warping improves robustness of prosody transfer under mismatched reference conditions without sacrificing naturalness. confidence: high relevance: medium limitations: - Training and primary evaluation use only the English ESD corpus — 350 parallel utterances across 10 speakers and 5 emotion categories. This is a narrow domain; generalisation to spontaneous, noisy, or multilingual emotional speech is entirely untested. - The small, parallel ESD corpus makes it difficult to assess whether the disentanglement holds under more naturalistic or non-parallel conditions. The ablation study evaluates the seen scenario only; it is not clear whether the ablated variants degrade similarly on unseen speakers and emotions. Speaker classification accuracy (SCA) is reported as a zero-shot metric for the seen-speaker scenario but becomes undefined for unseen speakers, so that dimension of the zero-shot evaluation lacks a corresponding metric. Model size and inference speed are not reported, which matters for the real-time dubbing applications the paper motivates. caveats: [] - id: '2508.08399' published_date: "2025-08-11" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - codec architecture: - VAE relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion claims: - claim_id: fully_discrete_disentanglement_of_phonetic_prosodic_and_speaker_information_in role: complicates claim: Fully discrete disentanglement of phonetic, prosodic, and speaker information in a speech codec is achievable without phoneme labels or F0 supervision, at the cost of a small reconstruction quality degradation. source: §III, §IV.B, Table II evidence: Fully discrete disentanglement of phonetic, prosodic, and speaker information in a speech codec is achievable without phoneme labels or F0 supervision, at the cost of a small reconstruction quality degradation. confidence: high relevance: low - claim_id: quantizing_speaker_vectors_into_discrete_codes_reduces_speaker_identity_fidelity role: complicates claim: Quantizing speaker vectors into discrete codes reduces speaker identity fidelity compared to continuous speaker representations, posing a fundamental trade-off between LLM compatibility and speaker retention. source: §IV.B, Table III evidence: Quantizing speaker vectors into discrete codes reduces speaker identity fidelity compared to continuous speaker representations, posing a fundamental trade-off between LLM compatibility and speaker retention. confidence: high relevance: high - claim_id: instance_normalization_of_ssl_residual_features_provides_a_label_free role: supports claim: Instance normalization of SSL residual features provides a label-free mechanism to separate time-invariant speaker statistics from time-variant prosodic content. source: §III.B evidence: Instance normalization of SSL residual features provides a label-free mechanism to separate time-invariant speaker statistics from time-variant prosodic content. confidence: high relevance: medium - claim_id: fully_discrete_speech_codecs_can_match_conventional_voice_conversion_methods role: supports claim: Fully discrete speech codecs can match conventional voice conversion methods on intelligibility and naturalness while enabling attribute manipulation through codebook-level operations. source: §IV.B, Table III evidence: Fully discrete speech codecs can match conventional voice conversion methods on intelligibility and naturalness while enabling attribute manipulation through codebook-level operations. confidence: high relevance: high limitations: - All experiments use LibriSpeech clean speech (16 kHz, studio conditions); performance on noisy, spontaneous, or out-of-domain speech is untested. The one-shot VC evaluation uses only two reference speakers (one male, one female), limiting statistical confidence in the speaker similarity results. - The model is not tested on any downstream application (TTS, ASR, speech LM), despite this being the stated motivation. Whether the disentangled discrete tokens actually improve over non-disentangled tokens on downstream tasks remains an open question — the paper acknowledges this as future work. The GRVQ codebook dimensionality analysis shows a clear trade-off between bitrate and speaker identity, but optimal bitrate allocation across the three streams is not systematically explored. Prosody quantization codebook interpretability beyond F0 correlation (e.g., energy, duration, speaking rate) is not investigated. caveats: [] - id: '2508.08961' published_date: "2025-08-12" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - SCA - VC architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: separating_the_token_used_for_llm_input_from_the_token role: supports claim: Separating the token used for LLM input from the token used for generation output can resolve the information-level conflict that makes joint optimisation of understanding and generation tasks difficult in a shared-token speech LLM. source: §DualSpeechLM, §Results and Analyses evidence: Separating the token used for LLM input from the token used for generation output can resolve the information-level conflict that makes joint optimisation of understanding and generation tasks difficult in a shared-token speech LLM. confidence: high relevance: medium - claim_id: training_a_speech_tokenizer_directly_against_a_text_llm_s role: supports claim: Training a speech tokenizer directly against a text LLM's next-token prediction objective is more effective at reducing the speech-text modality gap than optimising against ASR or SSL reconstruction losses alone. source: §USTokenizer, Table 1 evidence: Training a speech tokenizer directly against a text LLM's next-token prediction objective is more effective at reducing the speech-text modality gap than optimising against ASR or SSL reconstruction losses alone. confidence: high relevance: medium - claim_id: understanding_task_supervision_produces_representations_that_transfer_to_generation_quality role: supports claim: Understanding-task supervision produces representations that transfer to generation quality improvements, but the converse — generation-task supervision improving understanding — is weaker and less consistent. source: §Ablation Study, §H. Discussion evidence: Understanding-task supervision produces representations that transfer to generation quality improvements, but the converse — generation-task supervision improving understanding — is weaker and less consistent. confidence: high relevance: medium - claim_id: stochastic_conditioning_during_training_exposing_a_generation_module_to_varied role: supports claim: Stochastic conditioning during training (exposing a generation module to varied subsets of its conditioning signals) improves robustness to imperfect upstream predictions at inference time. source: §Ablation Study, Table 6 evidence: Stochastic conditioning during training (exposing a generation module to varied subsets of its conditioning signals) improves robustness to imperfect upstream predictions at inference time. confidence: high relevance: medium limitations: - The entire evaluation is conducted at 4.5K hours of training data with parameter-efficient LoRA fine-tuning. The claim that USTokens reduce data requirements is plausible but untested at the scale (70K–570K hours) where competing systems are evaluated. Whether the dual-token architecture and the understanding-driven tokeniser remain advantageous at scale is an open question. - No code or demo is linked in the paper, limiting reproducibility. The 4.5K-hour training regime excludes noisy, in-the-wild, and multilingual data, so generalisation to these conditions is untested despite the paper's stated future direction of expanding to multilingual and cross-domain data. The USTokenizer's understanding-driven loss requires a frozen LLM during tokeniser training, adding a significant computational overhead at the tokenisation stage (288% memory increase) even if this overhead disappears at DualSpeechLM inference. The model size of the full system (Phi-3.5-3B + AcousticGPT) is not explicitly stated in aggregate, and the AcousticGPT's token generation speed relative to real-time is not reported. caveats: [] - id: interspeech-2025-0115 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - codec architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - transformer_encoder_decoder_voice_conversion claims: - claim_id: even_codecs_explicitly_trained_with_disentanglement_objectives_fail_to_cleanly role: complicates claim: Even codecs explicitly trained with disentanglement objectives fail to cleanly separate pitch from other speech attributes in their token embeddings. source: §2.3, §2.4 evidence: Even codecs explicitly trained with disentanglement objectives fail to cleanly separate pitch from other speech attributes in their token embeddings. confidence: high relevance: medium - claim_id: linguistic_content_in_neural_audio_codec_representations_concentrates_in_the role: supports claim: Linguistic content in neural audio codec representations concentrates in the lowest RVQ scales regardless of whether distillation was used, but leaks into higher scales when the frame rate is very low. source: §2.1 evidence: Linguistic content in neural audio codec representations concentrates in the lowest RVQ scales regardless of whether distillation was used, but leaks into higher scales when the frame rate is very low. confidence: high relevance: low - claim_id: a_masked_autoencoder_framework_can_bridge_codec_tokens_and_perceptual role: supports claim: A masked-autoencoder framework can bridge codec tokens and perceptual speech attributes bidirectionally, enabling voice conversion at dramatically lower bitrates than spectrogram-based equivalents. source: §3.1, §3.2 evidence: A masked-autoencoder framework can bridge codec tokens and perceptual speech attributes bidirectionally, enabling voice conversion at dramatically lower bitrates than spectrogram-based equivalents. confidence: high relevance: high - claim_id: post_hoc_interpretability_tools_reveal_systematic_trade_offs_between_content role: supports claim: Post-hoc interpretability tools reveal systematic trade-offs between content accuracy and synthesis quality that differ by codec design, complicating the choice of codec for controllable speech generation. source: §3.2, Table 1 evidence: Post-hoc interpretability tools reveal systematic trade-offs between content accuracy and synthesis quality that differ by codec design, complicating the choice of codec for controllable speech generation. confidence: high relevance: low limitations: - All experiments use LibriSpeech, a clean read-speech corpus with limited acoustic diversity. Whether the observed encoding patterns hold for spontaneous speech, expressive data, or noise-conditioned codecs is untested. - The study covers four specific codecs; the broader generalisation across the growing landscape of codec designs (including future multi-scale or end-to-end codec-LM systems) is an open question. Pitch estimation from codec tokens remains poor, and no remedy is proposed — it is unclear whether this is a fundamental limitation of RVQ-based representations or an artefact of the particular codecs studied. The bidirectional AnCoGen-Codec is compared only against the Melspectrogram baseline and not against dedicated disentanglement-oriented codec frameworks such as FreeCodec or SpeechFlow, which would provide stronger context for the synthesis results. caveats: [] - id: interspeech-2025-0203 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - flow-matching - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion - transformer_encoder_decoder_voice_conversion claims: - claim_id: natural_language_prompts_can_control_emotional_voice_conversion_at_parity role: supports claim: Natural language prompts can control emotional voice conversion at parity with reference speech for the majority of listeners, reducing reliance on hard-to-source reference audio. source: §3.2.2 evidence: Natural language prompts can control emotional voice conversion at parity with reference speech for the majority of listeners, reducing reliance on hard-to-source reference audio. confidence: high relevance: high - claim_id: flow_matching_produces_noticeably_higher_speech_naturalness_and_audio_quality role: supports claim: Flow matching produces noticeably higher speech naturalness and audio quality in emotional voice conversion than GAN and autoencoder baselines. source: §3.2.1, Table 1 evidence: Flow matching produces noticeably higher speech naturalness and audio quality in emotional voice conversion than GAN and autoencoder baselines. confidence: high relevance: high - claim_id: combining_categorical_emotion_labels_with_free_form_prompt_labels_through role: supports claim: Combining categorical emotion labels with free-form prompt labels through soft-label contrastive training improves emotion embedding quality over prompt-only or label-only training. source: §3.3, Table 2 evidence: Combining categorical emotion labels with free-form prompt labels through soft-label contrastive training improves emotion embedding quality over prompt-only or label-only training. confidence: high relevance: medium - claim_id: an_explicit_scalar_intensity_gate_applied_to_emotional_embeddings_before role: supports claim: An explicit scalar intensity gate applied to emotional embeddings before content-emotion fusion improves both naturalness and emotion similarity in converted speech. source: §3.3, Table 2 evidence: An explicit scalar intensity gate applied to emotional embeddings before content-emotion fusion improves both naturalness and emotion similarity in converted speech. confidence: high relevance: medium limitations: - The system is trained and evaluated entirely on a proprietary internal Mandarin corpus. No open-source data or model weights are released, and no cross-lingual or multi-speaker generalisation is tested. - Comparisons are restricted to older GAN and autoencoder baselines (StarGAN-EVC, Seq2seq-EVC, MixEmo); no diffusion-based or recent flow-matching EVC systems are included, so the claimed state-of-the-art position cannot be verified against the most competitive contemporaries. The evaluation is any-to-one (fixed target speaker identity), leaving any-to-any EVC performance unaddressed. Emotion coverage is limited to seven categorical classes; whether the natural language conditioning generalises to subtler or blended emotional states is untested. caveats: [] - id: interspeech-2025-0305 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - singing - VC architecture: - flow-matching - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion - transformer_encoder_decoder_voice_conversion claims: - claim_id: flow_matching_decoders_produce_higher_audio_quality_than_gan_based role: supports claim: Flow matching decoders produce higher audio quality than GAN-based decoders in singing voice conversion when conditioning signal quality is held constant. source: §4.1, §4.2, Table 1, Table 2 evidence: Replacing NeuCoSVC's GAN-based FastSVC decoder with a CFM module improves MCD from 8.634 to 7.220 and MOS-Naturalness from 3.47 to 3.80 on OpenSinger, with the ablation confirming that even without the DCAM module the CFM-equipped model surpasses NeuCoSVC. confidence: high relevance: high - claim_id: ssl_feature_matching_prevents_timbre_leakage_in_singing_voice_conversion role: refines claim: SSL feature matching prevents timbre leakage in singing voice conversion but is insufficient on its own for high timbre similarity, because target timbre is distributed across the full reference utterance rather than captured by sparse nearest-neighbour retrieval. source: §4.2, Table 1, Table 2 evidence: The -spk&att ablation (SSL matching only, no speaker embeddings or DCAM) achieves SSIM 0.709 vs. 0.692 for NeuCoSVC (marginal improvement), while adding speaker embeddings with the full DCAM raises SSIM to 0.754 — a larger relative gain than the matching step alone provides. confidence: high relevance: high - claim_id: cross_attention_fusion_of_speaker_embeddings_and_melody_features_with role: supports claim: Cross-attention fusion of speaker embeddings and melody features with shared content queries improves timbre similarity and audio coherence over simple feature concatenation in conditional singing voice conversion. source: §4.2, Table 2 evidence: Removing the DCAM while retaining speaker embeddings (-att ablation) drops SSIM from 0.754 to 0.710 and MCD from 7.220 to 8.129, demonstrating that the attention mechanism adds value beyond the conditioning signals themselves. confidence: high relevance: high - claim_id: one_shot_singing_voice_conversion_evaluations_remain_narrow_in_scope role: complicates claim: One-shot singing voice conversion evaluations remain narrow in scope, limiting the generalisability of reported gains. source: §3.1, §3.4, §5 evidence: Experiments use a single Chinese singing dataset (OpenSinger), 20 samples for subjective evaluation with 15 listeners, and four unseen target speakers. Cross-language, multi-domain, or noisy-environment generalisation is explicitly deferred to future work. confidence: high relevance: high limitations: - The system is trained and evaluated exclusively on high-quality Chinese singing (OpenSinger, recorded in a professional studio), and the authors acknowledge that performance in noisy environments and cross-language settings is untested. The subjective evaluation is small (20 samples, 15 listeners), raising questions about statistical robustness. The pitch shifting strategy (scaling source pitch by the ratio of target-to-source median pitch) is a global heuristic that may not capture fine-grained vocal range adaptation. Model size, inference latency, and real-time factor are not reported. Whether the DCAM design generalises beyond the Chinese singing domain remains open. caveats: [] - id: interspeech-2025-0383 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - transformer_encoder_decoder_voice_conversion claims: - claim_id: discrete_unit_voice_conversion_can_be_extended_to_control_subjective role: supports claim: Discrete-unit voice conversion can be extended to control subjective perceptual attributes beyond speaker identity by adding a scalar conditioning signal to the synthesis model. source: §3, §5.3, Figure 6 evidence: A FastSpeech 2 model conditioned on HuBERT-based discrete units, ECAPA-TDNN speaker embeddings, and a target likability scalar successfully steered perceived likability for 3 of 4 speakers in pairwise preference tests. confidence: high relevance: high - claim_id: automatic_likability_predictors_based_on_tdnn_regression_on_crowd_sourced role: supports claim: Automatic likability predictors based on TDNN regression on crowd-sourced ratings can provide sufficient proxy labels to train large-scale perceptual attribute control systems. source: §4.2, Table 2 evidence: The predictor achieved LCC 0.46 and SRCC 0.49 with human ratings (p < 3e-17) and 74% binary classification accuracy; its outputs were used to automatically annotate the JVS and JTES corpora for VC training. confidence: high relevance: medium - claim_id: strong_likability_control_and_speaker_identity_preservation_are_in_tension role: complicates claim: Strong likability control and speaker identity preservation are in tension in discrete-unit VC systems, particularly at extreme target values. source: §5.2, §5.3, Figures 4–6 evidence: At target likability = 2 (outside the training range), CER increased substantially for female speakers and speaker m49 showed degraded speaker similarity and unexpected subjective likability drop; the inference-time scalar multiplier partially mitigates but does not eliminate this trade-off. confidence: high relevance: high - claim_id: voice_likability_control_demonstrates_effective_behaviour_for_majority_speaker_groups role: complicates claim: Voice likability control demonstrates effective behaviour for majority speaker groups but can fail for individual speakers due to identity-likability interaction effects. source: §5.3, Figure 6 evidence: Three of four speakers showed significant preference differences between target -1 and 1; speaker m49 exhibited the opposite trend, attributed to failure to preserve speaker identity, indicating that per-speaker variation is a real limitation. confidence: high relevance: medium - claim_id: perceived_voice_likability_is_a_multi_factorial_attribute_requiring_demographic role: refines claim: Perceived voice likability is a multi-factorial attribute requiring demographic-stratified modelling, not a single group-level score. source: §2, §4.2, Table 2 evidence: The predictor uses four separate listener-group outputs (by gender and age); per-group LCC ranges from 0.36 to 0.41 while the aggregate LCC is 0.46, confirming systematic variation across listener demographics. confidence: high relevance: medium limitations: - The evaluation is limited to four speakers (two female, two male) and one language (Japanese), with training on Japanese speech corpora. Cross-lingual and multi-lingual generalisability is entirely untested. - 'The practical control range of the system is narrow: despite targeting values from -2 to 2, predicted likability shifts only from approximately -0.51 to -0.23, suggesting the model substantially operates within each speaker''s inherent likability range rather than achieving wide stylistic transfer. This is acknowledged by the authors but not resolved.' - The likability predictor's correlation with human ratings is statistically significant but moderate (LCC 0.46), meaning a substantial portion of subjective likability variance is not captured. Since this predictor is the primary source of training supervision, any systematic biases in its predictions will propagate to the VC model. - The scalar multiplier (s = 2.5 at inference vs. 1 at training) is manually tuned and distribution-shifted, which may limit out-of-distribution robustness. Future work noted by the authors includes extending to natural language specification of desired voice characteristics. caveats: [] - id: interspeech-2025-0433 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - VAE relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion claims: - claim_id: voice_conversion_architectures_designed_for_human_speech_require_non_trivial role: supports claim: Voice conversion architectures designed for human speech require non-trivial adaptation to generalise to non-human vocalizations with broad frequency ranges and transient-rich characteristics. source: §4.2.2, Table 1 evidence: Replacing the proposed preprocessing pipeline with a conventional speech-focused one degraded WER from 24.02% to 62.29% and MOS-S from 3.78 to 3.53, indicating that human-speech assumptions about frame resolution and frequency range materially impair non-human sound conversion. confidence: high relevance: high - claim_id: isolating_style_conditioning_to_the_prior_network_and_normalizing_flow role: supports claim: Isolating style conditioning to the prior network and normalizing flow, and excluding it from the posterior encoder and decoder, reduces style leakage and improves speaker similarity in CVAE-based voice conversion. source: §4.2.3, Table 1 evidence: Adding the style embedding to the audio encoder and decoder (w/ SEED ablation) reduced MOS-S from 3.78 to 3.61, attributed to style overlap between the reference encoder output and latent acoustic tokens. confidence: high relevance: high - claim_id: kl_annealing_mitigates_posterior_collapse_in_vae_based_voice_conversion role: supports claim: KL annealing mitigates posterior collapse in VAE-based voice conversion and improves linguistic content preservation, particularly for complex non-human vocalizations. source: §4.2.3, Table 1 evidence: Removing KL annealing increased CER from 15.48% to 28.89% and WER from 24.02% to 44.69%, while MOS scores changed minimally, indicating that linguistic clarity is the primary casualty of over-regularization in early training. confidence: high relevance: high - claim_id: existing_fundamental_frequency_f0_estimation_methods_are_not_reliable_for role: complicates claim: Existing fundamental frequency (F0) estimation methods are not reliable for sounds lacking a well-defined harmonic structure, constraining prosodic feature extraction in non-human voice conversion systems. source: §3.1 evidence: The authors tested frame-level F0 from non-human sounds but found existing estimators (Praat, CREPE, SPICE, PESTO) exhibited limitations due to absent harmonic structure; the system falls back to energy-only prosodic features, leaving robust F0 extraction as an open problem. confidence: high relevance: high limitations: - The dataset is entirely internal and the evaluation uses only 9 human raters on an unspecified number of test samples, limiting reproducibility and the statistical reliability of MOS scores. - No publicly available data or code is confirmed, making direct comparison and reproduction difficult. The evaluation benchmarks non-human VC against baselines that were not adapted for non-human sounds, which is the correct setup for the paper's argument but means absolute MOS values are not comparable to human-speech VC literature. - 'F0 estimation for non-human sounds remains unsolved: the system uses energy-only prosodic features and omits pitch conditioning, which may limit prosodic expressiveness for vocalizations where pitch contour is perceptually salient (e.g., melodic birdsong). The evaluation scope is restricted to a set of internally defined sound categories (exclamations, designed voices, animal sounds from a commercial library), and generalisation to out-of-distribution non-human sounds is not tested.' caveats: [] - id: interspeech-2025-0438 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: linear_transformations_of_self_supervised_speech_features_are_sufficient_for role: supports claim: Linear transformations of self-supervised speech features are sufficient for competitive voice conversion, without complex nonlinear decoders or model fine-tuning. source: §3.2, Table 1 evidence: LinearVC's single learned projection matrix W on WavLM-Large layer 6 achieves WER 4.9%, EER 33.6%, and MUSHRA naturalness 62.5 on LibriSpeech test-clean, statistically indistinguishable from kNN-VC and SoundStorm in both naturalness and speaker similarity. confidence: high relevance: high - claim_id: content_and_speaker_identity_information_reside_in_orthogonal_low_dimensional role: supports claim: Content and speaker identity information reside in orthogonal low-dimensional subspaces within the same SSL layer, enabling voice style transfer through geometric manipulation. source: §4, Table 2; §5.2, Figure 4 evidence: Constraining the linear transformation to rotation and reflection only achieves EER 27.7% vs. 31.8% for unconstrained; adding translation alone gives only EER 7.7% with intelligibility maintained (CER 2.9%), confirming a shared phonetic subspace across speakers. SVD factorization at rank 16 achieves CER < 4%, while speaker similarity requires rank ~100. confidence: high relevance: high - claim_id: high_naturalness_in_voice_conversion_does_not_imply_high_speaker role: complicates claim: High naturalness in voice conversion does not imply high speaker similarity — these objectives can trade off sharply depending on the system design. source: §3.2, Table 1 evidence: FreeVC achieves the highest naturalness (71.1 MUSHRA) among all systems but the lowest speaker similarity (EER 10.5% vs. 33.6% for LinearVC and 38.9% for kNN-VC), indicating that perceptual smoothness and target-speaker fidelity are partly in tension. confidence: high relevance: high - claim_id: eer_as_an_objective_speaker_similarity_metric_provides_only_coarse role: refines claim: EER as an objective speaker similarity metric provides only coarse correspondence with perceived speaker similarity in voice conversion evaluation. source: §3.2 evidence: The paper notes that small EER differences do not reliably track subjective similarity ratings, and that EER gives a coarse correspondence with perceptual judgements. LinearVC and kNN-VC have comparable subjective similarity (67.5 vs. 67.2) but different EERs (33.6 vs. 38.9). confidence: high relevance: high limitations: - The analysis is restricted to WavLM-Large (layer 6) on English LibriSpeech. Whether the orthogonal subspace structure holds for other SSL models (HuBERT, wav2vec 2.0), other layers, other languages, or noisy/spontaneous speech settings is left as future work. The vocoder is shared across all systems, making it difficult to isolate conversion quality from synthesis quality. The training data requirement (2.7 minutes per target speaker) means LinearVC is not a zero-shot system in the strictest sense; it requires a small per-speaker adaptation step. Performance at very low reference amounts is untested. Future applications the authors suggest include speech anonymization and phonetic content extraction. caveats: [] - id: interspeech-2025-0464 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC - codec architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: explicit_mutual_information_minimisation_at_the_codec_embedding_level_provides role: supports claim: Explicit mutual information minimisation at the codec-embedding level provides effective prosody-timbre disentanglement for voice conversion. source: §3.5, Table 3 evidence: Removing the MI loss (L_MI) from the full system leads to a notably higher normalised F0 distance in the prosody-from-source scenario (3.28 vs. 2.82), while quality and timbre metrics change only modestly, isolating prosody control as the primary benefit of the MI objective. confidence: high relevance: high - claim_id: in_context_learning_codec_lms_can_serve_as_controllable_vc role: supports claim: In-context learning codec LMs can serve as controllable VC backbones when augmented with prosody-disentangling encoder modules. source: §3.4, §3.5, Table 2, Table 3 evidence: The proposed system builds on VALL-E X's ICL mechanism and outperforms VALL-E X in speaker similarity (ASV 0.91 vs. 0.84), intelligibility (WER 0.101 vs. 0.115), naturalness (MOS 4.36 vs. 4.19), and prosody alignment (F0 distance 2.70 vs. 3.10) in the prompt-based scenario. confidence: high relevance: low - claim_id: prosody_disentanglement_at_the_codec_level_introduces_a_small_trade role: complicates claim: Prosody disentanglement at the codec level introduces a small trade-off in absolute codec reconstruction fidelity compared to the unmodified encoder. source: §3.3, Table 1 evidence: PACE's ASV score (0.662) and NISQA score (3.98) are lower than the baseline EnCodec encoder (0.681, 4.17), though the gap does not substantially affect system-level VC performance. confidence: high relevance: low - claim_id: prosody_from_source_and_prosody_from_prompt_are_distinct_capability role: refines claim: Prosody-from-source and prosody-from-prompt are distinct capability axes in voice conversion; systems strong at one do not automatically handle the other. source: §3.5, Table 3 evidence: VALL-E X supports only prosody-from-prompt and is excluded from the source-prosody evaluation; TriAAN-VC and ProsoVC support only source-prosody and are excluded from the prompt-prosody evaluation. Only the proposed system is evaluated in both modes. confidence: high relevance: high limitations: - All evaluation is conducted on LibriTTS-clean-100 and test-clean, a relatively clean single-domain corpus with 247 speakers. Generalisation to noisy environments, expressive or emotional speech, or cross-lingual settings is not tested. - The 54-hour training dataset is modest for a codec language model approach; it is unclear whether the disentanglement quality degrades with longer or more expressive source utterances. No code or demo is reported, limiting reproducibility. The paper does not ablate the number of RVQ codebooks or the sensitivity of the MI-minimisation trade-off weight (lambda_MI), leaving the robustness of the disentanglement objective undercharacterised. Prosody is operationalised solely through f0 and UV binary flags; richer prosodic dimensions such as energy, speaking rate, and phrase-level structure are not captured. caveats: [] - id: interspeech-2025-0575 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC - TTS architecture: - VAE relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion claims: - claim_id: watermarks_embedded_in_the_speaker_specific_latent_space_of_a role: supports claim: Watermarks embedded in the speaker-specific latent space of a neural codec survive zero-shot voice cloning synthesis, whereas waveform-level watermarks do not. source: §1, §3.5, Table 1 evidence: Watermarks embedded in the speaker-specific latent space of a neural codec survive zero-shot voice cloning synthesis, whereas waveform-level watermarks do not. confidence: high relevance: high - claim_id: the_effectiveness_of_latent_space_watermarking_in_zero_shot_vc role: supports claim: The effectiveness of latent-space watermarking in zero-shot VC scenarios depends on the VC model preserving speaker-specific latents to achieve high speaker similarity. source: §1, §2.1 evidence: The effectiveness of latent-space watermarking in zero-shot VC scenarios depends on the VC model preserving speaker-specific latents to achieve high speaker similarity. confidence: high relevance: high - claim_id: vc_simulated_augmentation_during_training_without_exposure_to_actual_vc role: supports claim: VC-simulated augmentation during training — without exposure to actual VC model outputs — is sufficient to achieve robust watermark recovery from synthesized audio. source: §2.3, §3.6, Table 2 evidence: VC-simulated augmentation during training — without exposure to actual VC model outputs — is sufficient to achieve robust watermark recovery from synthesized audio. confidence: high relevance: medium - claim_id: codec_based_watermarking_pipelines_introduce_perceptible_audio_quality_degradation_compared role: complicates claim: Codec-based watermarking pipelines introduce perceptible audio quality degradation compared to waveform-level methods, representing a trade-off between VC resistance and transparency. source: §3.7, Table 3 evidence: Codec-based watermarking pipelines introduce perceptible audio quality degradation compared to waveform-level methods, representing a trade-off between VC resistance and transparency. confidence: high relevance: low limitations: - The model is trained only on VCTK, a small clean dataset, which limits robustness to out-of-distribution audio editing (the paper notes lower-than-1.0 ACC on traditional editing, likely due to this). The audio quality impact (PESQ 2.2 vs. 4.32 for AudioSeal) is significant and may be prohibitive for some use cases. The approach does not address adversarial attacks specifically designed to remove latent-space watermarks. Coverage is limited to English; multilingual generalization is untested. Finally, the approach assumes the zero-shot VC model must preserve speaker-specific latents for high similarity — models that do not operate this way could evade detection. caveats: [] - id: interspeech-2025-0656 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: cross_modal_feature_alignment_between_neural_signals_and_speaker_embeddings role: supports claim: Cross-modal feature alignment between neural signals and speaker embeddings can enable voice conversion without any target-speaker voice data. source: §3.1.2, §4.4 evidence: The EEG-voice feature alignment module, trained with embedding MSE and speaker classification losses, produces speaker embeddings from EEG that drive FreeVC-based conversion to zero-shot quality (Naturalness MOS 4.00, Consistency obj 0.8026 for unseen speakers). confidence: high relevance: high - claim_id: non_speech_biometric_signals_can_encode_speaker_identity_information_sufficient role: supports claim: Non-speech biometric signals can encode speaker-identity information sufficient to guide voice timbre conversion. source: §4.4.1, Figure 2 evidence: t-SNE visualisation shows synthesised speech clusters align with reference audio per speaker, and Homogeneity scores (0.9437–0.9465) exceed the FreeVC baseline (0.9371), indicating EEG features encode timbre-discriminative information. confidence: high relevance: high - claim_id: zero_shot_voice_conversion_from_eeg_signals_requires_a_large role: complicates claim: Zero-shot voice conversion from EEG signals requires a large-scale speech-only pre-training stage to compensate for the scarcity and noise of paired EEG-speech data. source: §3.2 evidence: The three-stage curriculum first pre-trains on VCTK (Stage I, speech only), then aligns EEG to pre-trained speaker embeddings (Stage II), before joint fine-tuning (Stage III). The authors explicitly attribute feasibility to leveraging the pre-trained VC model's representations. confidence: high relevance: high - claim_id: evaluation_of_eeg_driven_voice_conversion_is_fundamentally_limited_by role: complicates claim: Evaluation of EEG-driven voice conversion is fundamentally limited by the availability of paired EEG-speech corpora at the scale needed for generalisation. source: §4.1, §5 evidence: The entire EEG evaluation uses the Single-Word-Production Dutch-iBIDS dataset (10 speakers, single-word utterances). Seen-speaker training uses 80% of this data; unseen-speaker evaluation uses k-fold over 10 speakers. The authors note that "more data will improve performance." confidence: high relevance: high limitations: - The evaluation dataset contains only 10 speakers producing single words in Dutch. Results on connected speech, diverse languages, and larger speaker populations are entirely untested. Generalisability claims should be treated as preliminary. - 'The baseline comparison (FreeVC) is not an equivalent system: FreeVC uses a target-speaker voice prompt while the proposed system uses EEG, so observed differences in quality scores may partly reflect the inherent difficulty of the EEG conditioning signal rather than architectural superiority. The paper does not report intelligibility metrics (WER/CER), making it impossible to assess whether semantic content is preserved faithfully. The EEG signals in the dataset come from intracranial recordings (high SNR), which may not transfer to consumer-grade scalp EEG equipment used in practical BCI deployments.' caveats: [] - id: interspeech-2025-0787 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - TTS architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: speaker_embedding_manipulation_can_transfer_a_distinctive_speaking_style_lombard role: supports claim: Speaker embedding manipulation can transfer a distinctive speaking style (Lombard speech) to unseen speakers using only a small feedforward network trained on minimal paired data, without retraining the underlying TTS model. source: §2.3, §4.1 evidence: Speaker embedding manipulation can transfer a distinctive speaking style (Lombard speech) to unseen speakers using only a small feedforward network trained on minimal paired data, without retraining the underlying TTS model. confidence: high relevance: high - claim_id: perceptual_plausibility_of_artificially_generated_lombard_speech_depends_substantially_on role: supports claim: Perceptual plausibility of artificially generated Lombard speech depends substantially on modelling pitch and duration changes, not only level amplification as recommended by ITU-T P.1150. source: §4.3, Table 1 evidence: Perceptual plausibility of artificially generated Lombard speech depends substantially on modelling pitch and duration changes, not only level amplification as recommended by ITU-T P.1150. confidence: high relevance: medium - claim_id: spherical_interpolation_between_plain_and_lombard_speaker_embeddings_when_calibrated role: supports claim: Spherical interpolation between plain and Lombard speaker embeddings, when calibrated to a physical noise-level scale, enables continuous and controllable Lombard intensity without requiring recordings at each intermediate level. source: §2.5 evidence: Spherical interpolation between plain and Lombard speaker embeddings, when calibrated to a physical noise-level scale, enables continuous and controllable Lombard intensity without requiring recordings at each intermediate level. confidence: high relevance: medium - claim_id: embedding_space_style_transfer_trained_on_in_distribution_data_can role: supports claim: Embedding-space style transfer trained on in-distribution data can generalise to out-of-distribution speakers with a speaker similarity loss of approximately 0.5 MOS relative to an ideal upper bound. source: §4.3 evidence: Embedding-space style transfer trained on in-distribution data can generalise to out-of-distribution speakers with a speaker similarity loss of approximately 0.5 MOS relative to an ideal upper bound. confidence: high relevance: medium limitations: - '- Metavoice 1B is English-only; multilingual or language-adaptive Lombard generation is unaddressed. - Only 10 listeners in the listening test; statistical significance is limited. - The level calibration used ITU-T P.1150, which participants judged as too quiet at the highest noise levels — the standard may underestimate real Lombard level increases. - The feedforward embedding transform was trained on Lombard Grid (slow, scripted utterances) and tested on ITU-P.501 (different style); domain mismatch effects are partially visible. - Dynamic/time-varying background noise scenarios are left as future work.' caveats: [] - id: interspeech-2025-0815 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - VAE - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: discrete_speech_unit_representations_reduce_source_speaker_leakage_in_voice role: supports claim: Discrete speech unit representations reduce source speaker leakage in voice conversion but introduce pronunciation artefacts that degrade intelligibility compared to continuous feature counterparts. source: §4.2, Table 1 evidence: Discrete speech unit representations reduce source speaker leakage in voice conversion but introduce pronunciation artefacts that degrade intelligibility compared to continuous feature counterparts. confidence: high relevance: high - claim_id: mix_style_layer_normalisation_mitigates_the_train_inference_mismatch_caused role: supports claim: Mix-style layer normalisation mitigates the train-inference mismatch caused by content-style dependence in style encoders, improving zero-shot generalisation on unseen speakers. source: §4.3, Table 2 evidence: Mix-style layer normalisation mitigates the train-inference mismatch caused by content-style dependence in style encoders, improving zero-shot generalisation on unseen speakers. confidence: high relevance: medium - claim_id: enriching_global_style_embeddings_with_explicit_pitch_and_energy_features role: supports claim: Enriching global style embeddings with explicit pitch and energy features improves emotion transfer fidelity in expressive voice conversion beyond mel-spectrogram-only style encoding. source: §3.5, §4.3, Table 2 evidence: Enriching global style embeddings with explicit pitch and energy features improves emotion transfer fidelity in expressive voice conversion beyond mel-spectrogram-only style encoding. confidence: high relevance: high - claim_id: cross_attention_fusion_of_local_f0_contours_with_content_embeddings role: supports claim: Cross-attention fusion of local F0 contours with content embeddings produces stronger prosodic alignment to the target than additive F0 injection in non-autoregressive voice conversion. source: §3.1, §4.3, Table 2 evidence: Cross-attention fusion of local F0 contours with content embeddings produces stronger prosodic alignment to the target than additive F0 injection in non-autoregressive voice conversion. confidence: high relevance: high - claim_id: zero_shot_cross_lingual_voice_conversion_is_achievable_with_a role: supports claim: Zero-shot cross-lingual voice conversion is achievable with a monolingual training corpus when content representations are extracted from a multilingual speech model, though intelligibility degrades for unseen source languages. source: §4.4, Table 4 evidence: Zero-shot cross-lingual voice conversion is achievable with a monolingual training corpus when content representations are extracted from a multilingual speech model, though intelligibility degrades for unseen source languages. confidence: high relevance: high limitations: - 'The proposed system incurs a substantial WER penalty relative to baselines: 7.98% vs. 5.01% (ESD) and 8.84% vs. 3.48% (LibriTTS) for the full model, with discrete units identified as the cause. This intelligibility regression is acknowledged but not resolved; future work is deferred.' - The evaluation uses a small subjective panel (15 listeners, 10–15 samples per model), limiting the statistical power of MOS comparisons. The cross-lingual results are restricted to English and German; how performance degrades for more distant language pairs is untested. The model is trained on English-only data, and German-to-English conversion shows a 30.84% WER, suggesting significant cross-lingual generalisation limits. The model size and computational cost are not reported, making it difficult to assess deployment feasibility. caveats: [] - id: interspeech-2025-0816 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - singing - VC architecture: - diffusion relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - diffusion_voice_conversion claims: - claim_id: converting_speech_timbre_to_singing_requires_cross_modal_speaker_embedding role: supports claim: Converting speech timbre to singing requires cross-modal speaker embedding alignment, and standard singer-identity conditioning generalises poorly across the speech-singing domain boundary. source: §1, §2.1 evidence: Converting speech timbre to singing requires cross-modal speaker embedding alignment, and standard singer-identity conditioning generalises poorly across the speech-singing domain boundary. confidence: high relevance: high - claim_id: cycle_training_strategies_that_simulate_paired_cross_domain_data_can role: supports claim: Cycle training strategies that simulate paired cross-domain data can compensate for the scarcity of matched speech-singing corpora in voice conversion training. source: §2.3 evidence: Cycle training strategies that simulate paired cross-domain data can compensate for the scarcity of matched speech-singing corpora in voice conversion training. confidence: high relevance: high - claim_id: zero_shot_singing_voice_conversion_with_speech_prompts_achieves_lower role: supports claim: Zero-shot singing voice conversion with speech prompts achieves lower timbre similarity scores than same-domain (singing-to-singing) conversion, indicating that the cross-modal gap is not fully closed by embedding alignment alone. source: §3.3, Table 1, Table 2 evidence: Zero-shot singing voice conversion with speech prompts achieves lower timbre similarity scores than same-domain (singing-to-singing) conversion, indicating that the cross-modal gap is not fully closed by embedding alignment alone. confidence: high relevance: high - claim_id: automated_speaker_similarity_metrics_capture_relative_improvements_from_cross_domain role: supports claim: Automated speaker similarity metrics capture relative improvements from cross-domain adaptation that are not clearly reflected in small-panel subjective timbre similarity ratings. source: §3.2, §3.3, Table 3 evidence: Automated speaker similarity metrics capture relative improvements from cross-domain adaptation that are not clearly reflected in small-panel subjective timbre similarity ratings. confidence: high relevance: high limitations: - The subjective evaluation relies on only 10 volunteers, producing confidence intervals that overlap between all three systems on both MOS-n and MOS-ts. The claimed superiority of SSANSVC-stage2 over CoMoSVC in naturalness and similarity is not statistically robust at this sample size. - The model's loss function addresses only mel reconstruction; the authors note that timbre loss and lyrics recognition loss (to reduce CER) are absent and represent the primary direction for future improvement. The two-stage training procedure also introduces significant complexity and training cost compared to the CoMoSVC baseline. Evaluation is restricted to Mandarin speech and singing datasets, so generalisation to other languages and vocal styles is untested. The dependency on NUS-48E — one of few available paired speech-singing corpora — limits reproducibility in languages where such data does not exist. caveats: [] - id: interspeech-2025-0902 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - VAE - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: explicit_conditioning_on_acoustic_voice_quality_features_cpps_h1_h2 role: supports claim: Explicit conditioning on acoustic voice quality features (CPPS, H1-H2, H1-A3, creakiness) enables controllable manipulation of phonation type in a VC system. source: §3.2, §4.1 evidence: Explicit conditioning on acoustic voice quality features (CPPS, H1-H2, H1-A3, creakiness) enables controllable manipulation of phonation type in a VC system. confidence: high relevance: medium - claim_id: breathy_voice_is_perceived_as_more_intimate_and_more_invested role: supports claim: Breathy voice is perceived as more intimate and more invested than modal voice when paralinguistic content is held constant across speakers. source: §5.2, Table 1 evidence: Breathy voice is perceived as more intimate and more invested than modal voice when paralinguistic content is held constant across speakers. confidence: high relevance: medium - claim_id: creaky_voice_is_perceived_as_less_intimate_and_less_positive role: supports claim: Creaky voice is perceived as less intimate and less positive than modal voice, consistent with prior findings using natural speech stimuli. source: §5.2, Table 1 evidence: Creaky voice is perceived as less intimate and less positive than modal voice, consistent with prior findings using natural speech stimuli. confidence: high relevance: medium - claim_id: fine_tuning_an_existing_vc_backbone_with_lightweight_feature_encoders role: supports claim: Fine-tuning an existing VC backbone with lightweight feature encoders is sufficient to achieve intuitive control over multiple acoustic correlates of voice quality without degrading the base model's conversion capability. source: §3.3, §4.1 evidence: Fine-tuning an existing VC backbone with lightweight feature encoders is sufficient to achieve intuitive control over multiple acoustic correlates of voice quality without degrading the base model's conversion capability. confidence: high relevance: medium limitations: - '- CPPS is measured over voiced segments rather than sustained vowels, introducing minor irregularities. - Pitch control generalizes imperfectly across genders due to corpus-level standardization combining both genders. - The system models acoustic correlates of voice quality rather than voice quality per se; phonetic validation by trained phoneticians would strengthen claims. - No MUSHRA or absolute MOS for speech naturalness — evaluation focused on paralinguistic perception rather than synthesis fidelity. - Integration into live dialogue systems for adaptive voice quality in conversation is proposed as future work.' caveats: [] - id: interspeech-2025-0948 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - VAE - diffusion relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - vae_latent_voice_conversion - diffusion_voice_conversion claims: - claim_id: natural_language_prompts_enable_more_flexible_and_subjectively_accurate_emotion role: supports claim: Natural language prompts enable more flexible and subjectively accurate emotion control in voice conversion than numeric intensity values or reference audio selection. source: §1, §3.4 evidence: Natural language prompts enable more flexible and subjectively accurate emotion control in voice conversion than numeric intensity values or reference audio selection. confidence: high relevance: high - claim_id: a_diffusion_based_mapping_from_text_embeddings_to_speech_emotion role: supports claim: A diffusion-based mapping from text embeddings to speech emotion embeddings is sufficient to replace reference audio at inference time without significant quality loss. source: §2.1, §3.2, Table 1 evidence: A diffusion-based mapping from text embeddings to speech emotion embeddings is sufficient to replace reference audio at inference time without significant quality loss. confidence: high relevance: medium - claim_id: joint_training_of_a_text_to_emotion_mapper_with_reference role: supports claim: Joint training of a text-to-emotion mapper with reference emotion embeddings improves prosody naturalness over direct prediction from text alone. source: §3.3, Table 1 evidence: Joint training of a text-to-emotion mapper with reference emotion embeddings improves prosody naturalness over direct prediction from text alone. confidence: high relevance: medium - claim_id: preserving_speaker_identity_during_emotional_pitch_manipulation_requires_an_explicit role: supports claim: Preserving speaker identity during emotional pitch manipulation requires an explicit F0 constraint in the speaker encoder; adversarial training alone is insufficient. source: §2.3, §3.3, Table 1 evidence: Preserving speaker identity during emotional pitch manipulation requires an explicit F0 constraint in the speaker encoder; adversarial training alone is insufficient. confidence: high relevance: high - claim_id: mixed_emotion_synthesis_remains_harder_to_control_than_single_category role: supports claim: Mixed-emotion synthesis remains harder to control than single-category emotion intensity across both subjective and objective metrics. source: §3.4, Table 2, Table 3 evidence: Mixed-emotion synthesis remains harder to control than single-category emotion intensity across both subjective and objective metrics. confidence: high relevance: medium limitations: - Training and evaluation are conducted entirely on TextrolSpeech, a single corpus with a limited speaker set. Generalisation to out-of-domain speakers, languages, or acoustic conditions is untested, and all reported numbers should be interpreted within that constraint. - The evaluation uses only 25 listeners for subjective MOS across 132 utterances — a borderline sample size that may limit statistical reliability. The mixed-emotion accuracy (61.3%) is notably lower than single-attribute control, and the system's handling of complex emotional blends (e.g., contempt with happiness) is not analysed in depth. The discrete HuBERT token approach for linguistic content may introduce quantisation artefacts not reported in the paper. Future real-time or streaming deployment, mentioned in the conclusion as a direction, is not addressed in the current architecture. caveats: [] - id: interspeech-2025-0998 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - diffusion - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: multi_stage_speech_restoration_pipelines_that_separate_noise_suppression_from role: supports claim: Multi-stage speech restoration pipelines that separate noise suppression from speaker-guided generation outperform single-stage generative approaches under severe degradation conditions. source: §4.3, Table 3 evidence: GSR+VC substantially outperforms standalone GSR or standalone VC across all metrics on both VCTK-DEMAND and UNIVERSE; the gain is largest on the UNIVERSE set, which simulates more severe distortions including band-limiting, reverberation, codec artefacts, and packet drops. confidence: high relevance: medium - claim_id: self_supervised_discrete_speech_representations_provide_more_robust_content_features role: supports claim: Self-supervised discrete speech representations provide more robust content features for voice conversion than raw mel-spectrograms when the input speech is degraded. source: §4.3, Table 3 evidence: VC (SSL) using HuBERT+VQ consistently outperforms VC (Mel) using direct mel-spectrogram input, with the gap widening on the more challenging UNIVERSE dataset where VC (Mel) shows significant quality degradation. confidence: high relevance: high - claim_id: diffusion_based_voice_conversion_models_cannot_reliably_handle_degraded_input role: complicates claim: Diffusion-based voice conversion models cannot reliably handle degraded input without a dedicated pre-processing stage, even when conditioned on clean speaker embeddings. source: §4.3, Table 3 evidence: VC (SSL) in standalone mode achieves lower scores than GSR+VC on both evaluation sets; the VC module performs markedly worse when the input is noisy without the GSR front-end, confirming that speaker-embedding guidance alone does not compensate for noisy content features. confidence: high relevance: high - claim_id: enrollment_dependent_speaker_guidance_for_speech_restoration_limits_applicability_to role: complicates claim: Enrollment-dependent speaker guidance for speech restoration limits applicability to settings where clean reference speech from the same speaker is available in advance. source: §3, §4.1 evidence: The system assumes short, uncorrelated segments of clean speech are obtained beforehand for speaker embedding extraction; the paper does not evaluate performance when such enrollment audio is unavailable or mismatched. confidence: high relevance: medium limitations: - The system requires a clean enrollment utterance from the target speaker, which may not be available in all real-world scenarios. No comparison with Miipher could be performed due to unavailability of that model, leaving the relationship between this approach and the closest prior work unquantified. Evaluation uses only automated perceptual quality metrics (NISQA, UTMOS, WV-MOS, DNSMOS) without any human listening tests, so it is unclear whether the metric gains translate to perceived quality improvements. Both the GSR and VC models are trained on separate datasets, and the system has not been evaluated on the joint training configuration proposed as future work. Performance on languages other than English is not examined. caveats: [] - id: interspeech-2025-1081 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - GAN relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: explicit_content_restoration_mechanisms_can_compensate_for_linguistic_information_degraded role: supports claim: Explicit content-restoration mechanisms can compensate for linguistic information degraded by instance normalization in speaker disentanglement, preserving intelligibility without SSL feature extractors. source: §2.1, Table 2 evidence: The SNCR dual restoration loss, which decomposes the IN residual into content-relevant and content-irrelevant parts via phoneme-entropy constraints, reduces WER from 5.57% (without SNCR) to 3.78% compared to a baseline trained with neither IN nor dual restoration loss. confidence: high relevance: high - claim_id: gan_based_zero_shot_voice_conversion_systems_can_match_the role: supports claim: GAN-based zero-shot voice conversion systems can match the speaker similarity of diffusion-based systems at substantially lower parameter count and faster inference. source: §3.2, Table 1 evidence: The proposed 50M-parameter GAN system achieves SECS 0.25 versus DDDM-VC's SECS 0.27, while running at RTF 0.11 versus 0.29 and using 366M fewer parameters; naturalness (nMOS 3.86 vs. 3.52) also favors the GAN system. confidence: high relevance: high - claim_id: integrating_self_attention_layers_into_cnn_based_discriminators_improves_adversarial role: supports claim: Integrating self-attention layers into CNN-based discriminators improves adversarial training quality for mel-spectrogram reconstruction in voice conversion. source: §3.3, Table 2 evidence: Ablation Base4 (discriminator without self-attention) degrades nMOS and WER compared to the full system, confirming that attention-enhanced discrimination contributes to speech quality gains beyond the convolutional baseline. confidence: high relevance: high - claim_id: speaker_similarity_metrics_in_zero_shot_vc_evaluations_can_be role: complicates claim: Speaker similarity metrics in zero-shot VC evaluations can be inflated when the test set speakers overlap with a baseline system's training set, making fair cross-system comparison difficult. source: §3.2 evidence: VQMIVC achieves SECS 0.23 (close to the proposed 0.25) but was trained on VCTK, which overlaps with the VCTK test speakers; its WER of 21.4% reveals its conversions are not actually intelligible, suggesting its SECS reflects in-distribution behavior rather than genuine zero-shot capability. confidence: high relevance: high limitations: - The system trains and evaluates on English only (LibriLight and VCTK). Whether the SNCR mechanism generalizes to cross-lingual voice conversion or languages with different phonological properties is untested. The ablation evaluates components one at a time, leaving interactions between SNCR and consistency loss unexplored. The mel-spectrogram reconstruction approach limits the system to fixed-rate synthesis, and no streaming or low-latency deployment scenario is discussed. Inference speed is reported on GPU only; embedded or CPU deployment characteristics are not assessed. caveats: [] - id: interspeech-2025-1101 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - diffusion relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - diffusion_voice_conversion claims: - claim_id: diffusion_based_voice_conversion_systems_can_achieve_strong_emotion_controllability role: supports claim: Diffusion-based voice conversion systems can achieve strong emotion controllability in zero-shot settings when combined with mutual-information disentanglement and inference-time guidance. source: §3.2, §3.3, Table 2 evidence: Diffusion-based voice conversion systems can achieve strong emotion controllability in zero-shot settings when combined with mutual-information disentanglement and inference-time guidance. confidence: high relevance: high - claim_id: disentangling_speaker_identity_and_emotion_via_mutual_information_minimisation_improves role: supports claim: Disentangling speaker identity and emotion via mutual information minimisation improves emotion controllability in voice conversion without requiring parallel or speaker-specific training data. source: §2.1.4, §3.3, Table 2 evidence: Disentangling speaker identity and emotion via mutual information minimisation improves emotion controllability in voice conversion without requiring parallel or speaker-specific training data. confidence: high relevance: high - claim_id: in_emotional_voice_conversion_autoencoder_based_methods_tend_to_achieve role: complicates claim: In emotional voice conversion, autoencoder-based methods tend to achieve higher emotion accuracy than GAN-based methods, but at the cost of substantially lower naturalness and higher speech distortion. source: §3.2, Table 1 evidence: In emotional voice conversion, autoencoder-based methods tend to achieve higher emotion accuracy than GAN-based methods, but at the cost of substantially lower naturalness and higher speech distortion. confidence: high relevance: high - claim_id: classifier_free_style_guidance_applied_to_emotion_representations_at_inference role: supports claim: Classifier-free-style guidance applied to emotion representations at inference time provides a direct lever for trading naturalness against emotion controllability in diffusion-based EVC. source: §2.1.3, §3.3, Table 2 evidence: Classifier-free-style guidance applied to emotion representations at inference time provides a direct lever for trading naturalness against emotion controllability in diffusion-based EVC. confidence: high relevance: medium - claim_id: training_on_large_scale_in_the_wild_emotional_corpora_enables role: supports claim: Training on large-scale in-the-wild emotional corpora enables zero-shot generalisation to speakers absent from training, even when evaluation is conducted on acted-speech datasets with different recording conditions. source: §3.4, §4 evidence: Training on large-scale in-the-wild emotional corpora enables zero-shot generalisation to speakers absent from training, even when evaluation is conducted on acted-speech datasets with different recording conditions. confidence: high relevance: low limitations: - 'The comparison between ZSDEVC and EMOCONV-DIFF in Table 1 is not fully fair: EMOCONV-DIFF is evaluated in a seen-speaker scenario while ZSDEVC operates zero-shot. The naturalness gap may reflect this experimental asymmetry rather than a fundamental quality deficit.' - The model does not address intensity control within a target emotion category — prior work (Emovox) provides per-dimension arousal/valence control that ZSDEVC does not directly expose during inference. Evaluation covers only five emotion categories (angry, happy, sad, neutral, surprise) and excludes neutral-to-emotional conversion. Real-time or streaming use cases are not addressed. Results on out-of-domain acted speech (ESD) and in-the-wild speech (MSP-Podcast) show consistent trends, but the system's behaviour on highly expressive or non-English speech is untested. caveats: [] - id: interspeech-2025-1106 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - codec architecture: - VAE - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: explicit_speaker_perturbation_during_codec_training_is_more_effective_for role: supports claim: Explicit speaker perturbation during codec training is more effective for speaker disentanglement than relying on implicit information bottleneck alone. source: §3.3, Table 2; §3.4 evidence: LSCodec achieves higher target-speaker SECS (0.852 at 50Hz) and lower speaker probing accuracy than TiCodec 1VQ (SECS 0.714), which uses an implicit VQ bottleneck without any perturbation, even though LSCodec operates at lower bitrate (0.45 kbps vs 0.75 kbps). confidence: high relevance: high - claim_id: single_codebook_discrete_speech_codecs_can_match_or_exceed_multi role: supports claim: Single-codebook discrete speech codecs can match or exceed multi-codebook acoustic codec reconstruction quality at ultra-low bitrates when content and speaker information are explicitly decoupled. source: §3.2, Table 1 evidence: LSCodec-50Hz (V=300, 0.45 kbps) achieves WER 3.33% and MOS 4.49 on LibriTTS test-clean, outperforming all single-codebook baselines including WavTokenizer-small (WER 7.86, MOS 4.14 at 0.48 kbps) and multi-codebook SemantiCodec (WER 4.16 at 0.63 kbps). confidence: high relevance: low - claim_id: reducing_codec_frame_rate_through_temporal_downsampling_degrades_content_intelligibility role: complicates claim: Reducing codec frame rate through temporal downsampling degrades content intelligibility without proportional improvement in speaker disentanglement. source: §3.2, Table 1; §3.3, Table 2 evidence: Halving the frame rate from 50Hz to 25Hz reduces bitrate from 0.45 to 0.25 kbps but increases reconstruction WER from 3.33% to 5.46% and VC WER from 4.04% to 6.32%, while reconstruction SECS changes only marginally (0.954 to 0.945). confidence: high relevance: high - claim_id: an_auxiliary_ssl_token_prediction_objective_is_necessary_for_maintaining role: refines claim: An auxiliary SSL token prediction objective is necessary for maintaining content intelligibility when an information bottleneck is used to remove speaker timbre. source: §3.5, Table 3 evidence: Ablating the SSL token prediction loss increases VAE-stage WER from 4.96% to 11.22% while SECS remains essentially unchanged (0.811 to 0.811), confirming that the SSL prediction task guides content encoding independently of the speaker removal objective. confidence: high relevance: high - claim_id: multi_stage_codec_training_establishing_a_continuous_disentangled_space_before role: supports claim: Multi-stage codec training, establishing a continuous disentangled space before quantization, improves both content preservation and speaker disentanglement compared to direct VQ training. source: §3.5, Table 3 evidence: Skipping stage 1 (VAE pre-training) and training VQ-VAE directly degrades WER from 3.39% to 3.84% and SECS from 0.817 to 0.800 in the VQ-VAE stage, confirming that continuous-space initialization benefits discrete representation quality. confidence: high relevance: high limitations: - The model is evaluated exclusively on English LibriTTS data, leaving multilingual and cross-lingual generalization untested. The vocoder (CTX-vec2wav alpha) is trained on a fixed 24 kHz corpus, so quality at other sampling rates or in noisy conditions is unclear. Speaker probing uses a single X-vector classifier on LibriTTS speakers, which may not detect all forms of residual speaker information. The paper notes that stronger perturbation methods, better content preservation at 25Hz, and scaling to larger data are open directions. No code or pre-trained models are released. caveats: [] - id: interspeech-2025-1210 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - diffusion relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion claims: - claim_id: dual_granularity_emotion_feature_extraction_combining_utterance_level_and_frame role: supports claim: Dual-granularity emotion feature extraction (combining utterance-level and frame-level representations) improves emotion discriminability in voice conversion compared to single-scale approaches. source: §2.1.3, §3.3.3, Table 3 evidence: DiffEmotionVC's dual-granularity emotion encoder achieves 80% ECA and 0.78 Pearson Corr on the ESD dataset; ablation confirms removing the emotion encoder is the most damaging intervention, dropping Corr to 0.38. confidence: high relevance: high - claim_id: orthogonality_constraints_on_emotion_speaker_and_content_feature_spaces_provide role: supports claim: Orthogonality constraints on emotion, speaker, and content feature spaces provide a stable and effective disentanglement mechanism for emotional voice conversion. source: §2.2.2, §3.3.3, Table 3 evidence: Removing orthogonal loss reduces SECS from 0.73 to 0.70 and Corr from 0.78 to 0.72; the paper explicitly motivates orthogonal loss as a remedy for the training instability of the mutual information loss used in prior work. confidence: high relevance: high - claim_id: diffusion_based_evc_systems_achieve_strong_overall_emotion_accuracy_but role: complicates claim: Diffusion-based EVC systems achieve strong overall emotion accuracy but struggle to discriminate between high-arousal emotions sharing similar arousal-valence profiles. source: §3.3.1 evidence: DiffEmotionVC reaches 80% ECA overall but the paper notes difficulty distinguishing happy, surprised, and angry, attributing this to insufficient emotional diversity in the ESD training data rather than a fundamental model limitation. confidence: high relevance: medium - claim_id: discretisation_of_continuous_speech_representations_degrades_emotion_voice_conversion_by role: complicates claim: Discretisation of continuous speech representations degrades emotion voice conversion by introducing content-emotion feature leakage. source: §3.3.2, Table 2 evidence: Replacing continuous ContentVec with VQ-ContentVec drops UTMOS from 4.04 to 2.54 and Corr from 0.78 to 0.50; SpeechTokenizer RVQ1 discrete features produce the worst performance (UTMOS 1.79), demonstrating that discrete tokens cause timbre and emotion entanglement. confidence: high relevance: high - claim_id: cross_attention_fusion_outperforms_additive_fusion_for_integrating_heterogeneous_speech role: supports claim: Cross-attention fusion outperforms additive fusion for integrating heterogeneous speech features in voice conversion systems. source: §3.3.3, Table 3 evidence: Ablation replacing gated cross-attention with simple additive fusion reduces UTMOS from 4.04 to 3.26, a 19% degradation in predicted audio quality. confidence: high relevance: high limitations: - Evaluation is limited to the ESD dataset (five emotions, primarily Mandarin Chinese; the ablation table specifically targets the zh-Angry subset), restricting generalisability to other languages and broader emotion categories. The model size is unreported, making deployment trade-off analysis impossible. Distinguishing between high-arousal emotions (happy, surprised, angry) remains unresolved; the paper identifies more naturalistic emotional data as the likely remedy but leaves this to future work. No code is released, and there is no cross-lingual evaluation. caveats: [] - id: interspeech-2025-1229 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: in_context_learning_with_flow_matching_can_enable_voice_conversion role: supports claim: In-context learning with flow matching can enable voice conversion systems to simultaneously transform speaker timbre and preserve background sounds without an explicit separation step. source: §4.2, Table 2 evidence: E2E-BPVC achieves BS-MOS 4.60 and SS-MOS 4.02 comparable to Denoise-VC II (BS-MOS 4.65, SS-MOS 4.07) using a single model without a denoising module, validated by 12 human raters on LibriTTS test-clean with synthetic noise and music backgrounds at 7 and 12 dB SNR. confidence: high relevance: high - claim_id: standard_voice_conversion_evaluation_metrics_speaker_similarity_character_error_rate role: complicates claim: Standard voice conversion evaluation metrics (speaker similarity, character error rate, speech quality) are insufficient for assessing systems that operate on speech with background sounds. source: §4.1, Table 1 evidence: ECAPA-TDNN speaker similarity and ASR-based CER are degraded by background sound in both source and converted audio, causing clean-output systems to appear relatively stronger on objective metrics despite failing entirely on background preservation (ICL-VC BS-MOS 0.70). The authors explicitly note that objective metrics "do not adequately reflect the capabilities" of background-preserving systems. confidence: high relevance: high - claim_id: noise_robust_self_supervised_speech_representations_improve_content_disentanglement_in role: supports claim: Noise-robust self-supervised speech representations improve content disentanglement in voice conversion systems trained on speech with background sounds. source: §4.3, Table 3 evidence: Replacing HuBERT with WavLM as the semantic token backbone reduces CER from 10.27 to 7.99 under noisy evaluation conditions, and training k-means on noisy speech (rather than clean speech) further reduces CER to 7.99 versus 9.22, demonstrating that noise robustness at the representation level propagates to improved content disentanglement. confidence: high relevance: high - claim_id: designing_a_single_voice_conversion_model_to_handle_background_preservation role: complicates claim: Designing a single voice conversion model to handle background preservation introduces a competing objective that slightly degrades clean-speech conversion quality relative to a clean-speech-only system. source: §4.1, Table 1 evidence: E2E-BPVC achieves SIM 0.849 and CER 3.18 on clean-speech conversion, modestly below ICL-VC (SIM 0.873, CER 2.37), reflecting a trade-off introduced by the shared background-preservation training objective. confidence: high relevance: high limitations: - The evaluation relies exclusively on LibriTTS with synthetically added noise and music at controlled SNRs (7 dB and 12 dB), without testing on real-world recordings where backgrounds are natural, non-stationary, or below 7 dB SNR. The comparison set is limited to two baselines sharing the same ICL-VC foundation, so performance relative to independent VC architectures is unknown. The paper also acknowledges that the current experiments use small-scale training data, and that scaling up is needed to improve robustness. The model offers no controllability over whether to preserve or suppress background sounds, though the authors identify this as future work. caveats: [] - id: interspeech-2025-1397 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - singing - VC architecture: - diffusion relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - diffusion_voice_conversion claims: - claim_id: explicit_frequency_domain_decomposition_of_the_f0_contour_enables_more role: supports claim: Explicit frequency-domain decomposition of the F0 contour enables more accurate and controllable singing style transfer than implicit style-embedding approaches. source: §4.1.1, Table 1 evidence: VibE-SVC achieves 0.700 style accuracy in style-only conversion versus 0.213-0.525 for SoVITS baselines using direct style embeddings, on the VocalSet straight/vibrato benchmark. confidence: high relevance: medium - claim_id: adversarial_training_on_the_target_frequency_band_of_the_f0 role: supports claim: Adversarial training on the target frequency band of the F0 contour improves singing style accuracy without degrading naturalness. source: §4.3, Table 1 evidence: Removing the multi-period discriminator reduces style accuracy from 0.700 to 0.625 and MOS from 4.124 to 4.016 in the style-only conversion experiment. confidence: high relevance: medium - claim_id: increasing_style_transfer_accuracy_in_singing_voice_conversion_trades_off role: complicates claim: Increasing style transfer accuracy in singing voice conversion trades off against naturalness, and explicit disentanglement does not fully eliminate this tension. source: §4.1.2, Figure 3 evidence: Figure 3 shows a consistent inverse correlation between MOS and style accuracy across all baselines and VibE-SVC; the highest-accuracy model (VibE-SVC) has lower naturalness than the highest-naturalness baseline (SoVITS with style embedding, 0.213 style accuracy). confidence: high relevance: high - claim_id: the_effective_granularity_of_f0_based_singing_style_disentanglement_via role: refines claim: The effective granularity of F0-based singing style disentanglement via DWT is sensitive to decomposition level, with an optimal level that captures vibrato without including unrelated high-frequency content. source: §4.3, Table 3 evidence: Style accuracy is 0.163 at DWT level 3 (vibrato information absent), 0.694 at level 4 (optimal), and drops slightly at level 5 due to inclusion of irrelevant high-frequency components. confidence: high relevance: medium - claim_id: vibrato_extent_in_singing_voice_conversion_can_be_controlled_continuously role: supports claim: Vibrato extent in singing voice conversion can be controlled continuously at inference time by scalar multiplication of the isolated high-frequency F0 component, without retraining. source: §4.2, Table 2, Figure 5 evidence: Scaling the high-frequency F0 contour from 0.1 to 2.0 produces style accuracy ranging from 0.066 to 0.928; frame-level control is also demonstrated by applying scaling at specific target frame indices. confidence: high relevance: high limitations: - The model is restricted to two singing styles (straight and vibrato) derived from VocalSet, and does not address other common techniques such as falsetto, breathy voice, belt, or melisma. Generalization to other datasets and languages is untested. The DWT wavelet type (db1) and decomposition level (4) are dataset-specific hyperparameters that may need re-tuning for other corpora or style targets. Human evaluation uses at minimum 20 Amazon MTurk raters per model, which is on the low end for resolving the small MOS differences reported. The speaker similarity scores in the timbre and style conversion setting (SMOS 3.196) are noticeably lower than ground truth (3.549), suggesting that joint timbre and style conversion remains a meaningful challenge. caveats: [] - id: interspeech-2025-1434 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - diffusion relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion claims: - claim_id: full_utterance_time_reversal_can_serve_as_an_effective_signal role: supports claim: Full-utterance time reversal can serve as an effective signal-level data augmentation for speaker representation learning in voice conversion, as it suppresses phonemic content while retaining speaker-discriminative tonal features. source: §3.1, Table 1 evidence: A perceptual study shows 80.3% speaker identification accuracy from time-reversed speech; Table 1 confirms complete reversal achieves 100% WER (full linguistic removal) alongside the highest cosine speaker similarity score (0.96), higher than any short-time reversal window. confidence: high relevance: high - claim_id: fusing_speaker_embeddings_from_augmented_training_signals_with_conventional_embeddings role: supports claim: Fusing speaker embeddings from augmented training signals with conventional embeddings improves speaker similarity in zero-shot diffusion-based voice conversion. source: §4.3, Table 2 evidence: Adding reversed-speech speaker embeddings via a weighted fusion layer (α = β = 0.5) improves objective speaker similarity by 4.16% on average across DiffHierVC and DDDM-VC; DDDM-VC objective SPK-SIM rises from 0.70 to 0.79 and subjective MUSHRA from 77.46 to 78.61. confidence: high relevance: high - claim_id: the_effectiveness_of_speaker_embedding_augmentation_in_voice_conversion_varies role: complicates claim: The effectiveness of speaker embedding augmentation in voice conversion varies substantially across backbone architectures, complicating claims of generalisability. source: §4.3, Table 2 evidence: For DiffVC, the augmentation improves subjective speaker similarity (50.12 to 53.42) but reduces objective similarity (0.75 to 0.71), while DiffHierVC shows objective improvement but negligible subjective change; only DDDM-VC shows consistent gains on both metrics. confidence: high relevance: high - claim_id: improving_speaker_disentanglement_through_augmentation_does_not_necessarily_trade_off role: supports claim: Improving speaker disentanglement through augmentation does not necessarily trade off against generated speech quality in diffusion-based voice conversion. source: §4.3, Table 2 evidence: DDDM-VC+Ours improves both WV-MOS (3.84 to 3.91) and UTMOS (3.21 to 3.55) alongside speaker similarity gains, indicating that stronger speaker conditioning from the STR augmentation does not degrade synthesis quality. confidence: high relevance: high limitations: - 'Objective and subjective speaker similarity disagree for DiffVC: the augmentation reduces objective similarity (0.75 to 0.71) while improving subjective similarity (50.12 to 53.42). This discrepancy limits confidence in the metric-level generalisation claim across all diffusion backbones. *(§4.3, Table 2)*' - 'The perceptual study supporting the STR principle is small: 25 participants and 6 speakers, all in English. Whether the tonal-pattern preservation property holds equally for tonal languages (Mandarin, Thai) or heavily inflected languages is untested. The approach has been evaluated only on diffusion-based VC systems; compatibility with flow-matching and codec-based VC architectures remains unexplored. No code is publicly released, limiting reproducibility. The weighted fusion coefficients (α and β) are set empirically to 0.5; the paper does not explore learned dynamic weighting conditioned on the input utterance.' caveats: [] - id: interspeech-2025-1440 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - codec architecture: - VAE relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - vae_latent_voice_conversion claims: - claim_id: self_supervised_disentanglement_of_speech_into_content_speaker_and_prosody role: supports claim: Self-supervised disentanglement of speech into content, speaker, and prosody streams can match or exceed supervised codec quality at significantly lower bitrate. source: §4.1, Table 1, Table 2 evidence: Self-supervised disentanglement of speech into content, speaker, and prosody streams can match or exceed supervised codec quality at significantly lower bitrate. confidence: high relevance: low - claim_id: codec_coding_efficiency_is_more_sensitive_to_information_factorisation_than role: supports claim: Codec coding efficiency is more sensitive to information factorisation than to raw model capacity or bitrate allocation. source: §4.1, Table 1 evidence: Codec coding efficiency is more sensitive to information factorisation than to raw model capacity or bitrate allocation. confidence: high relevance: low - claim_id: routing_wavlm_supervision_to_the_decoder_rather_than_the_encoder role: supports claim: Routing WavLM supervision to the decoder rather than the encoder during training improves speaker-content disentanglement for voice conversion. source: §2.5, §4.2 evidence: Routing WavLM supervision to the decoder rather than the encoder during training improves speaker-content disentanglement for voice conversion. confidence: high relevance: high - claim_id: ultra_low_bitrate_codecs_below_0_5_kbps_can_achieve role: supports claim: Ultra-low-bitrate codecs (below 0.5 kbps) can achieve MUSHRA scores competitive with codecs operating at 2–3 kbps when disentanglement is applied to reduce frame-level redundancy. source: §4.1, Table 2 evidence: Ultra-low-bitrate codecs (below 0.5 kbps) can achieve MUSHRA scores competitive with codecs operating at 2–3 kbps when disentanglement is applied to reduce frame-level redundancy. confidence: high relevance: medium limitations: - The demo and code availability are not confirmed in the paper or metadata. Reproducibility relies on external checkpoints for baselines — FACodec and SpeechTokenizer results are inferred from official checkpoints under potentially different conditions than the re-trained TiCodec and DAC baselines. - Evaluation is restricted to English (LibriSpeech and VCTK). Generalisation to other languages, accents, or spontaneous-speech domains is untested. The prosody encoder's low-mel-bin design is validated empirically via t-SNE visualisation but without a formal mutual information analysis. It is unclear how much prosody actually remains once the speaker and content encoders are also active during decoding — partial speaker clustering in Fig. 2 suggests the separation is not complete. caveats: [] - id: interspeech-2025-1531 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - singing - VC architecture: - VAE - GAN relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - vae_latent_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: in_singing_voice_conversion_reducing_the_dimensionality_of_ssl_embeddings role: supports claim: In singing voice conversion, reducing the dimensionality of SSL embeddings through random channel selection proportionally reduces timbre leakage while preserving sufficient phonetic content for accurate reconstruction. source: §4. Results, Table 1 evidence: SSL-128-Emb (128 of 768 HuBERT dimensions) achieves SMOS 3.920 vs. SSL-Emb's 2.750 on the Chinese test set, while maintaining CMOS 4.244 vs. 4.366 for full embeddings. The pattern holds for SSL-Soft and ContentVec variants. confidence: high relevance: high - claim_id: discrete_token_based_content_representations_for_voice_conversion_cannot_generalize role: complicates claim: Discrete token-based content representations for voice conversion cannot generalize to phonetic inventories outside the training distribution. source: §4. Results, Table 2 evidence: SSL-Token CMOS drops from 4.086 on Chinese to 3.210 on other languages (English, Korean, Vietnamese, Japanese, Cantonese), demonstrating that k-means quantization of HuBERT with up to 10,000 clusters still loses phonetic detail that is language-specific. Continuous dimension-reduced embeddings maintain CMOS above 4.17 across both conditions. confidence: high relevance: high - claim_id: self_supervised_speech_embedding_dimensions_contain_roughly_proportional_timbre_and role: supports claim: Self-supervised speech embedding dimensions contain roughly proportional timbre and content signal, such that uniform random subsampling functions as an effective form of timbre disentanglement. source: §2.2 Proposed Content Encoder, §4. Results evidence: The uniform-distribution assumption underlying random dimension selection is empirically supported by consistent improvements across three distinct SSL embedding types (HuBERT, SSL-Soft, ContentVec), each responding to dimension reduction in the same direction. confidence: high relevance: high - claim_id: supervised_disentanglement_methods_for_ssl_content_encoders_in_voice_conversion role: refines claim: Supervised disentanglement methods for SSL content encoders in voice conversion can be matched or exceeded by unsupervised dimensionality reduction at equivalent embedding sizes. source: §4. Results, Table 1, Table 2 evidence: SSL-256-Emb surpasses SSL-Soft-Emb (which uses supervised soft target training) at the same 256-dimensional size on both SSIM and SMOS metrics in Chinese. ContentVEC-256-Emb matches token-based singer similarity while outperforming token-based CMOS on cross-lingual evaluation. confidence: high relevance: high limitations: - All training data is proprietary (200h internal Chinese singing corpus). No public benchmark or standard SVC evaluation set is used, making direct comparison to other published SVC systems infeasible. - The geometric assumption that timbre and content are uniformly distributed across SSL embedding dimensions is intuitive but unverified; the actual structure of HuBERT's representation space may be far from uniform, and it is unclear whether the technique generalises beyond informal Chinese singing. The optimal dimension count d is determined by grid search over 128 and 256 with no principled selection criterion. As d approaches zero, content reconstruction quality must eventually degrade, but the paper does not characterise this failure regime. The multilingual test set covers a limited set of languages, and the cross-lingual results do not control for dataset recording conditions. caveats: [] - id: interspeech-2025-1538 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: conditioning_acoustic_generation_on_explicitly_predicted_text_tokens_reduces_intelligibility role: supports claim: Conditioning acoustic generation on explicitly predicted text tokens reduces intelligibility errors in autoregressive voice conversion relative to purely acoustic-domain approaches. source: §3.3.3, Table 1 evidence: Removing text token generation from StarVC raises WER from 6.27% to 7.30% and SECS-WavLM drops from 0.472 to 0.382; StarVC achieves the lowest WER and CER among all compared systems including diffusion-based CosyVoice (8.24%/4.27%). confidence: high relevance: high - claim_id: multi_stage_training_that_initializes_voice_conversion_with_asr_pretraining role: supports claim: Multi-stage training that initializes voice conversion with ASR pretraining improves both content preservation and speaker similarity relative to single-stage training. source: §3.3.3, Table 1 evidence: Removing multi-stage training degrades SECS-Res from 0.835 to 0.812 and raises WER from 6.27% to 7.24%; multi-stage training is the single largest contributor in the ablation study. confidence: high relevance: high - claim_id: objective_speaker_embedding_metrics_and_perceptual_speaker_similarity_ratings_can role: complicates claim: Objective speaker embedding metrics and perceptual speaker similarity ratings can diverge for codec-based voice conversion systems trained with strong linguistic objectives. source: §3.3.1, §3.3.2, Tables 1-2 evidence: StarVC scores marginally below CosyVoice on SECS-Res (0.835 vs. 0.839) and SECS-WavLM (0.472 vs. 0.478), yet exceeds CosyVoice on subjective SMOS (3.98 vs. 3.94), suggesting embedding-based metrics underestimate perceived similarity for this system class. confidence: high relevance: high - claim_id: autoregressive_voice_conversion_systems_can_produce_explicit_transcription_output_alongside role: refines claim: Autoregressive voice conversion systems can produce explicit transcription output alongside converted audio at negligible additional cost, enabling inline content verification without separate ASR inference. source: §3.3.1, Table 1 evidence: StarVC generates text tokens with WER-Text of 4.95% and CER-Text of 1.51% as a byproduct of the VC decoding process, providing word-level content verification as part of the conversion pipeline. confidence: high relevance: high limitations: - Subjective MOS evaluation involves only 20 listeners and 20 source-target pairs, making the reported SMOS and NMOS advantages over CosyVoice and OpenVoice V2 (all within overlapping confidence intervals) difficult to interpret as significant. - The evaluation covers English only on a single clean corpus (LibriTTS test-clean). Generalization to cross-lingual conversion, noisy conditions, or longer conversational utterances is untested. The three-stage training pipeline requires 180 GPU-hours on 8 H100s, representing a substantial compute cost that may limit practical adoption. Data augmentation relies on OpenVoice V2-synthesized speech, which could propagate artifacts from that system into StarVC's training distribution. Whether the text-before-speech decoding constraint generalizes to expressive or emotional speech conversion, where prosody is not captured by a pure transcription, remains an open question. caveats: [] - id: interspeech-2025-1550 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - TTS - VC - evaluation architecture: - transformer-enc-dec - VAE - GAN relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution - infrastructure current_role: active_evidence method_family: - transformer_encoder_decoder_voice_conversion - vae_latent_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: diacritization_of_arabic_text_input_significantly_improves_tts_intelligibility_and role: supports claim: Diacritization of Arabic text input significantly improves TTS intelligibility and subjective quality in Modern Standard Arabic synthesis. source: §4.1, Table 4 evidence: VITS trained with diacritics achieved 20.67% WER versus 35.69% without, and was the only model with a statistically significant preference for the diacritized variant in pairwise preference tests with native speakers. confidence: high relevance: medium - claim_id: multi_speaker_training_improves_synthesis_quality_for_individual_target_speakers role: supports claim: Multi-speaker training improves synthesis quality for individual target speakers relative to speaker-specific training on equivalent data volume. source: §4.1, Figure 2b evidence: Multi-speaker VITS was strongly preferred over single-speaker VITS trained on the same speaker's 2.69 hours; both models were evaluated on the same speaker in a pairwise preference test. confidence: high relevance: medium - claim_id: synthetic_speech_data_augmentation_can_improve_tts_intelligibility_even_when role: supports claim: Synthetic speech data augmentation can improve TTS intelligibility even when the augmenting speech is of variable quality. source: §4.1 evidence: Training VITS on all ArVoice parts including synthetic speech (Google Standard and WaveNet TTS) reduced WER by 8.2% absolute versus human-speech-only training, with pairwise preference also favoring the augmented model (44% vs 30%). confidence: high relevance: medium - claim_id: multilingual_llm_based_tts_systems_do_not_reliably_transfer_to role: complicates claim: Multilingual LLM-based TTS systems do not reliably transfer to Arabic without adequate language-specific training data or adaptation, and can produce unintelligible output despite fine-tuning. source: §4.1, Table 4 evidence: Fish-Speech, a dual-autoregressive LLM-based multilingual system, achieved WER above 100% on Arabic after fine-tuning on ArVoice human speech, and was excluded from subjective evaluation due to confirmed low intelligibility. confidence: high relevance: medium limitations: - The professionally recorded portions of ArVoice (Parts 1 and 2) are not freely downloadable; access requires signing a formal Data Usage Agreement. Only the ASC-derived and synthetic portions are available under CC BY 4.0. This limits reproducibility for experiments requiring the full human-voice data. - Human speech totals approximately 10 hours across 7 speakers, which is sufficient for fine-tuning but constraining for zero-shot multi-speaker TTS or large-scale model training. Coverage is restricted to Modern Standard Arabic; dialectal varieties are not represented, leaving adaptation to Egyptian, Gulf, or Moroccan Arabic as an open problem. Each preference test uses 25 samples evaluated by at least 10 raters per pair, which is adequate for detecting large differences but may lack power for subtle distinctions. The evaluation of VC systems relies on automated speaker verification similarity scores rather than human perceptual evaluation of voice identity. caveats: [] - id: interspeech-2025-1625 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: active_adversarial_defense_mechanisms_can_prevent_voice_conversion_models_from role: supports claim: Active adversarial defense mechanisms can prevent voice conversion models from extracting speaker characteristics without sacrificing perceptual audio quality. source: §3.2, Table 1 evidence: Mimic Blocker achieves PESQ 3.633 and STOI 0.942 on VCTK while maintaining ASR above 0.88 in both white-box and black-box conditions, compared to PESQ 1.61-1.99 for prior baselines at equivalent or lower ASR levels. confidence: high relevance: high - claim_id: pretrained_self_supervised_speech_representations_can_serve_as_model_agnostic role: supports claim: Pretrained self-supervised speech representations can serve as model-agnostic attack targets for VC defense, enabling consistent protection across different VC architectures without retraining. source: §3.1, §3.2, Table 1, Table 2 evidence: Training with WavLM (white-box) and HuBERT (black-box) as feature extractors, Mimic Blocker achieves ASR of 0.88 on FreeVC and 0.99 on TriAAN-VC with the same trained model, demonstrating cross-architecture transfer. confidence: high relevance: medium - claim_id: waveform_domain_adversarial_perturbation_preserves_speech_naturalness_better_than_spectrogram role: supports claim: Waveform-domain adversarial perturbation preserves speech naturalness better than spectrogram-domain approaches in voice conversion defense. source: §2.2, §3.2, §3.3, Table 1 evidence: Prior defenses applying attacks in the Mel-spectrogram domain with vocoder reconstruction achieve PESQ 1.61-1.99; Mimic Blocker's direct waveform noise injection achieves PESQ 3.633, and 99.7% of evaluators judge the perturbed waveform as perceptually identical to the original speaker. confidence: high relevance: high - claim_id: active_vc_defense_training_does_not_require_target_speaker_data role: refines claim: Active VC defense training does not require target speaker data, relaxing a key dependency of earlier adversarial protection methods. source: §2.3, §1 evidence: Unlike DYV and RW-VoiceShield, which require style-and-target speech pairs during training, Mimic Blocker uses only the original speaker's own speech by maximizing the L2 distance between SSL embeddings of original and perturbed waveforms via a self-supervised loss. confidence: high relevance: high limitations: - The subjective evaluation involves only 6 evaluators assessing 50 speech pairs from VCTK. This panel size is small by standard listening-test norms and may not capture evaluator diversity or yield statistically robust naturalness estimates. - Evaluation is limited to two VC models (FreeVC, TriAAN-VC) on a single English dataset; performance against other VC architectures and non-English speakers is unknown. Training requires approximately 25 hours on an NVIDIA RTX 4090, which could be a practical barrier if per-speaker models are needed at scale. The white-box and black-box definitions are modified from prior work to accommodate the model-agnostic design, making direct numerical comparison with all earlier methods imprecise. It remains unclear how robust the defense is against adaptive attacks specifically designed to counter WavLM/HuBERT-based perturbations. caveats: [] - id: interspeech-2025-1639 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - codec - VC architecture: - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: targeted_distillation_into_specific_rvq_layers_can_isolate_fine_grained role: supports claim: Targeted distillation into specific RVQ layers can isolate fine-grained speaking style attributes (such as vocal effort) independently of semantic content in neural speech codecs. source: §2.3, §3.1, Table 2 evidence: LombardTokenizer conditions the second RVQ layer via cosine distillation from Lombard speech encoders while keeping RVQ layer 1 semantically focused via mHuBERT; the resulting system achieves WER 10.97% and EER 6.67% on vocal effort conversion on AVID, substantially outperforming FreeVC (WER 20.35%, EER 16.67%) while retaining comparable synthesis quality (PESQ 3.07 vs. SpeechTokenizer 3.01). confidence: high relevance: medium - claim_id: disentanglement_constraints_in_neural_codecs_reduce_unconstrained_reconstruction_quality_relative role: complicates claim: Disentanglement constraints in neural codecs reduce unconstrained reconstruction quality relative to codecs without regularisation. source: §3.1, Table 1 evidence: EnCodec (no disentanglement) achieves PESQ 3.32 and STOI 0.94 on LibriSpeech, while LombardTokenizer's dual distillation (semantic and Lombard) yields PESQ 3.07 and STOI 0.93, consistent with SpeechTokenizer's 3.01; the quality gap widens on in-distribution neutral speech but narrows on expressive zero-shot data. confidence: high relevance: medium - claim_id: providing_a_specialized_style_encoder_to_a_voice_conversion_model role: complicates claim: Providing a specialized style encoder to a voice conversion model architecture does not guarantee that the encoder's information will be effectively exploited for style control. source: §3.2, Table 2, Figure 2 evidence: FreeVC modified with the same Lombard encoder (FVClmb) fails to produce statistically distinguishable vocal effort levels in perceptual evaluation, and degrades WER on FLombard (32.63%) relative to the standard speaker-encoder variant (24.04%), while LT1 using the same encoder via RVQ distillation achieves WER 17.74% and accurate perceptual effort transfer. confidence: high relevance: high - claim_id: zero_shot_generalization_of_speaking_style_transfer_across_languages_is role: supports claim: Zero-shot generalization of speaking style transfer across languages is achievable when codec disentanglement is guided by multilingual self-supervised representations. source: §2.1, §3.2, Table 2 evidence: LombardTokenizer trained on English AVID achieves WER 15.77% on the unseen French FLombard dataset (zero-shot), compared to FreeVC's 24.04–32.63%; the paper attributes part of this advantage to replacing HuBERT with multilingual mHuBERT in the semantic RVQ layer. confidence: high relevance: low - claim_id: codec_level_disentanglement_enables_robust_cross_speaker_style_transfer_with role: supports claim: Codec-level disentanglement enables robust cross-speaker style transfer with low speaker identity leakage under both intra-speaker and inter-speaker conditions. source: §3.2, Table 2, Figure 2 evidence: LombardTokenizer inter-speaker vocal effort conversion produces perceptual distributions not significantly different from intra-speaker conversion (Dunn's test), with EER remaining below 8% on AVID for both LT1 (6.67%) and LT2 (7.83%), indicating preserved speaker identity. confidence: high relevance: high limitations: - The zero-shot evaluation is from English training to French test data, and both languages are Indo-European — the claim of cross-lingual generalisation has not been tested on typologically distant languages. - The model is evaluated on controlled intensity datasets (AVID, FLombard) and trained on studio-quality recordings; performance in real-world noisy conditions or spontaneous Lombard speech is unknown. The AVID dataset uses instructed intensity levels rather than naturally elicited Lombard speech, which may reduce ecological validity. Synthesis quality is measured with PESQ and STOI, which emphasise intelligibility and signal fidelity but may not capture naturalness of expressive speech styles. The study does not address how many simultaneous disentanglement targets an RVQ structure can support before quality degrades substantially. caveats: [] - id: interspeech-2025-1747 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - diffusion - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: performing_knowledge_distillation_in_the_conversion_process_rather_than_the role: supports claim: Performing knowledge distillation in the conversion process rather than the reconstruction process is necessary to avoid identity-mapping collapse when the content encoder is simultaneously trainable. source: §4.2, Table 1, Table 2 evidence: Baseline reconstruction-distillation with trainable CNN (FastVoiceGrad + pϕ) achieves UTMOS 3.45 and SECS 0.718; switching to conversion-based ADCD raises these to 4.03 and 0.853, respectively. Direct distillation (an alternative that avoids conversion-process training) degrades to UTMOS 3.35 with a 1-layer encoder, confirming the mechanism failure. confidence: high relevance: medium - claim_id: simultaneously_distilling_both_the_diffusion_backbone_and_the_content_encoder role: supports claim: Simultaneously distilling both the diffusion backbone and the content encoder of a one-step diffusion VC model can reduce inference cost substantially with little or no quality degradation relative to distilling only the diffusion module. source: §4.3, Table 3, Table 5 evidence: FasterVoiceGrad (joint distillation) achieves UTMOS 4.03 and SECS 0.853 vs. FastVoiceGrad's 3.96 and 0.847, while delivering 6.6x GPU RTF and 1.8x CPU RTF improvement across both VCTK and LibriTTS evaluations. confidence: high relevance: medium - claim_id: neural_speaker_encoder_based_similarity_metrics_may_not_reflect_perceptual role: complicates claim: Neural speaker-encoder-based similarity metrics may not reflect perceptual speaker identity as judged by human listeners, particularly when source speaker residuals remain after conversion. source: §4.3, Table 3, Table 4 evidence: FasterVoiceGrad scores higher SECS (0.853 vs. 0.847) than FastVoiceGrad but lower sMOS (2.66 vs. 2.84); the authors attribute the discrepancy to the CNN content encoder not explicitly removing source speaker characteristics, which humans but not speaker encoders detect. confidence: high relevance: high - claim_id: contrastive_speaker_emphasis_via_inverse_score_distillation_mitigates_the_trade role: refines claim: Contrastive speaker emphasis via inverse score distillation mitigates the trade-off between content preservation and speaker conversion when joint distillation is used. source: §4.2, Table 1 evidence: Adding inverse score distillation on top of reconversion-based distillation improves SECS from 0.844 to 0.853 without degrading CER (1.2) or UTMOS (4.03), recovering the speaker similarity lost by reconversion's content preservation bias. confidence: high relevance: high limitations: - The CNN content encoder does not explicitly separate source speaker identity from linguistic content. Subjective sMOS scores (2.66) are measurably lower than FastVoiceGrad's (2.84), suggesting residual source voice characteristics persist and limit perceptual speaker conversion quality despite competitive automatic metrics. - Subjective evaluation involved only 11 participants and 90 speaker/sentence pairs, which constrains the statistical power of the sMOS comparisons. The GPU speedup (6.6x) is larger than the CPU speedup (1.8x), reflecting architectural factors that may affect deployment on edge hardware differently. The study does not evaluate against modern flow-matching or large-scale VC baselines, leaving the system's position in the broader landscape uncharacterised. Future directions suggested include accent conversion and real-time VC applications. caveats: [] - id: interspeech-2025-1763 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - GAN - diffusion relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - gan_adversarial_voice_conversion - diffusion_voice_conversion claims: - claim_id: intermediate_vocoder_features_after_partial_upsampling_are_sufficient_for_waveform role: supports claim: Intermediate vocoder features after partial upsampling are sufficient for waveform-quality adversarial discrimination of acoustic feature generators. source: §3.2, Tables 1 and 5, Figure 3 evidence: FVG + VPFD₁ (single upsampling step, 8x) matches full waveform discriminator performance on UTMOS, DNSMOS, CER, and SECS across both VCTK and LibriTTS; visualisation shows periodic waveform structures emerge after one upsampling step. confidence: high relevance: medium - claim_id: freezing_pretrained_feature_extractors_in_projected_gan_discriminators_is_essential role: supports claim: Freezing pretrained feature extractors in projected GAN discriminators is essential for acoustic synthesis quality. source: §3.2, Table 2 evidence: 'Ablation shows that both pretraining and freezing V_feat are independently necessary: omitting either degrades UTMOS, DNSMOS, and SECS, with no change in training time or memory.' confidence: high relevance: medium - claim_id: waveform_domain_discriminators_in_two_stage_tts_vc_training_are role: complicates claim: Waveform-domain discriminators in two-stage TTS/VC training are effective but impose resource costs that make them impractical outside well-resourced settings. source: §1, §3.3, Tables 1 and 3 evidence: VWD (MPD + MRD applied to vocoder output) requires 47 hours and 66.3 GB GPU memory on VCTK; mel-spectrogram discriminators avoid this cost but fail to match waveform-domain quality on DNSMOS regardless of model size. confidence: high relevance: medium - claim_id: for_vocoder_based_feature_projection_a_minimum_of_one_upsampling role: refines claim: For vocoder-based feature projection, a minimum of one upsampling step is necessary to produce the periodic structures required for effective adversarial discrimination. source: §3.2, Table 1, Figure 3 evidence: VPFD₀ (no upsampling) significantly degrades DNSMOS (3.66 vs. 3.79) and SECS (0.843 vs. 0.851) relative to VPFD₁; Figure 3 shows periodic structures absent in mel spectrograms and zero-upsampling features appear only after one step. confidence: high relevance: medium limitations: - VPFD is validated only on one VC system (FastVoiceGrad on VoiceGrad) and never on a TTS system, despite TTS being a stated target application. The subjective evaluation involves only 11 participants, which is small for a listening test. All experiments use 22.05 kHz audio with 80-dimensional log-mel spectrograms and HiFi-GAN V1 as the vocoder; performance with other vocoders, sample rates, or codec-based acoustic representations is unknown. The approach requires a high-quality pretrained vocoder whose intermediate features provide sufficient discriminative power, which may not hold for vocoders trained on limited or mismatched data. caveats: [] - id: interspeech-2025-1779 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: rectified_flow_achieves_comparable_or_better_sample_quality_to_diffusion role: supports claim: Rectified flow achieves comparable or better sample quality to diffusion for voice conversion at substantially fewer inference steps. source: §4.2, Table 1 evidence: Rectified flow achieves comparable or better sample quality to diffusion for voice conversion at substantially fewer inference steps. confidence: high relevance: high - claim_id: conditioning_speaker_embeddings_on_concurrent_content_and_pitch_features_improves role: supports claim: Conditioning speaker embeddings on concurrent content and pitch features improves speaker similarity in zero-shot voice conversion. source: §3.1, §4.2, Table 1 evidence: Conditioning speaker embeddings on concurrent content and pitch features improves speaker similarity in zero-shot voice conversion. confidence: high relevance: high - claim_id: a_single_step_ode_solver_can_match_the_quality_of role: supports claim: A single-step ODE solver can match the quality of dozens of diffusion steps when the flow trajectories are sufficiently linear. source: §4.2, Table 1 evidence: A single-step ODE solver can match the quality of dozens of diffusion steps when the flow trajectories are sufficiently linear. confidence: high relevance: medium - claim_id: recursive_rectification_retraining_on_model_generated_samples_yields_only_marginal role: supports claim: Recursive rectification (retraining on model-generated samples) yields only marginal improvements when the initial model is already well-trained. source: §4.2, Table 2 evidence: Recursive rectification (retraining on model-generated samples) yields only marginal improvements when the initial model is already well-trained. confidence: high relevance: medium limitations: - The model is trained and evaluated on a 38-hour clean subset of LibriTTS with a single-GPU budget, and evaluated only on same-domain test utterances. Generalisation to out-of-domain or expressive speech is neither tested nor discussed. - Speaker similarity scores (SECS ~0.84) are competitive but still well below the vocoder upper bound (0.987), suggesting substantial headroom. WER and CER remain measurably above the ground truth pipeline (CER 2.12 vs. 0.52 for GT), indicating some content leakage. The pitch extraction step adds over 1 second of preprocessing latency for a ~9-second utterance, which limits real-time applicability. The paper does not report real-time factor (RTF) or measure latency end-to-end. It is also unclear how performance scales with reference speech duration — the evaluation uses a fixed 4.7-second target clip. caveats: [] - id: interspeech-2025-1993 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - TTS - VC architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: embedding_watermark_detection_directly_into_codec_encoder_training_is_a role: supports claim: Embedding watermark detection directly into codec encoder training is a viable alternative to post-hoc or hard-coded watermark gates for protecting open-source zero-shot TTS models. source: §2.2, §3.3.1 evidence: Embedding watermark detection directly into codec encoder training is a viable alternative to post-hoc or hard-coded watermark gates for protecting open-source zero-shot TTS models. confidence: high relevance: low - claim_id: neural_codec_architectures_are_a_natural_intervention_point_for_access role: supports claim: Neural codec architectures are a natural intervention point for access-control in speaker-conditioned TTS because they mediate all speaker information transfer from prompt to synthesis. source: §1, §2.3 evidence: Neural codec architectures are a natural intervention point for access-control in speaker-conditioned TTS because they mediate all speaker information transfer from prompt to synthesis. confidence: high relevance: low - claim_id: training_time_augmentation_with_common_audio_distortions_substantially_improves_a role: supports claim: Training-time augmentation with common audio distortions substantially improves a codec's robustness to watermark removal attacks without degrading reconstruction quality on clean audio. source: §2.2, Table 1, Table 2 evidence: Training-time augmentation with common audio distortions substantially improves a codec's robustness to watermark removal attacks without degrading reconstruction quality on clean audio. confidence: high relevance: low - claim_id: codec_level_defenses_for_voice_cloning_create_a_structural_barrier role: supports claim: Codec-level defenses for voice cloning create a structural barrier to adaptation attacks because TTS models trained on modified codec distributions cannot be trivially swapped to unprotected codecs without retraining. source: §2.3, §3.3.2 evidence: Codec-level defenses for voice cloning create a structural barrier to adaptation attacks because TTS models trained on modified codec distributions cannot be trivially swapped to unprotected codecs without retraining. confidence: high relevance: high limitations: - The defense is effective only against speech watermarked with the specific watermarking model (AudioSeal) used during codec training. A copyrighted voice that is unwatermarked — or that is protected with a different, unseen watermarking system — receives no protection. The attacker simply needs to avoid using an AudioSeal-watermarked prompt. - The evaluation is conducted only on the VALL-E architecture and EnCodec backbone; whether the approach generalizes to other zero-shot TTS architectures (e.g., flow-matching or diffusion-based systems) is not tested. All data is clean studio speech (LibriSpeech/LibriTTS-R); robustness in noisy or spontaneous speech conditions is unknown. The speed adjustment and low-pass filter attacks are reported as failures for the codec detector, though the authors argue these attacks also degrade clean prompts, partially neutralising them as practical bypass routes. No listening test compares watermark-rejected output against human expectations of what a "protection failure" looks and sounds like. caveats: [] - id: interspeech-2025-2043 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_voice_conversion claims: - claim_id: training_free_voice_conversion_based_on_distribution_matching_in_self role: complicates claim: Training-free voice conversion based on distribution matching in self-supervised embedding subspaces can achieve speaker similarity and content preservation comparable to trained codec-based systems when reference audio is limited to a few seconds. source: §4.4, Table 2 evidence: Training-free voice conversion based on distribution matching in self-supervised embedding subspaces can achieve speaker similarity and content preservation comparable to trained codec-based systems when reference audio is limited to a few seconds. confidence: high relevance: high - claim_id: the_nearest_neighbour_approach_in_knn_style_voice_conversion_degrades role: supports claim: The nearest-neighbour approach in kNN-style voice conversion degrades significantly in cross-lingual settings because phoneme-level proximity in the embedding space conflates content with language-specific pronunciation. source: §1, §4.4, Table 3 evidence: The nearest-neighbour approach in kNN-style voice conversion degrades significantly in cross-lingual settings because phoneme-level proximity in the embedding space conflates content with language-specific pronunciation. confidence: high relevance: high - claim_id: non_uniform_variance_structure_in_self_supervised_speech_representations_makes role: supports claim: Non-uniform variance structure in self-supervised speech representations makes global optimal transport maps suboptimal; factorizing the embedding space by variance before applying transport improves both content preservation and numerical stability. source: §3 evidence: Non-uniform variance structure in self-supervised speech representations makes global optimal transport maps suboptimal; factorizing the embedding space by variance before applying transport improves both content preservation and numerical stability. confidence: high relevance: medium - claim_id: a_content_speaker_similarity_trade_off_is_inherent_to_wavlm role: complicates claim: A content-speaker-similarity trade-off is inherent to WavLM-based voice conversion and can be navigated via the block-size hyperparameter of a factorized transport scheme. source: §4.4, Table 2 evidence: A content-speaker-similarity trade-off is inherent to WavLM-based voice conversion and can be navigated via the block-size hyperparameter of a factorized transport scheme. confidence: high relevance: high limitations: - The Gaussian assumption underlying MKL-VC is specific to WavLM-Large embeddings, as demonstrated empirically. The authors explicitly note that for any new encoder the assumption must be verified from scratch, making the method non-portable without additional analysis effort. - The method is evaluated only against objective metrics (WER, CER, X-vector cosine similarity) on LibriSpeech and FLEURS, and a small subjective ranking with six experts. No MOS or MUSHRA scores are reported, and the subjective evaluation is a ranking rather than an absolute naturalness measure, making it difficult to position MKL-VC on the standard VC evaluation scale. - Diff-VC was evaluated on only 855 of 7800 samples due to compute constraints; its baseline number may therefore be unreliable for fair comparison. SinkVC is a re-implementation rather than the official release, introducing uncertainty about whether the reported gap to MKL-VC reflects the method or the reimplementation fidelity. - No code or demo is linked in the paper; reproducibility depends on the authors releasing code. caveats: [] - id: interspeech-2025-2151 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC - evaluation architecture: - GAN relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution - infrastructure current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: objective_voice_conversion_evaluation_metrics_that_require_ground_truth_utterances role: supports claim: Objective voice conversion evaluation metrics that require ground-truth utterances (MCD, F0-RMSE, FFE, GPE) are only feasible when a parallel corpus exists, making dataset parallelism a prerequisite for rigorous VC benchmarking. source: §1.3 evidence: The authors identify the absence of parallel Farsi data as the direct reason these objective metrics cannot be applied to existing Farsi corpora; FaVC is designed specifically to make them feasible. confidence: high relevance: high - claim_id: gan_based_voice_conversion_systems_trained_on_parallel_corpora_in role: supports claim: GAN-based voice conversion systems trained on parallel corpora in low-resource languages can reach naturalness and speaker similarity scores comparable to training on established English benchmarks. source: §4.3, Table 2 evidence: CycleGAN-VC, StarGAN-VC, StarGAN-VC2, and StarGANv2-VC trained on FaVC achieve MOS-N scores of 3.3–3.94 and MOS-P of 2.5–4.1, within the range of the same models trained on VCC2018 under identical configuration. confidence: high relevance: high - claim_id: non_english_voice_conversion_research_is_limited_by_the_near role: complicates claim: Non-English voice conversion research is limited by the near-absence of parallel, phonemically balanced corpora outside English. source: §1.2, §2.2 evidence: Despite Farsi being spoken by over 100 million people, no publicly available parallel Farsi VC dataset existed prior to FaVC; existing Farsi datasets (DeepMine, Farsi ESD, FarsDAT) are non-parallel and target ASR, TTS, or emotion recognition. confidence: high relevance: high - claim_id: incorporating_film_and_adain_conditioning_into_a_tts_decoder_supports role: supports claim: Incorporating FiLM and AdaIN conditioning into a TTS decoder supports effective one-shot voice conversion with results competitive with many-to-many GAN baselines. source: §4.1, §4.3, Table 2 evidence: Modified StyleTTS-VC with FiLM+AdaIN achieves MOS-N 3.94 and MOS-P 3.87 on FaVC (MCD 5.58), the highest naturalness score among the five evaluated models and competitive with StarGANv2-VC on speaker similarity (MOS-P 4.1). confidence: high relevance: high limitations: - The dataset is small (11 speakers, 405 utterances each), which limits the training capacity for data-hungry approaches. Evaluations across FaVC and English datasets conflate language, speaker population, and recording condition differences; the cross-language parity finding should be treated as indicative rather than controlled. No statistical significance testing is reported for MOS comparisons. Cross-lingual VC scenarios (Farsi to English or vice versa) are not evaluated, despite being flagged as a future direction. The dataset is currently distributed upon request rather than through an open public repository, which constrains reproducibility. caveats: [] - id: interspeech-2025-2283 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - TTS - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - evaluation_caution current_role: active_evidence method_family: [] claims: - claim_id: pronunciation_based_objective_metrics_correlate_more_reliably_with_accent_quality role: supports claim: Pronunciation-based objective metrics correlate more reliably with accent quality rankings than general intelligibility or naturalness proxies. source: §5.2, Table 2 evidence: PPG CosSim and PPG JS both achieved SRCC=0.9643 with hypothesised accent ranking (p=0.0005); VF RMSE achieved SRCC=0.9286 (p=0.0025). WER SRCC was 0.6429 and not statistically significant (p=0.1194). confidence: high relevance: medium - claim_id: wer_is_a_reliable_quality_metric_for_evaluating_tts_systems role: contradicts claim: WER is a reliable quality metric for evaluating TTS systems on underrepresented accents. source: §5.2, Table 2 evidence: WER ranked copysyn worse than xtts and xtts worse than corrupt30k, despite the hypothesised reverse quality ordering; WER's Spearman rank correlation with the quality ranking was non-significant (p=0.1194), attributed to accent bias in ASR models trained on standard varieties. confidence: high relevance: medium - claim_id: providing_reference_transcriptions_to_listeners_during_accent_similarity_evaluation_significantly role: supports claim: Providing reference transcriptions to listeners during accent similarity evaluation significantly improves statistical discriminability with fewer participants. source: §5.1, Figure 1 evidence: Baseline XAB with 15 listeners failed to reach p<0.05; XAB+trans+screen achieved significance within 10 valid submissions; XAB+trans+highlight+screen required as few as 5 valid submissions, reaching 64.1±6.7% preference for copysyn. confidence: high relevance: low - claim_id: auxiliary_highlight_tasks_in_listening_tests_improve_statistical_efficiency_but role: complicates claim: Auxiliary highlight tasks in listening tests improve statistical efficiency but nearly double completion time, limiting benefit to settings with constrained listener pools. source: §5.1 evidence: XAB+trans+highlight took ~30.6 minutes vs. ~16.9 minutes for baseline XAB; for accents with large listener pools the cost is not offset by efficiency gains, but for underrepresented accents with few available participants the highlight design remains advantageous. confidence: high relevance: medium limitations: - The study evaluates a single accent variety (Edinburgh Scottish English) using two speakers from VCTK. Generalisability to other underrepresented or L2 accents, other ZS-TTS systems, and accent conversion tasks is asserted but not demonstrated. The high SRCC for speaker similarity (WavLM) is acknowledged as potentially confounded by the catastrophic forgetting corruption scheme affecting both accent and broader speaker modelling simultaneously. The XAB setup enforces different-gender reference and target speakers to prevent confusing speaker and accent similarity, but this design choice may not hold for all accent evaluation scenarios. Future work is noted to explore XMOS/XCMOS alternatives, broader accent coverage, and additional synthesis systems. caveats: [] - id: interspeech-2025-2684 published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: explicit_disentanglement_of_content_and_prosody_into_separate_discrete_token role: supports claim: Explicit disentanglement of content and prosody into separate discrete token spaces via different SSL representations enables independent control of speaking style in zero-shot voice conversion. source: §2.1, §3.2, Table 2 evidence: Using HuBERT (content) and ContentVec with SimVQ bottleneck (prosody) as separate extractors, with a prosody mask transformer for reference-guided style transfer, yields F0 Corr of 0.941 for prosody preservation and 0.822 for prosody conversion on ESD/VCTK, while ablations show that using a single mel-based prosody input significantly degrades performance. confidence: high relevance: high - claim_id: flow_matching_with_in_context_learning_achieves_competitive_zero_shot role: supports claim: Flow matching with in-context learning achieves competitive zero-shot voice conversion quality at substantially fewer parameters than larger autoregressive systems. source: §3.2, Table 1 evidence: Discl-VC (131M params) achieves MOS 4.31, UTMOS 4.079, and SECS 0.929 on VCTK zero-shot VC, surpassing Vevo (922M params) on naturalness and matching speaker similarity, demonstrating that compact flow matching transformers are competitive with large-scale AR systems for VC. confidence: high relevance: high - claim_id: prosody_transfer_from_a_reference_speaker_introduces_a_trade_off role: complicates claim: Prosody transfer from a reference speaker introduces a trade-off with target speaker identity preservation. source: §3.2, Table 2 evidence: In the prosody conversion task, Discl-VC achieves lower SECS (0.847) than Vevo (0.892) despite better UTMOS and WER, suggesting that explicitly replacing source prosody with reference tokens disrupts timbre modeling and degrades speaker similarity relative to a system where prosody and identity are more entangled. confidence: high relevance: high - claim_id: simvq_freezing_codebook_vectors_and_learning_a_linear_projection_reduces role: supports claim: SimVQ (freezing codebook vectors and learning a linear projection) reduces codebook collapse in VQ-based speech discretisation. source: §3.3, Table 3 evidence: Ablation replacing SimVQ with standard VQ causes degradation across all metrics (UTMOS 4.042 vs 4.079, WER 2.182% vs 1.946%, F0 Corr 0.970 vs 0.973, SECS 0.928 vs 0.929), attributed to codebook collapse during training. confidence: high relevance: medium - claim_id: ssl_based_prosody_extraction_for_vc_can_retain_speaker_correlated role: complicates claim: SSL-based prosody extraction for VC can retain speaker-correlated information when the same-speaker assumption holds during training, causing train-inference mismatch. source: §3.3, Table 3 evidence: Ablation without ContentVec (using mel spectrogram first 20 dimensions as prosody input) shows the largest performance drop (UTMOS 4.034, WER 3.147%), attributed to prosody tokens containing residual speaker information because source and target audio come from the same speaker during training, creating a mismatch with cross-speaker inference. confidence: high relevance: medium limitations: - Evaluation is limited to English and uses only two baselines (Vevo and FAcodec) on a relatively small test set (450 pairs for zero-shot VC). The prosody conversion task's lower speaker similarity suggests that the prosody mask transformer introduces identity leakage when reference prosody comes from a different speaker. The paper does not report results on multilingual speakers or noisy conditions, leaving generalisation untested. The two-stage training procedure adds complexity and requires the stage-1 encoder to be frozen before the prosody mask transformer can be trained. caveats: [] - id: interspeech-2025-bokkahallisatish25_interspeech published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - SCA - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: minor method_family: [] claims: - claim_id: interactive_evaluation_tools_that_pair_voice_conversion_with_side_by role: supports claim: Interactive evaluation tools that pair voice conversion with side-by-side response comparison can surface speaker-dependent biases in speech foundation models that automated benchmarks do not capture. source: §2.2, §2.4 evidence: The platform lets users re-ask questions with voice-converted inputs and directly observe changes in response tone, phrasing, and behavior, positioning human interactive comparison as the primary bias discovery mechanism rather than the automated metrics. confidence: high relevance: high - claim_id: automated_speech_evaluation_metrics_are_insufficient_on_their_own_for role: complicates claim: Automated speech evaluation metrics are insufficient on their own for assessing fairness and speaker-dependent behavior in speech foundation models. source: §2.3, §2.4 evidence: Even with speech rate, pitch statistics, sentiment analysis, and semantic similarity available, the authors present human interactive comparison as the primary mode of bias discovery, arguing that quantitative measures miss subtle differences in model behavior across speaker identities. confidence: high relevance: low - claim_id: existing_benchmarks_for_speech_foundation_models_treat_speaker_attributes_independently role: supports claim: Existing benchmarks for speech foundation models treat speaker attributes independently, limiting the ability to detect intersectional or compounded identity-based biases. source: §1 evidence: Survey of VoxDialogue, Spoken StereoSet, and VoxEval reveals that each evaluates dimensions such as gender or age in isolation; VoxEval explicitly excludes bias and harmful content analysis as outside its scope. confidence: high relevance: medium limitations: - The platform reports no empirical benchmark results, so claims about its effectiveness at bias discovery remain qualitative and user-dependent. The voice conversion module's perceptual fidelity (whether transformed voices are actually perceived as intended) is not systematically evaluated, which could confound interpretation of response differences. The selection of speech LMs available in the platform is not enumerated. Large-scale studies to obtain statistically reliable metrics are identified as future work. caveats: [] - id: interspeech-2025-cho25c_interspeech published_date: "2025-08-17" entry_date: '2026-07-28' year: 2025 venue: Interspeech task: - VC architecture: - hybrid relevance: medium evidence_role: - architecture_variant current_role: minor method_family: - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: voice_conversion_models_trained_exclusively_on_human_speech_are_insufficient role: complicates claim: Voice conversion models trained exclusively on human speech are insufficient for targets with broader-than-human frequency range and non-periodic vocalizations. source: §3 evidence: Monster sounds span a wider frequency range than human speech, contain intricate audio-effect details, and include non-speech elements (unvoiced breathing, extreme vocal expressions) absent from standard human-speech training corpora; standard VC models trained on these corpora fail to reproduce the target timbres. confidence: high relevance: high - claim_id: replacing_f0_estimation_with_frame_level_energy_as_the_primary role: supports claim: Replacing f0 estimation with frame-level energy as the primary prosodic cue enables voice conversion for target voices where pitch periodicity cannot be reliably estimated. source: §4 evidence: The H2NH prior encoder substitutes frame-level energy for f0 because f0 estimation degrades severely for non-human monster sounds; the system still produces satisfactory conversions in the real-time demonstration. confidence: high relevance: high - claim_id: extending_audio_bandwidth_to_44_1_khz_and_incorporating_high role: supports claim: Extending audio bandwidth to 44.1 kHz and incorporating high-temporal-resolution discriminators improves voice conversion quality for transient-rich non-human acoustic targets. source: §4 evidence: The H2NH model uses a 5 ms hop-length STFT, Mel spectrograms covering 0-22.05 kHz, FDRL with multiple hop lengths, and a DAC discriminator specifically to capture fine temporal details and broad frequency content of monster vocalizations that standard 22.05 kHz pipelines cannot reproduce. confidence: high relevance: high limitations: - This paper contains only a surface-level architectural description; training data, hyperparameters, speaker or monster coverage, and quantitative evaluation metrics are all deferred to the companion Interspeech 2025 research paper. Claims about conversion fidelity cannot be independently verified from this paper alone. - The system targets a predefined set of monster voices for a specific gaming title; generalisation to arbitrary non-human voices, varied recording conditions, or diverse languages is not assessed. No ablation studies, failure cases, or degradation conditions are described. The demonstration runs locally within a VM environment, and no information is given about latency, throughput, or hardware requirements that would inform deployment feasibility. caveats: [] - id: '2508.15565' published_date: "2025-08-21" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: anonymizing_adversarial_utterances_toward_a_pseudo_speaker_derived_from_the role: supports claim: Anonymizing adversarial utterances toward a pseudo-speaker derived from the batch mean of adversarial embeddings improves identity unlinkability without requiring a designated real speaker. source: §IV-A, Table I evidence: Anonymizing adversarial utterances toward a pseudo-speaker derived from the batch mean of adversarial embeddings improves identity unlinkability without requiring a designated real speaker. confidence: high relevance: medium - claim_id: in_feedforward_adversarial_anonymization_training_with_a_composite_loss_covering role: supports claim: In feedforward adversarial anonymization, training with a composite loss covering untargeted attack, perceptual quality, and unlinkability objectives achieves better balance between de-identification and identity unlinkability than untargeted attack alone. source: §IV-A, Table I evidence: In feedforward adversarial anonymization, training with a composite loss covering untargeted attack, perceptual quality, and unlinkability objectives achieves better balance between de-identification and identity unlinkability than untargeted attack alone. confidence: high relevance: medium - claim_id: adversarial_perturbation_based_voice_anonymization_degrades_substantially_under_strong_adaptive role: supports claim: Adversarial perturbation-based voice anonymization degrades substantially under strong adaptive attacks such as quantization, revealing a fundamental vulnerability that is independent of the training strategy. source: §V-F, Table III evidence: Adversarial perturbation-based voice anonymization degrades substantially under strong adaptive attacks such as quantization, revealing a fundamental vulnerability that is independent of the training strategy. confidence: high relevance: medium - claim_id: speaker_adversarial_perturbations_transfer_less_effectively_to_black_box_speaker role: supports claim: Speaker adversarial perturbations transfer less effectively to black-box speaker extractors with strong verification capability, indicating that white-box EER gains overstate real-world privacy protection. source: §V-G, Table II evidence: Speaker adversarial perturbations transfer less effectively to black-box speaker extractors with strong verification capability, indicating that white-box EER gains overstate real-world privacy protection. confidence: high relevance: medium limitations: - De-identification and identity unlinkability EERs drop sharply under adaptive attacks (quantization reduces de-id EER from 46.79% to 7.63%), and black-box transfer to the ResNet100 extractor similarly reduces EERs to single digits. The method's privacy guarantees are therefore limited to white-box threat models, which may not reflect realistic deployment conditions. - Identity unlinkability generalises less well than de-identification to out-of-domain datasets, particularly LibriSpeech and AIShell, suggesting the batch mean loss is sensitive to the speaker distribution at training time. The method also degrades speech intelligibility (WER increases across all ASR test sets compared to original speech), which limits applicability in voice assistant or captioning contexts. Future directions include improving transferability against black-box extractors, enhancing resilience to adaptive attacks, and strengthening out-of-domain unlinkability. caveats: [] - id: '2508.16332' published_date: "2025-08-22" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - VC - singing architecture: - autoregressive-LM - flow-matching - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence current_role: influential method_family: - autoregressive_token_voice_conversion - flow_matching_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: joint_pre_training_on_speech_and_singing_voice_data_improves role: complicates claim: Joint pre-training on speech and singing voice data improves generation quality in both domains, with singing data contributing to expressive speech prosody richness and speech data compensating for the limited size of singing corpora. source: §V-A, Table I evidence: Joint pre-training on speech and singing voice data improves generation quality in both domains, with singing data contributing to expressive speech prosody richness and speech data compensating for the limited size of singing corpora. confidence: high relevance: medium - claim_id: chromagram_based_prosody_tokenization_provides_a_notation_free_octave_invariant role: supports claim: Chromagram-based prosody tokenization provides a notation-free, octave-invariant representation that bridges the F0 distribution gap between speech and singing, enabling unified prosody control without expert MIDI annotations. source: §III-A evidence: Chromagram-based prosody tokenization provides a notation-free, octave-invariant representation that bridges the F0 distribution gap between speech and singing, enabling unified prosody control without expert MIDI annotations. confidence: high relevance: medium - claim_id: autoregressive_models_initialized_from_llm_checkpoints_can_achieve_competitive_zero role: supports claim: Autoregressive models initialized from LLM checkpoints can achieve competitive zero-shot TTS quality at low codec frame rates (12.5 Hz) when paired with strong post-training, partially compensating for the sequence granularity disadvantage relative to higher frame-rate systems. source: §V-A, Table VII evidence: Autoregressive models initialized from LLM checkpoints can achieve competitive zero-shot TTS quality at low codec frame rates (12.5 Hz) when paired with strong post-training, partially compensating for the sequence granularity disadvantage relative to higher frame-rate systems. confidence: high relevance: low - claim_id: single_objective_preference_alignment_in_multi_capability_speech_models_degrades role: supports claim: Single-objective preference alignment in multi-capability speech models degrades complementary objectives; joint multi-objective optimization is necessary to avoid quality regressions on non-targeted capabilities. source: §V-F, Figure 5 evidence: Single-objective preference alignment in multi-capability speech models degrades complementary objectives; joint multi-objective optimization is necessary to avoid quality regressions on non-targeted capabilities. confidence: high relevance: medium - claim_id: inference_time_pitch_shift_applied_to_prosody_tokens_improves_speaker role: complicates claim: Inference-time pitch shift applied to prosody tokens improves speaker similarity in voice and singing conversion tasks, at the cost of a minor intelligibility degradation due to train-inference distribution mismatch. source: §V-E, Table VI evidence: Inference-time pitch shift applied to prosody tokens improves speaker similarity in voice and singing conversion tasks, at the cost of a minor intelligibility degradation due to train-inference distribution mismatch. confidence: high relevance: medium limitations: - '- Training-inference mismatch when applying pitch shift: content-style tokens from pitch-shifted audio are out-of-distribution, causing slight WER degradation. The paper flags future work to include pitch shift augmentation during training. - Singing voice data used (7K hours source-separated from in-the-wild songs) may have variable quality. - The 12.5 Hz frame rate of the content-style tokenizer slightly limits VC intelligibility compared to Vevo-FM (50 Hz), as shown in Table VIII. - Melody-MOS for Vevo2 in SVC is slightly lower than the FM-only Vevo2-FM, suggesting a quality-style tradeoff when adding text input. - Generalization to tonal languages in singing is not specifically evaluated.' caveats: [] - id: '2411.19770' published_date: "2025-08-28" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - diffusion relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion claims: - claim_id: contrastive_training_with_noise_augmented_views_enforces_noise_invariant_speaker role: supports claim: Contrastive training with noise-augmented views enforces noise-invariant speaker representations and substantially improves one-shot VC robustness at low SNR without adding inference cost. source: §III.A, Tables I-II evidence: Noro's dual-branch reference encoding module and noise-agnostic contrastive speaker loss hold SECS at 80.09 and CER at 4.66 in 0-5 dB noise, versus 77.28 and 7.26 for the baseline; weight sharing means inference architecture is unchanged. confidence: high relevance: medium - claim_id: standard_one_shot_voice_conversion_systems_degrade_substantially_when_reference role: complicates claim: Standard one-shot voice conversion systems degrade substantially when reference speech contains background noise, even after data augmentation training. source: §III.A.2, Table II evidence: The diffusion-based baseline trained on LibriLight with no noise-robustness mechanism shows CMOS dropping from 3.29 to 2.09 and SMOS from 3.02 to 2.75 under 0-5 dB noisy reference conditions. confidence: high relevance: high - claim_id: voice_conversion_reference_encoders_trained_on_large_scale_speech_data role: supports claim: Voice conversion reference encoders trained on large-scale speech data develop speaker representations competitive with dedicated self-supervised speaker models. source: §III.B.2, Table III evidence: VC-SPK2VEC (the Noro baseline reference encoder repurposed as a speaker encoder, 72.4M params, trained on LibriLight 60k hr) achieves 5.32% EER on VoxCeleb1 under SUPERB, outperforming wav2vec 2.0 Base (6.02%), wav2vec 2.0 Large (5.65%), and HuBERT Large (5.98%). confidence: high relevance: high - claim_id: speaker_noise_disentanglement_in_voice_conversion_benefits_from_training_objectives role: refines claim: Speaker-noise disentanglement in voice conversion benefits from training objectives that explicitly align clean and noisy representations of the same speaker, beyond simple noise augmentation. source: §III.A.2, Figure 2 evidence: t-SNE visualisations show that the baseline (trained with augmentation but no contrastive alignment) produces clearly separated clean/noisy representation clusters, while Noro's contrastive loss causes them to mix, correlating with the performance gap under noise. confidence: high relevance: high limitations: - The evaluation uses reference speech from VCTK (studio-recorded English) with synthetically added noise from DEMAND; real-world recordings that mix noise with reverberation, codec compression, or far-field capture may behave differently. The test set is small (ten source-reference pairs per condition for subjective evaluation, 150 for objective), and the paper does not report statistical significance for differences between Noro and the baseline in clean conditions where they are nearly equal. The contrastive loss relies on speaker labels during training, so the approach does not extend directly to fully unsupervised training on unlabelled data. The secondary VC-SPK2VEC finding is evaluated only under one SUPERB protocol; performance on other speaker tasks (diarization, speaker counting) is not explored. caveats: [] - id: '2507.14534' published_date: "2025-08-30" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - GAN - hybrid relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence - evaluation_caution current_role: active_evidence method_family: - gan_adversarial_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: streaming_voice_conversion_quality_degrades_significantly_when_offline_hubert_representations role: supports claim: Streaming voice conversion quality degrades significantly when offline HuBERT representations are naively replaced by causal alternatives, but knowledge distillation into an Emformer backbone can recover content accuracy with acceptable latency. source: §III.B, Table III evidence: Streaming voice conversion quality degrades significantly when offline HuBERT representations are naively replaced by causal alternatives, but knowledge distillation into an Emformer backbone can recover content accuracy with acceptable latency. confidence: high relevance: high - claim_id: causal_temporal_upsampling_via_pixel_shuffle_eliminates_the_checkerboard_artifacts role: supports claim: Causal temporal upsampling via pixel shuffle eliminates the checkerboard artifacts introduced by zero-padding non-causal vocoders, without sacrificing subjective quality. source: §III.D, Table III evidence: Causal temporal upsampling via pixel shuffle eliminates the checkerboard artifacts introduced by zero-padding non-causal vocoders, without sacrificing subjective quality. confidence: high relevance: medium - claim_id: explicit_style_modeling_with_clustering_based_vector_quantization_improves_zero role: supports claim: Explicit style modeling with clustering-based vector quantization improves zero-shot speaker similarity in streaming VC beyond what timbre embeddings alone provide. source: §III.C, Table I evidence: Explicit style modeling with clustering-based vector quantization improves zero-shot speaker similarity in streaming VC beyond what timbre embeddings alone provide. confidence: high relevance: high - claim_id: online_voice_conversion_systems_can_achieve_speaker_similarity_comparable_to role: supports claim: Online voice conversion systems can achieve speaker similarity comparable to offline systems when style transfer is modeled at chunk level rather than at the global utterance level. source: §IV.B, Table I evidence: Online voice conversion systems can achieve speaker similarity comparable to offline systems when style transfer is modeled at chunk level rather than at the global utterance level. confidence: high relevance: high limitations: - '- Evaluation is in English only; cross-lingual style transfer is untested. - The reference speaker must be fully available before streaming begins, limiting applications where reference is also captured in real-time. - CER is slightly higher than StreamVC because StreamVC reuses source pitch; Conan introduces some pitch variation that ASR penalizes as CER. - Model size is not reported; the cost of the Emformer + main model + CSV in production deployment is unclear. - Perceptual evaluation used 15 listeners per pair on Amazon Mechanical Turk style tasks; larger-scale evaluation would be needed to establish statistical robustness.' caveats: [] - id: '2509.00503' published_date: "2025-08-30" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC - codec architecture: - autoregressive-LM - transformer-enc-dec relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - autoregressive_token_voice_conversion - transformer_encoder_decoder_voice_conversion claims: - claim_id: adaptive_entropy_based_segmentation_of_discrete_speech_tokens_preserves_more role: supports claim: Adaptive entropy-based segmentation of discrete speech tokens preserves more task-relevant linguistic information than fixed-length downsampling at equivalent compression ratios. source: §6.1, Table 3; §6.2, Table 4 evidence: Adaptive entropy-based segmentation of discrete speech tokens preserves more task-relevant linguistic information than fixed-length downsampling at equivalent compression ratios. confidence: high relevance: medium - claim_id: optimal_token_granularity_differs_systematically_between_understanding_and_generation_tasks role: supports claim: 'Optimal token granularity differs systematically between understanding and generation tasks: recognition-oriented tasks (ASR, ST) benefit from moderate compression near phoneme rate, while voice conversion requires finer token density to maintain acoustic fidelity.' source: §5.1, Table 1; §6.3, Table 5 evidence: 'Optimal token granularity differs systematically between understanding and generation tasks: recognition-oriented tasks (ASR, ST) benefit from moderate compression near phoneme rate, while voice conversion requires finer token density to maintain acoustic fidelity.' confidence: high relevance: high - claim_id: ssl_derived_semantic_tokens_at_standard_rates_50_hz_contain role: supports claim: SSL-derived semantic tokens at standard rates (50 Hz) contain substantial redundancy that can be removed without degrading — and occasionally improving — downstream task performance. source: §6.1, Table 3 evidence: SSL-derived semantic tokens at standard rates (50 Hz) contain substantial redundancy that can be removed without degrading — and occasionally improving — downstream task performance. confidence: high relevance: medium - claim_id: entropy_boundaries_in_compressed_token_sequences_align_with_linguistically_meaningful role: supports claim: 'Entropy boundaries in compressed token sequences align with linguistically meaningful units: 15 Hz compression achieves 83.2% phoneme boundary alignment, while 7 Hz aligns primarily with word boundaries (89.7%).' source: Appendix C.3, Table 11 evidence: 'Entropy boundaries in compressed token sequences align with linguistically meaningful units: 15 Hz compression achieves 83.2% phoneme boundary alignment, while 7 Hz aligns primarily with word boundaries (89.7%).' confidence: high relevance: medium limitations: - 'Voice conversion quality degrades noticeably with compression: entropy-guided 15 Hz already falls below HuBERT deduplicated (Q-MOS 3.85 vs 4.12), and the gap widens at higher compression. For generation tasks, this framework does not improve on simply using deduplicated tokens — only for understanding tasks does compression help.' - The framework is evaluated exclusively on HuBERT-derived tokens; whether the entropy-based approach transfers to other SSL features (WavLM, w2v-BERT) or supervised tokenizers (S3, FACodec) is untested. The entropy LLM requires pre-training on 20k hours of speech, adding a pipeline step beyond vanilla k-means clustering. The method is tested on English only, and its behaviour on morphologically complex or tonal languages — where token redundancy patterns may differ — remains unknown. All evaluations use the English MLS training corpus, so generalisation across domains and recording conditions is unexplored. caveats: [] - id: '2509.04667' published_date: "2025-09-04" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - GAN - hybrid relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: limited_lookahead_in_causal_speech_encoders_substantially_improves_linguistic_content role: supports claim: Limited lookahead in causal speech encoders substantially improves linguistic content preservation with minimal latency penalty compared to purely causal encoders. source: §V.A, §V.B, Tables I–II evidence: Wave+CL accuracy improves from 53.16% at zero lookahead to 78.99% at 140ms, while end-to-end latency increases from 84.3ms to 203ms; extending to 280ms adds only 0.7pp accuracy with 120ms additional delay. confidence: high relevance: low - claim_id: better_content_encoding_in_streaming_anonymization_introduces_a_fundamental_tension role: complicates claim: 'Better content encoding in streaming anonymization introduces a fundamental tension: improved linguistic clarity reduces speaker anonymization strength under adversarial threat models.' source: §V.E, Table III evidence: Adding the contextual layer drops lazy-informed EER from 36.61% to 20.35% at zero lookahead, meaning the cleaner representations are more discriminative for speaker recognition attacks, directly trading anonymization quality for intelligibility. confidence: high relevance: low - claim_id: token_quantization_via_k_means_clustering_achieves_near_chance_speaker role: supports claim: Token quantization via k-means clustering achieves near-chance speaker verification performance in streaming anonymization by removing fine-grained speaker cues from content representations. source: §V.C, §V.D, §V.E, Tables IV–V evidence: Applying a 256-centroid k-means bottleneck raises lazy-informed EER from ~12% to ~47% (Wave+CL, 140ms lookahead), at a cost of WER rising from 2.09% to 9.52% and MOS falling from 3.79 to 3.22. confidence: high relevance: low - claim_id: streaming_voice_anonymization_systems_can_approach_offline_pipeline_anonymization_performance role: supports claim: Streaming voice anonymization systems can approach offline-pipeline anonymization performance when evaluated under the lazy-informed threat scenario, while retaining real-time latency. source: §V.F, Table VI evidence: DarkStream achieves 22.68% semi-informed EER in streaming mode (140ms lookahead), matching VoicePrivacy 2024 baselines B3 (26.28%) and B5a (22.09%) that require full-utterance processing. confidence: high relevance: low - claim_id: direct_waveform_synthesis_in_streaming_voice_conversion_maintains_acceptable_naturalness role: complicates claim: Direct waveform synthesis in streaming voice conversion maintains acceptable naturalness without mel-spectrogram intermediate representations, but k-means quantization introduced for privacy causes perceivable quality degradation beyond what objective metrics capture. source: §V.D, Table V evidence: MOS drops from 3.79 (Wave+CL) to 3.22 (Wave+CL+KMeans) with quantization; WER degrades only modestly, indicating that intelligibility metrics underestimate the perceptual impact of quantization artifacts. confidence: high relevance: high limitations: - DarkStream does not explicitly disentangle static speaker traits (accent, age, sex) from dynamic attributes (emotion, speaking style), leaving indirect identity cues potentially intact. The semi-informed EER of 22.68% remains well above chance, indicating meaningful residual linkability for well-resourced adversaries. - 'The privacy/quality trade-off exposed by the quantization ablation is steep: each MOS point recovered (by disabling k-means) costs roughly 30pp EER under the lazy-informed scenario. Systems requiring both high quality and robust anonymization against semi-informed attackers have no current solution in this architecture. Comparison of perceptual quality against the offline VoicePrivacy baselines is not reported, so whether DarkStream''s naturalness advantage over batch-processing pipelines is real remains an open question. Evaluation is limited to English (LibriTTS), and generalization to accented or code-switched speech is untested.' caveats: [] - id: '2509.07376' published_date: "2025-09-09" entry_date: '2026-07-28' year: 2025 venue: EMNLP task: - TTS architecture: - VAE relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - vae_latent_voice_conversion claims: - claim_id: hierarchical_locally_aware_facial_feature_extraction_substantially_improves_voice_face role: supports claim: Hierarchical, locally-aware facial feature extraction substantially improves voice-face identity congruence compared to global visual representations in face-to-speech synthesis. source: §5.3, Table 5 evidence: Progressive Facial Granularity Aggregation (FGA) — hierarchical patch decomposition with progressive convolutional aggregation — yields SECS of 79.96 (seen) vs. 66.25 when replaced with a single vanilla transformer over the full image, a gap of 13.71 points. confidence: high relevance: medium - claim_id: cross_modal_multi_task_supervision_over_demographic_attributes_improves_face role: supports claim: Cross-modal multi-task supervision over demographic attributes improves face-voice alignment in end-to-end synthesis systems. source: §5.2, Table 4 evidence: Bilateral attribute enhancement (predicting gender and ethnicity from both the facial embedding and synthesized audio) produces the highest SECS configuration at 79.96 seen / 71.39 unseen; applying supervision to only one modality yields lower scores (77.76 / 70.27 for visual-only, 75.84 / 69.52 for audio-only). confidence: high relevance: medium - claim_id: multi_view_face_augmentation_pairing_multiple_facial_frames_per_speaker role: supports claim: Multi-view face augmentation — pairing multiple facial frames per speaker across varying poses and lighting — is critical for robust speaker identity generalization in face-to-speech systems. source: §5.3, Table 5 evidence: Removing the multi-view augmentation strategy causes the largest single-component SECS drop in ablation studies (from 79.96 to 64.43, a decrease of 15.53 on seen speakers and 9.35 on unseen), exceeding the contribution of any individual architectural module. confidence: high relevance: high - claim_id: end_to_end_face_to_voice_synthesis_without_audio_space role: complicates claim: End-to-end face-to-voice synthesis without audio-space alignment targets still requires explicit cross-modal semantic supervision to maintain speaker identity coherence. source: §5.2, §5.3, Table 4, Table 5 evidence: Training the progressive facial encoder end-to-end without audio-alignment targets is the paper's stated improvement over prior multi-stage pipelines, but removing bilateral attribute supervision (even partially) consistently degrades SECS — visual attribute enhancement removal alone costs 5.23 SECS points. confidence: high relevance: high - claim_id: face_to_voice_synthesis_systems_trained_on_demographically_skewed_corpora role: complicates claim: Face-to-voice synthesis systems trained on demographically skewed corpora may produce uneven speaker similarity across underrepresented groups. source: §Appendix B, Table 6, Table 7 evidence: The LRS3-TED training set is 74.66% male and 72.23% Caucasian; the proposed model achieves SECS of 75.97 for male and 75.03 for female speakers, while Middle Eastern (69.25) and African American (71.65) speakers show measurably lower scores despite the bilateral attribute supervision. confidence: high relevance: medium limitations: - 'The framework focuses on overall vocal timbre and does not capture emotional prosody: facial expressions that correlate with affective speech are excluded from the current conditioning design. Age-conditioned synthesis is also limited by dataset skew; the LRS3-TED distribution is not representative of older speakers, leaving age alignment as partial.' - Demographic coverage in the training data is heavily imbalanced, with Middle Eastern and African American speakers showing noticeably lower SECS scores despite the bilateral supervision. Whether this gap can be closed by dataset rebalancing or additional attribute supervision is an open question. - The evaluation uses 40 speakers and 21 annotators, which, while reasonable for an FTV study, limits statistical power for cross-demographic comparisons. The comparison baselines do not include the most recent large-scale zero-shot TTS systems, so absolute quality relative to the broader field is unclear. caveats: [] - id: '2509.08379' published_date: "2025-09-10" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - diffusion - flow-matching relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion - flow_matching_voice_conversion claims: - claim_id: operating_diffusion_and_flow_matching_models_in_a_compressed_latent role: supports claim: Operating diffusion and flow-matching models in a compressed latent representation improves audio quality and inference speed in non-parallel voice conversion compared to operating directly on mel-spectrograms. source: §III.A, §IV.H, Table IV, Table X evidence: LatentVoiceGrad-DPM outperforms VoiceGrad-DPM in pMOS (3.93 vs. 3.86), subjective qMOS (4.09 vs. 3.83), sMOS (3.05 vs. 2.63), and GPU RTF (0.034 vs. 0.045) on VCTK zero-shot any-to-any conversion. confidence: high relevance: high - claim_id: flow_matching_achieves_comparable_voice_conversion_quality_to_diffusion_models role: supports claim: Flow matching achieves comparable voice conversion quality to diffusion models with substantially fewer inference steps. source: §IV.G, §IV.J, Tables VII, IX evidence: VoiceGrad-FM with L=3 Euler steps achieves pMOS 3.85 (versus 3.86 for VoiceGrad-DPM at L=20), at GPU RTF 0.007 versus 0.045, a six-fold speedup with no quality penalty. confidence: high relevance: high - claim_id: adversarial_autoencoder_training_substantially_improves_audio_quality_and_speaker_similarity role: supports claim: Adversarial autoencoder training substantially improves audio quality and speaker similarity in latent-domain voice conversion compared to reconstruction-only training. source: §IV.F, Table V evidence: Adding adversarial loss during autoencoder training improves pMOS from 3.78 to 3.93 and SECS from 0.829 to 0.844 on VCTK zero-shot VC with the DPM generative model. confidence: high relevance: high - claim_id: discrete_acoustic_token_sequences_from_neural_audio_codecs_underperform_continuous role: complicates claim: Discrete acoustic token sequences from neural audio codecs underperform continuous spectral representations as the conversion domain for iterative generative voice conversion models. source: §IV.E, Tables II, III evidence: VoiceGrad with DAT features (DAC codec, dimensionality 1024) achieves pMOS 2.41 versus 3.86 for mel-spectrograms; LatentVoiceGrad-DAT shows CER 9.08 versus 2.99 for the mel-spectrogram variant, suggesting the combination of high-dimensional discrete tokens and score-based conversion is not yet effective. confidence: high relevance: high - claim_id: the_noise_injection_ratio_at_the_initial_point_of_the role: refines claim: The noise injection ratio at the initial point of the ODE in flow-matching voice conversion controls a three-way trade-off between audio quality, intelligibility, and speaker similarity. source: §IV.G, Table VI evidence: Systematic sweeps of r from 0 to 1 in VoiceGrad-FM and LatentVoiceGrad-FM show that increasing r raises SECS but degrades CER, with pMOS peaking around r=0.4-0.6; r=0.7 provides a practical balance across all three metrics. confidence: high relevance: high limitations: - Only objective metrics are reported for most ablations; the subjective listening test covers only 12 listeners and does not include FACodec as a comparison. The DAT evaluation is acknowledged as potentially sub-optimal due to untuned hyperparameters, so the conclusion that discrete tokens are unsuitable for this framework remains tentative. The model is evaluated on English speech only (VCTK and LibriTTS), and generalisation to other languages or noisy conditions is untested. The phoneme encoder relies on a supervised ASR model trained on English data, which ties the system to English without further adaptation. caveats: [] - id: '2509.09201' published_date: "2025-09-11" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - codec - VC architecture: - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: neural_audio_codecs_can_disentangle_speech_and_background_sound_in role: supports claim: Neural audio codecs can disentangle speech and background sound in the representation domain, enabling downstream tasks to selectively access either component without explicit front-end separation. source: §4.3, §4.5, §6.1, Table 4, Table 6 evidence: DeCodec's SOP+RST design achieves orthogonal speech and background subspaces; recombining representations enables one-shot VC (SPK-SIM 0.83, WER 50.46) and speech enhancement (DNSMOS OVL 3.39) without denoising pre-processing, outperforming cascaded StoRM+SpeechTokenizer on ASR (WER* 26.7 vs. 34.5). confidence: high relevance: medium - claim_id: semantic_guidance_from_self_supervised_features_in_the_first_quantiser role: supports claim: Semantic guidance from self-supervised features in the first quantiser layer improves the noise-robustness of codec representations used for downstream ASR. source: §6.1.4, Table 5 evidence: Ablation-3 (SOP+RST without SG) achieves WER* 41.9 on noisy speech; adding HuBERT-L9 guidance reduces it to 25.8 (causal) and 23.6 (non-causal), confirming that semantic anchoring helps the quantiser concentrate linguistic content in a background-invariant first layer. confidence: high relevance: low - claim_id: explicit_disentanglement_constraints_in_neural_codecs_introduce_a_reconstruction_quality role: complicates claim: Explicit disentanglement constraints in neural codecs introduce a reconstruction quality trade-off relative to purely reconstruction-optimised designs. source: §6.1.1, Table 2 evidence: DeCodec's mel distance on clean speech (0.89) is worse than DAC (0.65) and HiFi-Codec (0.75), which use no orthogonality or disentanglement losses, suggesting that forcing orthogonal subspace separation increases spectral distortion. confidence: high relevance: medium - claim_id: hierarchical_codec_disentanglement_enables_controllable_background_sound_handling_in_zero role: supports claim: Hierarchical codec disentanglement enables controllable background sound handling in zero-shot TTS without retraining the downstream generation model. source: §6.2.2, Table 7 evidence: VALL-E trained on DeCodec tokens achieves MOS 4.09 with background preserved (BPMOS 4.19) vs. MOS 3.96 without, controlled solely by whether the BRVQ-1:8 background tokens are included at inference; the TTS model itself was trained only on clean speech. confidence: high relevance: low - claim_id: voice_conversion_on_noisy_speech_via_representation_recombination_produces_high role: complicates claim: Voice conversion on noisy speech via representation recombination produces high WER even when speaker similarity is well-preserved, due to voiced/unvoiced segment boundary mismatches between source and reference utterances. source: §6.1.3, Table 4 evidence: DeCodec one-shot VC achieves SPK-SIM 0.83 (matching the reference ceiling of 0.69 being clearly exceeded) but WER 50.46, which the authors attribute to structural mismatch in speech segment timing rather than semantic content corruption. confidence: high relevance: high limitations: - Subjective evaluations use panels of 10-12 volunteers on 300-clip test sets, which is small for MOS-based conclusions. The noisy speech test set is constructed by synthetically mixing clean LibriSpeech with DNS-Noise at controlled SNRs (-5 to 20 dB), which may not reflect the diversity of real-world background conditions. - The model operates at 16 kHz and is trained on a speech-dominant corpus; performance on music or non-speech audio types is not evaluated despite the universal codec framing. The high VC WER (50.46) under noisy conditions indicates that the current representation recombination approach for voice conversion degrades intelligibility significantly and would likely need additional design work before practical deployment. Model size is not reported, making direct efficiency comparisons with baselines difficult. caveats: [] - id: '2509.14270' published_date: "2025-09-15" entry_date: '2026-07-28' year: 2025 venue: ACL task: - TTS architecture: [] relevance: medium evidence_role: - architecture_variant - evaluation_caution current_role: active_evidence method_family: [] claims: - claim_id: structured_keyphrase_infusion_via_multi_step_llm_prompting_substantially_reduces role: supports claim: Structured keyphrase infusion via multi-step LLM prompting substantially reduces semantic repetition in generated TTS training corpora compared to single-prompt domain generation. source: §3.1, §4.1 evidence: SpeechWeave's keyphrase pipeline achieves 45.8%/44.4% lower grouped mean pairwise similarity in English/Spanish and 17.4%/9.7% higher diphone coverage relative to direct domain prompting with Mistral-7b-Instruct, even at high temperature (Table 3). confidence: high relevance: medium - claim_id: generating_semiotic_class_entities_with_embedded_normalization_rules_at_source role: supports claim: Generating semiotic class entities with embedded normalization rules at source achieves higher normalization accuracy for TTS training text than applying a post-hoc normalizer to LLM-generated output. source: §3.2, §4.2.1 evidence: At-source entity normalization reaches 0.97 accuracy in English and 0.94 in Spanish, compared to 0.67 and 0.54 for NeMo's WFST text normalizer on the same 500-sentence evaluation sets per language (Table 4). confidence: high relevance: medium - claim_id: fine_tuning_a_pre_trained_tts_model_on_synthetic_pipeline role: supports claim: Fine-tuning a pre-trained TTS model on synthetic pipeline-generated data with controlled diversity and normalization can meaningfully improve downstream speech intelligibility. source: §4.2.3 evidence: StyleTTS 2 fine-tuned on SpeechWeave data shows 40% relative WER reduction in English (15.37% to 9.36%) and 27% in Spanish (85.05% to 48.44%) on LibriSpeech test sets; the Spanish result also demonstrates cross-lingual adaptation from a monolingual English checkpoint (Table 6). confidence: high relevance: medium - claim_id: automated_speech_quality_metrics_from_predictive_models_should_not_be role: complicates claim: Automated speech quality metrics from predictive models should not be treated as equivalent to human MOS scores when evaluating synthetic TTS training data. source: §4.2.2, Table 5 evidence: SpeechWeave reports MOS of 4.95 (English) and 4.87 (Spanish) estimated by the NISQA neural quality predictor rather than human raters; the paper notes this explicitly. Automated MOS predictors are known to diverge from human judgments, particularly for TTS systems that differ from the predictor's training distribution. confidence: high relevance: medium limitations: - The evaluation covers only English and Spanish, and improvements in normalization accuracy and diversity may not hold for morphologically rich or lower-resource languages, which the paper acknowledges as future work. - The entity sampler supports nine semiotic classes; any entity type not included in the recipes will not be normalized at source, and the post-processor may handle them incorrectly. The extent of this gap depends on how often such entities appear in target domains. - The pipeline depends on Mistral-7b-Instruct for text generation and OpenVoice V2 for voice cloning, and performance is expected to vary with model substitution. No ablation is provided over LLM or TTS model choice, so the contribution of each component to the overall result is not fully isolated. - The downstream evaluation uses WER from an ASR model to assess TTS quality, which measures intelligibility rather than naturalness or speaker similarity. Prosody, expressiveness, and voice consistency are not evaluated beyond the automated MOS and SNR scores. caveats: [] - id: '2509.13068' published_date: "2025-09-16" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - codec - VC architecture: - autoregressive-LM - VAE relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion - vae_latent_voice_conversion claims: - claim_id: cascaded_residual_codec_architectures_can_enforce_attribute_disentanglement_through_structure role: supports claim: Cascaded residual codec architectures can enforce attribute disentanglement through structure rather than through adversarial training objectives. source: §2.1, §3.3.3, Table 3 evidence: MSR-Codec achieves clean separation of timbre, prosody, and semantic content by having each stream operate on residuals from the previous stage, without adversarial disentanglement loss; VC experiments confirm independent manipulation of each attribute. confidence: high relevance: low - claim_id: explicit_prosodic_supervision_in_a_dedicated_codec_stream_promotes_measurable role: supports claim: Explicit prosodic supervision in a dedicated codec stream promotes measurable disentanglement of pitch from speaker identity. source: §2.1.2, §3.3.3, Table 3 evidence: VQ1 (prosody stream) is trained with MSE loss against ground-truth F0 and spectral energy; prosody-only VC achieves low ΔF0,tar (12.3-14.2 Hz) while maintaining high SIM-src (0.59-0.64), confirming that prosody and timbre are independently manipulable. confidence: high relevance: high - claim_id: disentangled_codec_designs_can_achieve_competitive_speaker_similarity_at_lower role: supports claim: Disentangled codec designs can achieve competitive speaker similarity at lower bitrates than undifferentiated RVQ codecs. source: §3.3.1, Table 1 evidence: MSR-Codec-424 achieves SPK-SIM 0.80 at 424 bps, higher than WavTokenizer (0.67 at 900 bps) and X-Codec (0.72 at 1000 bps), attributed to the time-invariant timbre stream which preserves speaker identity without scaling with utterance length. confidence: high relevance: low - claim_id: data_efficient_tts_systems_built_on_factorized_codec_representations_can role: supports claim: Data-efficient TTS systems built on factorized codec representations can achieve competitive intelligibility relative to larger models trained on more data. source: §3.3.2, Table 2 evidence: The 0.2B MSR-Codec-524 TTS model trained on 45k hours achieves WER 3.07% on Seed-TTS-eval English, outperforming Llasa-1B trained on 250k hours (WER 3.22%) and FireRedTTS-0.4B trained on 150k hours (WER 3.82%). confidence: high relevance: low - claim_id: signal_fidelity_codec_metrics_stoi_pesq_and_speaker_similarity_diverge role: complicates claim: Signal-fidelity codec metrics (STOI, PESQ) and speaker similarity diverge at low bitrates, making holistic quality assessment difficult. source: §3.3.1, Table 1 evidence: MSR-Codec-424 achieves the highest SPK-SIM (0.80) among codecs at comparable bitrates but lower STOI (0.84) and PESQ-WB (1.82) than some baselines, indicating that speaker preservation and signal-level fidelity are optimized differently by the multi-stream design. confidence: high relevance: low limitations: - No subjective listening test (MOS/MUSHRA) is reported for any condition; all quality comparisons rely on automatic metrics (UTMOS, STOI, PESQ, WER, SPK-SIM). Conclusions about perceived naturalness cannot be confirmed from the available data. - 'The VC evaluation protocol is small in scope: 8 target speakers from VCTK and 100 source utterances from LibriTTS. Generalisation to more diverse speakers, accents, or noisy conditions is not assessed. The FreGAN vocoder operates at 16 kHz, and the Mel-spectrogram-based pipeline may impose a quality ceiling relative to waveform-domain codecs. The TTS model is evaluated only on English; the codec was trained on Mandarin and English data but multilingual TTS capability is not demonstrated. Model size figures for the codec itself are not reported; only the TTS model size (0.2B) is provided.' caveats: [] - id: '2504.20581' published_date: "2025-09-17" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution - infrastructure current_role: active_evidence method_family: [] claims: - claim_id: automated_speaker_similarity_metrics_can_serve_as_architecture_agnostic_proxies role: supports claim: Automated speaker-similarity metrics can serve as architecture-agnostic proxies for voice cloning quality, enabling reproducible evaluation without human raters. source: §3, §4 evidence: ClonEval evaluates five open-source models as black boxes using WavLM cosine similarity, requiring no human listeners or model internals access, while revealing systematic performance differences across systems and conditions. confidence: high relevance: high - claim_id: benchmark_evaluations_using_only_neutral_read_speech_overestimate_the_practical role: complicates claim: Benchmark evaluations using only neutral read-speech overestimate the practical voice cloning performance of current TTS systems. source: §7.1, Table 1 evidence: All five models achieved WavLM cosine similarity in the 0.88–0.91 range on LibriSpeech test-clean, but scores dropped substantially on emotional datasets; OuteTTS fell to 0.54 on SAVEE, revealing that neutral-data performance does not generalize to expressive conditions. confidence: high relevance: high - claim_id: emotion_transfer_fidelity_varies_systematically_by_emotion_category_with_high role: complicates claim: Emotion transfer fidelity varies systematically by emotion category, with high-arousal negative emotions consistently harder to clone than neutral or positive-valence speech. source: §7.3, Table 3 evidence: 'Across all five evaluated models in Table 3, fear produced the lowest or near-lowest per-emotion scores (e.g., XTTS-v2: 0.7929 for fear vs. 0.848 for neutral), and disgust and anger also ranked consistently below neutral for most models.' confidence: high relevance: medium limitations: - The benchmark is English-only; generalization of the protocol and leaderboard to multilingual voice cloning is deferred to future work. Speaker similarity via WavLM cosine similarity does not capture naturalness, intelligibility, or audio artefacts, so a system with high speaker similarity scores may still produce perceptually poor speech. The paper acknowledges the absence of human evaluation and plans to add it. Because the leaderboard relies on vendors self-reporting generated samples, it cannot rule out benchmark-specific optimizations. WavLM representations may not generalize equally across all speaker demographics and acoustic environments, which could introduce bias in rankings for out-of-distribution reference voices. caveats: [] - id: '2509.14579' published_date: "2025-09-18" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - VC architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: cross_lingual_zero_shot_voice_cloning_in_flow_matching_tts role: supports claim: Cross-lingual zero-shot voice cloning in flow-matching TTS can be achieved without audio prompt transcripts by using forced alignment to partition training data at word boundaries. source: §4.3, Table 3 evidence: CL-F5 achieves WER 2.496% on a cross-lingual English test set drawn from four unseen languages (German, French, Hindi, Korean), while the F5-TTS baseline cannot perform cross-lingual cloning at all due to its transcript dependency. confidence: high relevance: high - claim_id: multi_granularity_speaking_rate_predictors_trained_with_ordinal_aware_gaussian role: supports claim: Multi-granularity speaking rate predictors trained with ordinal-aware Gaussian loss provide reliable duration estimation for transcript-free flow-matching TTS. source: §4.1, §4.2, Table 1, Table 2 evidence: The phoneme-level predictor (M1) achieves MAE=0.759s on LibriSpeech-PC and enables WER 2.079%, improving over the length-ratio baseline (2.205%); the syllable-level predictor (M2) is preferred for Chinese synthesis on SeedTTS test-zh. confidence: high relevance: medium - claim_id: removing_audio_prompt_transcripts_from_flow_matching_tts_incurs_a role: complicates claim: Removing audio prompt transcripts from flow-matching TTS incurs a small but consistent cost in speaker similarity. source: §4.2, Table 2, §5 evidence: CL-F5 M1 achieves SIM-o 0.663 vs. 0.668 for the transcript-conditioned baseline on LibriSpeech-PC; the authors also report reduced capacity for transferring accent and emotion relative to the original F5-TTS. confidence: high relevance: medium - claim_id: the_optimal_linguistic_granularity_for_acoustic_speaking_rate_prediction_is role: refines claim: The optimal linguistic granularity for acoustic speaking rate prediction is language-dependent rather than universal. source: §4.1, Table 1 evidence: Phoneme-level (M1) outperforms syllable-level (M2) for English duration prediction, while M2 outperforms M1 for Chinese on SeedTTS test-zh; word-level (M3) is consistently the weakest across all languages and test sets. confidence: high relevance: medium limitations: - The speaking rate predictors are trained exclusively on English and Chinese data. While cross-lingual generalisation to German, French, Hindi, and Korean is demonstrated empirically, the scope of generalisation to genuinely low-resource or typologically distant languages remains untested. - 'Speaker characteristic transfer is degraded compared to the transcript-conditioned baseline: the authors note reduced accuracy in preserving accents and emotional cues. This points to an open question about how much speaker-identity information is carried by the reference transcript versus the audio signal alone. Future work suggested by the paper includes compensating for missing linguistic information from transcripts to recover expressiveness.' caveats: [] - id: '2509.15462' published_date: "2025-09-18" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - codec - VC architecture: - autoregressive-LM - flow-matching relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion - flow_matching_voice_conversion claims: - claim_id: factorising_speech_into_semantic_components_content_style_timbre_enables_task role: supports claim: Factorising speech into semantic components (content, style, timbre) enables task-relevant transmission at lower bitrates than general-purpose codecs that encode all features uniformly. source: §3.3, Table 1 evidence: Content-style tokens at 650 bps achieve WER 0.15 and sentiment accuracy 59%, within 1% of EnCodec at 1.5 kbps (WER 0.20, accuracy 60%), while using approximately half the bitrate. confidence: high relevance: high - claim_id: reusing_a_compressed_speaker_reference_transmitted_once_per_speaker_can role: supports claim: Reusing a compressed speaker reference transmitted once per speaker can maintain speaker similarity at lower average bitrate than encoding full audio continuously. source: §3.4, Table 1 evidence: Vevo with Zonos speaker embedding (1 sec timbre) achieves SpkrSim 0.54, matching EnCodec at 1.5 kbps (0.54), while long-run average bitrate approaches 650 bps as registered speakers accumulate. confidence: high relevance: medium - claim_id: generative_reconstruction_from_semantic_tokens_improves_perceptual_quality_scores_but role: complicates claim: Generative reconstruction from semantic tokens improves perceptual quality scores but degrades low-level signal fidelity metrics relative to waveform-level codecs. source: §3.4, Table 1 evidence: Vevo configurations outperform EnCodec on UTMOS and NISQA across all bitrates, but score lower on PESQ and STOI because the flow-matching decoder was not trained to preserve signal-level characteristics. confidence: high relevance: medium - claim_id: semantic_codec_approaches_face_a_latency_and_error_propagation_trade role: complicates claim: Semantic codec approaches face a latency and error-propagation trade-off that general-purpose codecs avoid. source: §2.2, §4 evidence: Timbre transmission introduces per-speaker latency L = d_sample + d_transmit; errors in that one-time transmission cause permanent voice reconstruction inaccuracies until a correction is transmitted. confidence: high relevance: low - claim_id: neural_semantic_token_representations_are_moderately_robust_to_channel_bit role: supports claim: Neural semantic token representations are moderately robust to channel bit errors, maintaining acceptable downstream task performance at realistic noise levels. source: §3.5, Table 2 evidence: At 0.1% bit-flip rate the system shows no measurable degradation; at 1% BER sentiment classification (0.63) and speaker verification (0.77) still exceed Opus at 5 kbps. Performance collapses only above 10% BER. confidence: high relevance: medium limitations: - 'Timbre transmission errors are permanent: a corrupted one-time speaker embedding results in incorrect voice reconstruction for all subsequent utterances from that speaker until a retransmission is triggered. The paper does not propose an error-recovery mechanism.' - The system does not handle overlapping speakers; the paper acknowledges this would require sender-side speaker separation at additional bitrate cost. Evaluation is restricted to English and does not address non-English languages, which are explicitly noted as out-of-distribution for several downstream models. The test set of 1,000 clips from VoxCeleb1 is relatively small for claims about general-purpose voice communication performance. The real-time latency introduced by speaker embedding generation and transmission is uncharacterised across different network conditions. caveats: [] - id: '2509.15629' published_date: "2025-09-19" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC - singing - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: [] claims: - claim_id: dynamic_temporal_features_in_singing_vibrato_glissando_breathy_voice_are role: supports claim: Dynamic temporal features in singing (vibrato, glissando, breathy voice) are substantially harder to convert than static spectral features, and current systems cannot model them reliably. source: §4.1 evidence: Style accuracy scores for vibrato (43.9%), glissando (42.6%), and breathy (37.3%) were markedly lower than those for falsetto (48.8%), mixed voice (48.3%), and pharyngeal (44.8%); no system approached human-level performance on the dynamic styles. confidence: high relevance: medium - claim_id: jointly_converting_singer_identity_and_singing_style_simultaneously_degrades_naturalness role: supports claim: Jointly converting singer identity and singing style simultaneously degrades naturalness compared to identity-only conversion. source: §4.1 evidence: Top SVCC 2025 systems achieved approximately 3.7 MOS naturalness, below the approximately 3.9 MOS ground truth, whereas prior SVCC 2023 top systems reached human-level naturalness on the simpler identity-only task. confidence: high relevance: medium - claim_id: autoregressive_language_model_architectures_with_flow_matching_decoders_are_competitive role: supports claim: Autoregressive language model architectures with flow-matching decoders are competitive with specialized diffusion systems for singing voice conversion. source: §4.1 evidence: Systems based on Vevo1.5 (ARLM + flow-matching) achieved the highest singing style similarity scores in the challenge, outperforming pure diffusion-based systems using SeedVC and Serenade. confidence: high relevance: high - claim_id: neural_mos_prediction_models_show_stronger_correlation_with_subjective_naturalness role: supports claim: Neural MOS prediction models show stronger correlation with subjective naturalness scores for singing voice than traditional signal-based metrics. source: §4.2 evidence: SHEETSSQA and SingMOS achieved Spearman rank correlation coefficients above 0.6 with subjective naturalness scores; speaker and singer embeddings were the strongest predictors of identity and style similarity (SRCC above 0.75). confidence: high relevance: medium - claim_id: singer_identity_similarity_evaluation_in_challenges_is_confounded_by_evaluation role: complicates claim: 'Singer identity similarity evaluation in challenges is confounded by evaluation design: even ground truth recordings achieve only approximately 70% similarity scores with a single-sample reference.' source: §4.1 evidence: Ground truth samples reached only approximately 70% singer identity similarity in SVCC 2025 listening tests; the challenge responded by presenting three reference samples per singer (instead of one in prior challenges) to reduce this floor effect. confidence: high relevance: low limitations: - Objective metrics show weak-to-moderate correlation with subjective scores across most dimensions, with only neural MOS predictors and embedding-based similarity reaching SRCC above 0.6. Objective-only comparisons for singing style conversion should be treated with caution until better proxy metrics are established. - The challenge attracted only 7 participating teams (26 systems including ablations), limiting the diversity of architectural approaches evaluated. The dataset is derived exclusively from GTSinger, restricting style diversity to the 7 included categories and to the singers chosen for Task 1 and Task 2. The zero-shot task evaluation is further complicated by the inherent ambiguity of singer identity evaluation (GT achieving only approximately 70% similarity), which may inflate the apparent success of some zero-shot systems. Open questions include how to model the time-varying noise and F0 dynamics that characterize breathy, vibrato, and glissando styles, and whether objective metrics can be developed with sufficiently high correlation to replace or supplement crowd-sourced listening tests at scale. caveats: [] - id: '2509.16010' published_date: "2025-09-19" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - VC architecture: - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: disentangling_speaker_identity_from_expressive_style_into_separate_adapter_modules role: supports claim: Disentangling speaker identity from expressive style into separate adapter modules improves both speaker similarity and style expressivity in personalised voice cloning. source: §3.3, Table 2 evidence: Ablations on GPT-SOVITS-V4 show removing the private ID-LoRA drops SS from 0.645 to 0.507, while removing the Style-LoRA drops SE from 0.704 to 0.588; a single unified adapter cannot optimise both objectives without mutual degradation. confidence: high relevance: high - claim_id: collaborative_style_learning_across_clients_in_a_federated_setting_can role: supports claim: Collaborative style learning across clients in a federated setting can overcome per-client data scarcity and produce higher speaker similarity than purely local fine-tuning. source: §3.2, Table 2 evidence: Fed-PISA exceeds Local FT (LoRA) in both SS (0.645 vs 0.529) and nMOS (4.08 vs 3.36), demonstrating that sharing expressive style information across clients compensates for limited per-client data. confidence: high relevance: medium - claim_id: personalized_aggregation_weighted_by_stylistic_similarity_between_clients_outperforms_uniform role: supports claim: Personalized aggregation weighted by stylistic similarity between clients outperforms uniform averaging for federated style learning. source: §3.3, Table 2 evidence: Under identical GPT-SOVITS-V4 backbone and LoRA configuration, attention-based personalized aggregation achieves SE 0.704 and SS 0.645 versus FedAvg's SE 0.476 and SS 0.523, confirming that style-averaged updates homogenise client models and harm expressivity. confidence: high relevance: medium - claim_id: in_speaker_adaptation_stylisation_steps_beyond_a_small_fraction_of role: complicates claim: In speaker adaptation, stylisation steps beyond a small fraction of total training degrade speaker identity and peak naturalness, establishing a ceiling on achievable style transfer without identity loss. source: §3.4, Figure 2 evidence: Holding total steps at 100, speaker similarity decreases monotonically as stylisation steps increase, while naturalness peaks at 20% stylisation (m=20); excessive stylisation corrupts identity and degrades nMOS. confidence: high relevance: high - claim_id: fair_cross_framework_comparison_in_federated_tts_is_obstructed_when role: complicates claim: Fair cross-framework comparison in federated TTS is obstructed when competing methods are architecturally coupled to legacy backbones and cannot be reimplemented on modern foundations. source: §3.1.2 evidence: FedSpeech and Federated Dynamic Transformer use FastSpeech2-XL and Transformer-TTS respectively and are incompatible with LoRA; the evaluation must compare them on their original configurations, making it impossible to isolate the contribution of the federation strategy from the backbone quality. confidence: high relevance: medium limitations: - The federated baselines (FedSpeech, Federated Dynamic Transformer) run on architecturally distinct and weaker backbones; the performance gap reflects backbone modernization in addition to the proposed federation strategy. No ablation on GPT-SOVITS-V4 with a standard FedAvg baseline using the same LoRA parameter budget is reported to cleanly isolate the aggregation contribution. - Evaluation uses 60 speakers treated as 60 independent clients from four relatively small emotion datasets, which may not represent the statistical diversity or scale of real-world federated deployments. Naturalness is evaluated by 22 in-lab researchers rather than crowd-sourced listeners, which may limit generalisability of the nMOS scores. The paper does not address communication round latency or asynchronous client availability, both of which matter in practical on-device deployment. How the framework scales to many more clients or to cross-lingual speaker sets remains untested. caveats: [] - id: '2509.16195' published_date: "2025-09-19" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - codec - VC architecture: - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - hybrid_semantic_acoustic_voice_conversion claims: - claim_id: single_codebook_binary_quantization_at_sub_1_kbps_bitrates_can role: supports claim: Single-codebook binary quantization at sub-1 kbps bitrates can match or exceed multi-codebook streaming codecs on naturalness and intelligibility in speech resynthesis. source: §4.1, Table 2 evidence: FocalCodec-S@50-65k achieves UTMOS 3.85 and dWER 3.68% at 0.80 kbps with a single codebook of 65,536 entries, outperforming Mimi6 (0.83 kbps, 6 codebooks, UTMOS 3.44, dWER 4.77%) on both metrics. confidence: high relevance: low - claim_id: multi_stage_causal_distillation_of_self_supervised_speech_encoders_preserves role: supports claim: Multi-stage causal distillation of self-supervised speech encoders preserves hybrid acoustic-semantic representations for downstream tasks under streaming constraints. source: §4.2, Table 3 evidence: FocalCodec-Stream variants trained via four-stage WavLM distillation outperform acoustic streaming codecs (EnCodec, AudioDec, HILCodec) on ASR, keyword spotting, and intent classification despite operating at lower bitrates; the 65k variant matches or surpasses PAST on all discriminative and generative tasks except ASR. confidence: high relevance: low - claim_id: supervised_domain_specific_fine_tuning_of_hybrid_codecs_achieves_strong role: complicates claim: Supervised domain-specific fine-tuning of hybrid codecs achieves strong in-domain intelligibility at the cost of multilingual generalization. source: §4.1 evidence: PAST, fine-tuned on English data, achieves the lowest English dWER among streaming codecs (4.04%) but degrades severely on multilingual MLS (49.35% dWER), whereas FocalCodec-Stream (trained on English-only Libri-Light but without supervised task fine-tuning) retains competitive multilingual performance (19.88% dWER). confidence: high relevance: medium - claim_id: voice_conversion_quality_in_streaming_codecs_requires_joint_optimization_of role: supports claim: Voice conversion quality in streaming codecs requires joint optimization of intelligibility and speaker fidelity; gains on one metric alone are insufficient for practical use. source: §4.1, Table 2 evidence: Mimi6 achieves competitive speaker similarity (91.3%) in one-shot VC on VCTK but at 110% dWER, while PAST achieves lower dWER (18.28%) at only 68.5% speaker similarity; FocalCodec-S@50-65k is the only streaming codec to simultaneously achieve high values on both (dWER 22.71%, Sim 92.5%). confidence: high relevance: high - claim_id: a_lightweight_refiner_module_bridging_causal_and_full_context_feature role: supports claim: A lightweight refiner module bridging causal and full-context feature distributions substantially improves perceptual quality in distilled streaming codecs. source: §4.3, Table 4 evidence: Ablation on FocalCodec-S@50-4k shows that removing the refiner degrades UTMOS from 3.87 to 3.84 and dWER from 4.39% to 4.65%; omitting Stage 4 fine-tuning (which jointly trains the refiner) has a larger effect, raising dWER to 5.05% and reducing speaker similarity from 96.3% to 95.8%. confidence: high relevance: low limitations: - Training data is limited to English (LibriTTS, Libri-Light), so the multilingual robustness observed on MLS reflects generalization rather than explicit multilingual training. A performance gap with the non-streaming FocalCodec@50 remains across most metrics, particularly in ASR WER (17% vs. 15.33%) and SI error rate (2.18% vs. 0.35%), reflecting the inherent cost of the 80 ms latency budget. Downstream generative tasks (TTS, speech language modeling) are left for future work, so performance of the codec's discrete representations in autoregressive modeling pipelines is not yet demonstrated. - The paper does not provide listening tests or crowd-sourced MOS, relying instead on the automatic UTMOS predictor for naturalness assessment. caveats: [] - id: '2509.17143' published_date: "2025-09-21" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - VC architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: in_zero_shot_voice_conversion_temporally_coarser_syllabic_representations_reduce role: supports claim: In zero-shot voice conversion, temporally coarser syllabic representations reduce pitch leakage from linguistic features more effectively than standard frame-aligned SSL features, enabling cleaner prosody control at the cost of intelligibility. source: §2.1, §4, Table 2 evidence: MaskVCT-Spk using SylBoost syllabic tokens achieves the lowest FPC (0.167) among all tested systems, indicating near-complete pitch independence from the source, while MaskVCT-All with continuous features retains more pitch correlation (FPC 0.417). confidence: high relevance: high - claim_id: multiple_classifier_free_guidance_weights_applied_to_distinct_conditioning_factors role: supports claim: Multiple classifier-free guidance weights applied to distinct conditioning factors in a single masked generative model enable user-configurable inference-time trade-offs between intelligibility, pitch fidelity, and speaker similarity. source: §2.5, §3.4, Table 2 evidence: MaskVCT defines triple CFG weights (w_all, w_spk, w_ling) over speaker, pitch, and linguistic conditions within one trained model; sweeping these weights continuously interpolates between MaskVCT-All (WER 4.68%, S-SIM 0.865) and MaskVCT-Spk (WER 6.47%, S-SIM 0.895). confidence: high relevance: medium - claim_id: syllabic_speech_representations_that_suppress_pitch_leakage_in_voice_conversion role: complicates claim: Syllabic speech representations that suppress pitch leakage in voice conversion also degrade content intelligibility through syllable misreadings caused by coarse temporal quantisation. source: §4, §5, Table 2 evidence: MaskVCT-Spk achieves the highest speaker similarity (S-SIM 0.895) but the highest WER (6.47%) among systems tested, substantially above FACodec (3.55%) and FreeVC (3.96%); the conclusion section attributes misreadings to K-means syllable mapping errors in SylBoost. confidence: high relevance: high - claim_id: masked_non_autoregressive_codec_models_can_match_or_exceed_autoregressive role: supports claim: Masked non-autoregressive codec models can match or exceed autoregressive and diffusion-based baselines on speaker similarity and quality in zero-shot VC while operating with fewer discrete tokens per utterance. source: §3.4, §4, Table 2 evidence: MaskVCT-Spk (2048 tokens) achieves higher S-SIM (0.895) and SS-MOS (3.69) than MaskGCT-S2A (8192 tokens, S-SIM 0.863, SS-MOS 3.02) and competitive UTMOS (3.17 vs. 3.24). confidence: high relevance: high limitations: - Syllabic tokens introduce misreadings that WER alone cannot fully diagnose; the authors acknowledge the K-means quantiser cannot recover from incorrect syllable boundary assignments, and propose future work to address this with a trainable VQ module. - The model is English-only. Accent conversion experiments are limited to L2-ARCTIC and test only two conversion directions; how well the syllabic pitch-stripping generalises to tonal languages (where pitch is phonemic) is unexplored. The 511-pair test set is relatively small for statistical confidence, especially given the reported confidence intervals overlap for several key comparisons. No code or trained checkpoint is publicly released, limiting reproducibility. caveats: [] - id: '2509.18060' published_date: "2025-09-22" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS architecture: - flow-matching relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence - infrastructure current_role: active_evidence method_family: - flow_matching_voice_conversion claims: - claim_id: routing_hidden_representations_through_dialect_specific_sub_networks_inside_the role: supports claim: Routing hidden representations through dialect-specific sub-networks inside the Transformer FFN captures fine-grained dialectal acoustic variation more effectively than conditioning through a shared-parameter network alone. source: §3.3, Table 2 evidence: Ablating DSDR-Net (replacing it with a standard shared FFN) while keeping the dialect fusion embedding drops dialect classification accuracy from 80.25% to 60.12% and dialect embedding cosine similarity from 78.3% to 58.6%. confidence: high relevance: medium - claim_id: injecting_dialect_style_conditioning_early_into_both_the_encoder_and role: supports claim: Injecting dialect/style conditioning early, into both the encoder and the generative (flow-prediction) network, produces more dialect-consistent speech than injecting it only at the output stage via separate per-dialect vocoders. source: §3.2, Table 1 evidence: Compared to a prior Tibetan multi-dialect design that shares a mel-decoder and uses separate per-dialect WaveNet vocoders, TMD-TTS's early dialect fusion module plus DSDR-Net reaches up to 88.09% DECS and 87.78% DCA versus a Matcha-TTS baseline extended with the late-fusion design (65.2–65.8% on the same metrics). confidence: high relevance: medium - claim_id: synthetic_speech_generated_by_a_dialect_conditioned_tts_system_when role: supports claim: Synthetic speech generated by a dialect-conditioned TTS system, when filtered for dialect consistency and perceptual quality, is usable as training data for a downstream speech-to-speech conversion task and can outperform a small, manually collected parallel corpus. source: §3.5, Table 4 evidence: A voice conversion model (DurFlex-EVC) trained on the TMDD dataset synthesized by TMD-TTS achieves higher MOS (3.23/3.63 at 16k/22kHz) than the same model trained on the prior manually collected baseline dataset (3.07/3.54). confidence: high relevance: medium - claim_id: gains_in_speaker_style_consistency_metrics_from_dialect_or_attribute role: complicates claim: Gains in speaker/style-consistency metrics from dialect- or attribute-specific conditioning mechanisms can come with a measurable inference-speed cost relative to simpler architectures. source: §3.2 evidence: TMD-TTS's real-time factor (~0.031–0.032) is roughly 50% higher than VITS2's (~0.020–0.021), even though TMD-TTS still meets real-time synthesis requirements. confidence: high relevance: medium limitations: - The evaluation is confined to a single language (Tibetan) and its three dialects; no experiments test whether DSDR-Net's routing mechanism generalizes to other dialect-continuum languages or to conventional multilingual TTS. The dialect classifier used for DCA/DECS metrics is itself a pretrained model whose own accuracy is not independently validated in this paper, so objective dialect-fidelity numbers are only as trustworthy as that classifier. Code and demo availability are not stated in the paper. The comparison baselines were reimplemented by the authors rather than run from official checkpoints, which is a reasonable and disclosed choice given the lack of existing public multi-dialect Tibetan TTS baselines, but leaves some residual uncertainty about baseline tuning. caveats: [] - id: '2509.19231' published_date: "2025-09-23" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - VC - evaluation architecture: - diffusion - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - diffusion_voice_conversion - gan_adversarial_voice_conversion claims: - claim_id: disentangling_acoustic_pronunciation_linked_style_from_prosodic_and_speaker_identity role: supports claim: Disentangling acoustic (pronunciation-linked) style from prosodic and speaker-identity style in a TTS-based reconstruction system allows mispronunciation patterns to be suppressed while speaker identity is preserved. source: §5.1, Table 1 evidence: ChiReSSD, which selectively fine-tunes acoustic/prosodic style encoders and the pitch extractor while reusing StyleTTS2's disentangled style representations, achieves higher speaker similarity (0.62) and lower pitch deviation (19.98%) than a one-shot baseline that transfers style holistically from an unseen reference without domain adaptation (0.52 similarity, 22.58% F0 difference). confidence: high relevance: high - claim_id: optimizing_a_speech_reconstruction_system_for_automatic_speech_recognition_based role: complicates claim: Optimizing a speech reconstruction system for automatic-speech-recognition-based intelligibility metrics can conflict with optimizing for speaker-identity preservation. source: §5.2, Table 2 evidence: A single-speaker adult-voice TTS baseline with no style transfer obtains the lowest WER/CER on STAR (0.34/0.11) precisely because it discards the child speaker's identity, while the identity-preserving ChiReSSD model scores worse on the same ASR-based metrics (WER 0.49, CER 0.29) despite being judged clinically more accurate. confidence: high relevance: medium - claim_id: an_automatic_phone_recognition_based_estimate_of_consonant_production_accuracy role: supports claim: An automatic phone-recognition-based estimate of consonant production accuracy can approximate expert clinical judgments of speech intelligibility well enough to reduce, though not eliminate, the need for manual phonetic transcription. source: §5.3 evidence: Automatic PCC estimates derived from a universal phone recognizer and Levenshtein distance correlate with a certified speech-language therapist's manual PCC annotations at Pearson ρ = 0.63 across 21 original/reconstructed sample pairs. confidence: high relevance: medium - claim_id: a_style_based_tts_reconstruction_approach_adapted_for_one_clinical role: supports claim: A style-based TTS reconstruction approach adapted for one clinical population of disordered speech can generalize to a structurally different disorder and age group without population-specific retraining. source: §5.4, Table 3 evidence: ChiReSSD, trained only on pediatric SSD data, reduces CER to below 0.03 and WER to as low as 0.06 on the TORGO adult dysarthria dataset across mild-to-severe severity levels, while keeping speaker similarity at 0.74-0.77, versus 0.43-0.55 for a non-personalized TTS baseline. confidence: high relevance: medium limitations: - Clinical validation of the automatic PCC metric rests on only 21 annotated sample pairs from a single speech-language therapist, with no inter-rater reliability reported; the ρ = 0.63 correlation should be treated as a preliminary estimate, not a validated clinical tool. - The STAR evaluation set itself is small (234 utterances from six children), and reconstruction quality is partly assessed with ASR models (whisperX) that are known to be poorly calibrated for child and disordered speech, which the paper acknowledges as a likely source of residual error inflation on STAR relative to LibriTTS. Generalization beyond the two evaluated accents/populations (Central Scottish child SSD, Canadian English adult dysarthria) is untested, and the guidance parameters (α, β) were tuned rather than learned, leaving open whether they transfer to other disorder types or severities without manual retuning. caveats: [] - id: '2509.19812' published_date: "2025-09-24" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS architecture: - GAN relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - gan_adversarial_voice_conversion claims: - claim_id: progressive_mixing_based_knowledge_distillation_can_compress_a_deep_audio role: supports claim: Progressive, mixing-based knowledge distillation can compress a deep audio watermarking encoder to a fraction of its computational cost while matching the teacher model's robustness and imperceptibility. source: §IV.D-E, Tables I-II evidence: Distilling from an 8-block/32-channel INN teacher to a 2-block/16-channel student lowers GFLOPS by 93.6% (36.0 → 2.3) yet the student's average BER (0.51%) is lower than the teacher's (0.56%) and its PESQ (4.30) is within 0.03 of the teacher's (4.33). confidence: high relevance: medium - claim_id: distilling_a_compressed_watermarking_encoder_by_supervising_it_only_through role: complicates claim: Distilling a compressed watermarking encoder by supervising it only through the teacher's decoder output, without intermediate mixing of encoder representations, transfers robustness poorly. source: §IV.E, Table I evidence: A direct knowledge distillation (DKD) student trained under identical settings to PKDMark shows more than triple the bit error rate (1.94% vs 0.51%) and lower perceptual quality (PESQ 4.08 vs 4.30). confidence: high relevance: medium - claim_id: embedding_watermark_information_using_both_phase_and_amplitude_in_the role: refines claim: Embedding watermark information using both phase and amplitude in the complex STFT domain, rather than amplitude alone, improves the robustness of deep audio watermarking against signal distortions. source: §IV.E, Table I evidence: Removing the complex-valued message feature map from the teacher model (amplitude-only embedding) raises average BER from 0.56% to 1.77% and drops SNR from 45.75dB to 42.25dB. confidence: high relevance: medium - claim_id: efficient_watermark_detectors_that_achieve_near_perfect_bit_accuracy_under role: complicates claim: Efficient watermark detectors that achieve near-perfect bit accuracy under basic signal distortions can still fail under advanced temporal-domain attacks such as time-stretching, pitch-shifting, or reverberation. source: §IV.C, Table I evidence: AudioSeal attains 0.00% BER on several basic distortions but its BER rises to 47-59% under slow-speed, fast-speed, and pitch-shift attacks, driving its average to 18.66% versus PKDMark's 0.51% under the same 14-distortion suite. confidence: high relevance: medium limitations: - The paper explicitly leaves neural codec compression and neural denoising attacks untested, which is a significant gap given that the stated motivating threat, unauthorized voice cloning by modern generative speech models, increasingly routes synthesized audio through neural codecs before distribution. - Beyond that gap, the evaluation compares against only two open-source baselines (WavMark, AudioSeal); several more recent efficient or robust watermarking systems discussed in the paper's own related work (SilentCipher, DiscreteWM, MaskMark) are not empirically compared. The detection experiment relies on a simple majority-vote heuristic over an 8-bit synchronization code (7-of-8 bit match), whose robustness to attacks specifically targeting the sync code is not evaluated. The training corpus includes 100 hours of Microsoft Azure TTS synthetic speech whose characteristics are not detailed, and although CommonVoice is multilingual, no per-language robustness breakdown is reported. caveats: [] - id: '2509.24570' published_date: "2025-09-29" entry_date: '2026-07-28' year: 2025 venue: arXiv task: - TTS - VC - evaluation architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - control_evidence - infrastructure current_role: active_evidence method_family: - autoregressive_token_voice_conversion claims: - claim_id: automated_pipelines_combining_expressive_tts_voice_conversion_and_llm_based role: supports claim: Automated pipelines combining expressive TTS, voice conversion, and LLM-based instruction generation can produce large-scale paired speech style editing data without manual recording or annotation, provided a multi-criterion filtering step is applied. source: §2.1, §2.2, Fig. 3 evidence: The three-stage pipeline (EmoCapTTS synthesis + Chatterbox voice conversion + Qwen3-8B instruction generation) yields 382 hours and ~100,000 pairs from EARS and Expresso source material, filtered to WER < 10, style similarity > 0.5, and speaker similarity > 0.5 *(§2.1, §2.2, Fig. 3)*. confidence: high relevance: high - claim_id: fine_grained_diverse_natural_language_instructions_improve_both_in_domain role: supports claim: Fine-grained, diverse natural-language instructions improve both in-domain accuracy and cross-domain generalization of instruction-guided speech style editing models relative to coarse, templated instruction sets. source: §4.2, Table 2 evidence: LlasaEdit trained on ISSE outperforms the same architecture trained on ESD across WER, style similarity, speaker similarity, and UTMOS in-domain (8.06 vs. 10.07 WER; 0.68 vs. 0.64 style-sim), and the ISSE-trained model's cross-domain performance on ESD exceeds the ESD-trained model's in-domain performance on several metrics *(§4.2, Table 2)*. confidence: high relevance: medium - claim_id: instruction_guided_style_editing_models_trained_on_narrow_templated_instruction role: complicates claim: Instruction-guided style editing models trained on narrow, templated-instruction datasets fail catastrophically when evaluated on more diverse, fine-grained instruction distributions. source: §4.2, Table 2 evidence: The ESD-trained LlasaEdit model, when evaluated on the ISSE test set, produces a WER of 68.17, compared to 10.07 on its own in-domain ESD test set, indicating the model does not generalize beyond the coarse single-attribute instructions it was trained on *(§4.2, Table 2)*. confidence: high relevance: medium - claim_id: isolating_style_variation_from_speaker_identity_in_synthetically_generated_paired role: complicates claim: Isolating style variation from speaker identity in synthetically generated paired training data requires an explicit voice-conversion correction step, since expressive TTS models conditioned on style descriptions alone conflate style and timbre changes. source: §2.1 evidence: EmoCapTTS-generated stylized speech differs from the anchor speech in timbre because the model lacks explicit speaker control; a separate voice conversion stage (Chatterbox) is needed to re-align target timbre to the anchor speaker before the pair can be used to define a style-only edit *(§2.1)*. confidence: high relevance: high limitations: - The dataset and benchmark are limited to English, which the authors explicitly flag as constraining applicability to multilingual editing scenarios. The generated portion of ISSE (292 of 382 hours) is itself the product of a TTS+VC synthesis pipeline rather than real recordings, so any systematic biases or artifacts introduced by EmoCapTTS or Chatterbox could propagate into models trained on it; the quality-filtering thresholds (WER < 10, similarity > 0.5) are relatively loose and their effect on downstream editing fidelity is not separately ablated. The benchmark comparison is against a single alternative dataset (ESD) and a single model architecture (LlasaEdit); no comparison is made against other instruction-guided editing systems such as InstructSpeech, and no ablation isolates the individual contribution of instruction diversity versus raw data scale. caveats: [] claim_clusters: - id: content_speaker_disentanglement_enables_conversion claim: Separating linguistic content from speaker identity is central to robust voice conversion. status: strongly_supported confidence: high supporting_papers: - '2104.00355' - '2403.03100' - '2406.02430' - '2412.04724' - '2502.07243' - '2507.04817' - '2507.09070' - 2025.acl-demo.37 - '2508.02038' - '2508.06890' - '2508.08399' - interspeech-2025-0305 - interspeech-2025-0438 - interspeech-2025-0464 - interspeech-2025-0902 - interspeech-2025-1081 - interspeech-2025-1101 - interspeech-2025-1106 - interspeech-2025-1210 - interspeech-2025-1229 - interspeech-2025-1434 - interspeech-2025-1440 - interspeech-2025-1531 - interspeech-2025-1538 - interspeech-2025-1639 - interspeech-2025-1747 - interspeech-2025-1779 - interspeech-2025-2684 - '2509.09201' - '2509.13068' - '2509.16010' - '2509.19231' contradicting_papers: [] refining_papers: - '2507.09070' - interspeech-2025-0115 - interspeech-2025-1106 - interspeech-2025-1397 - interspeech-2025-1531 - interspeech-2025-1639 - interspeech-2025-1747 - interspeech-2025-2043 - '2411.19770' - '2509.09201' caveats: - Perfect separation is neither demonstrated nor always desirable because prosody and accent carry both linguistic and speaker information. last_reviewed: '2026-07-28' - id: ssl_units_improve_content_representation claim: Self-supervised speech representations provide speaker-reduced content units that improve conversion intelligibility and transfer. status: strongly_supported confidence: high supporting_papers: - '2104.00355' - '2502.07243' - 2025.naacl-short.65 - '2507.09070' - 2025.acl-long.790 - 2025.acl-long.87 - '2508.04996' - '2508.08399' - interspeech-2025-0438 - interspeech-2025-0998 - interspeech-2025-1229 - interspeech-2025-1440 - interspeech-2025-1531 - interspeech-2025-1625 - interspeech-2025-2043 - interspeech-2025-2684 - '2411.19770' - '2507.14534' contradicting_papers: [] refining_papers: - '2507.02176' - 2025.acl-long.87 - interspeech-2025-0305 - interspeech-2025-1106 - interspeech-2025-1531 - interspeech-2025-2043 - interspeech-2025-2684 caveats: - SSL layers retain different amounts of pitch, style, and identity, so the choice of layer and discretization remains consequential. last_reviewed: '2026-07-28' - id: speaker_similarity_intelligibility_tradeoff claim: Voice conversion systems face a persistent trade-off between target-speaker similarity and linguistic intelligibility. status: strongly_supported confidence: high supporting_papers: - '2104.00355' - '2411.09943' - '2412.04724' - '2502.07243' - '2507.04817' - '2507.09310' - 2025.acl-long.790 - 2025.acl-long.87 - interspeech-2025-0305 - interspeech-2025-0438 - interspeech-2025-0816 - interspeech-2025-1081 - interspeech-2025-1531 - interspeech-2025-1538 - interspeech-2025-1779 - '2509.15462' - '2509.17143' contradicting_papers: [] refining_papers: - '2411.09943' - '2507.09070' - 2025.acl-long.87 - '2508.08399' - interspeech-2025-1106 - interspeech-2025-2043 - '2508.16332' - '2509.08379' - '2509.09201' caveats: - Reported trade-offs are sensitive to speaker-verification models, ASR models, languages, and reference conditions. last_reviewed: '2026-07-28' - id: reference_conditioning_controls_zero_shot_fidelity claim: The amount and representation of target-speaker reference audio strongly controls zero-shot conversion fidelity. status: strongly_supported confidence: high supporting_papers: - '2411.09943' - '2412.04724' - interspeech-2025-0203 - interspeech-2025-0816 - interspeech-2025-0948 - interspeech-2025-1229 - interspeech-2025-2151 - interspeech-2025-2684 - '2411.19770' - '2509.15462' contradicting_papers: [] refining_papers: - 2025.naacl-short.65 - interspeech-2025-0305 - interspeech-2025-0464 - interspeech-2025-0998 - interspeech-2025-2684 - '2411.19770' - '2509.14579' caveats: - Reference duration and recording conditions vary substantially across studies, limiting direct comparison. last_reviewed: '2026-07-28' - id: zero_shot_any_to_any_conversion_is_feasible claim: Zero-shot and any-to-any conversion can generalize to unseen speakers without per-speaker retraining. status: strongly_supported confidence: high supporting_papers: - '2411.09943' - '2412.04724' - '2502.07243' - 2025.naacl-short.65 - '2507.09070' - '2507.09282' - 2025.acl-demo.37 - 2025.acl-long.790 - 2025.acl-long.87 - interspeech-2025-0575 - interspeech-2025-0815 - interspeech-2025-0816 - interspeech-2025-1081 - interspeech-2025-1434 - interspeech-2025-1779 - interspeech-2025-2684 - '2507.14534' - '2509.14579' - '2509.17143' contradicting_papers: [] refining_papers: - '2411.09943' - 2025.naacl-short.65 - 2025.acl-long.87 - interspeech-2025-0656 - interspeech-2025-1081 caveats: - Unseen-speaker success often degrades for accents, expressive styles, atypical speech, and out-of-domain channels. last_reviewed: '2026-07-28' - id: prosody_timbre_factorization_improves_control claim: Factoring prosody, style, pitch, and timbre enables more controllable conversion than a single speaker bottleneck. status: strongly_supported confidence: high supporting_papers: - '2104.00355' - '2312.01479' - '2411.09943' - '2412.04724' - '2502.07243' - '2507.04817' - '2507.09310' - '2506.18296' - 2025.acl-long.790 - '2508.02038' - '2508.06890' - interspeech-2025-0203 - interspeech-2025-0433 - interspeech-2025-0464 - interspeech-2025-0787 - interspeech-2025-0815 - interspeech-2025-0948 - interspeech-2025-1101 - interspeech-2025-1210 - interspeech-2025-1639 - interspeech-2025-1779 - interspeech-2025-2043 - interspeech-2025-2684 - interspeech-2025-cho25c_interspeech - '2508.16332' - '2507.14534' - '2509.13068' - '2509.15462' - '2509.15629' - '2509.16010' - '2509.17143' - '2509.19231' contradicting_papers: [] refining_papers: - 2025.naacl-short.65 - '2507.04817' - '2507.09310' - interspeech-2025-0433 - interspeech-2025-0464 - interspeech-2025-1101 - interspeech-2025-1210 - interspeech-2025-1397 - interspeech-2025-1639 - interspeech-2025-2684 - '2508.16332' - '2509.17143' - '2509.24570' caveats: - Fine-grained factorization can reduce naturalness when the factors interact or are estimated unreliably. last_reviewed: '2026-07-28' - id: flow_matching_improves_parallel_conversion claim: Flow matching enables high-quality voice conversion with fewer sequential generation steps than diffusion or autoregressive alternatives. status: strongly_supported confidence: high supporting_papers: - '2412.04724' - 2025.acl-long.790 - 2025.acl-long.87 - '2508.04996' - interspeech-2025-0203 - interspeech-2025-0305 - interspeech-2025-1229 - interspeech-2025-1779 - interspeech-2025-2684 - '2509.08379' - '2509.15629' contradicting_papers: [] refining_papers: - '2509.08379' caveats: - Speed comparisons depend on solver steps, hardware, decoder implementation, and latent dimensionality. last_reviewed: '2026-07-28' - id: diffusion_supports_flexible_voice_conversion claim: Diffusion models support high-fidelity voice conversion under speaker, pitch, and style conditioning. status: strongly_supported confidence: high supporting_papers: - '2411.09943' - '2412.04724' - 2025.acl-long.87 - interspeech-2025-1101 - interspeech-2025-1434 - interspeech-2025-1747 - interspeech-2025-1779 - '2509.08379' - '2509.15629' - '2509.17143' contradicting_papers: [] refining_papers: - interspeech-2025-0998 - interspeech-2025-1210 caveats: - Iterative sampling remains a latency constraint and evaluations often use different baselines or step budgets. last_reviewed: '2026-07-28' - id: adversarial_training_reduces_identity_leakage claim: Adversarial objectives can suppress source-speaker leakage and improve perceptual conversion quality. status: strongly_supported confidence: high supporting_papers: - '2508.06890' - interspeech-2025-0305 - interspeech-2025-1081 - interspeech-2025-1625 - interspeech-2025-1763 - interspeech-2025-2151 - interspeech-2025-cho25c_interspeech - '2508.15565' - '2509.08379' contradicting_papers: [] refining_papers: - '2507.04817' - interspeech-2025-1763 caveats: - Adversarial training may destabilize optimization and does not guarantee preservation of linguistic content. last_reviewed: '2026-07-28' - id: codec_and_discrete_tokens_enable_modular_vc claim: Codec and discrete speech tokens provide modular interfaces for content-preserving conversion and waveform resynthesis. status: strongly_supported confidence: high supporting_papers: - '2507.01348' - '2507.09070' - '2508.08399' - interspeech-2025-0115 - interspeech-2025-0464 - interspeech-2025-0815 - interspeech-2025-0998 - interspeech-2025-1106 - interspeech-2025-1639 - interspeech-2025-2684 - '2509.13068' - '2509.16195' - '2509.17143' contradicting_papers: [] refining_papers: - interspeech-2025-1106 - interspeech-2025-1531 - interspeech-2025-1538 - '2509.08379' caveats: - Quantization can discard pitch, timing, and identity cues or leak them into nominally content-only tokens. last_reviewed: '2026-07-28' - id: cross_lingual_conversion_requires_accent_control claim: Cross-lingual voice conversion requires separating speaker identity from language and accent while preserving intelligibility. status: strongly_supported confidence: high supporting_papers: - '2312.01479' - '2409.09098' - '2502.07243' - '2507.01348' - interspeech-2025-0815 - '2509.14579' contradicting_papers: [] refining_papers: - '2409.09098' caveats: - Evidence is concentrated in a limited set of high-resource languages and accent labels can conflate speaker and geography. last_reviewed: '2026-07-28' - id: nonparallel_training_reduces_data_requirements claim: Non-parallel and unpaired training make voice conversion feasible without matched source–target utterances. status: emerging confidence: medium supporting_papers: - interspeech-2025-2151 - '2509.08379' contradicting_papers: [] refining_papers: [] caveats: - Removing parallel-data requirements can weaken identifiability and makes objective evaluation harder. last_reviewed: '2026-07-28' - id: robust_conversion_requires_domain_invariance claim: Robust voice conversion requires content and speaker representations that tolerate noise, channel, and domain mismatch. status: strongly_supported confidence: high supporting_papers: - '2406.02430' - '2507.01348' - '2507.09310' - '2506.18296' - '2508.04996' - interspeech-2025-0998 - interspeech-2025-1229 - interspeech-2025-1531 - interspeech-2025-1639 - '2411.19770' - '2509.07376' contradicting_papers: [] refining_papers: - 2025.acl-long.87 - '2411.19770' - '2509.08379' - '2509.09201' caveats: - Robustness improvements on simulated corruption may not transfer to spontaneous or pathological speech. last_reviewed: '2026-07-28' - id: singing_conversion_requires_pitch_preservation claim: Singing voice conversion requires explicit pitch handling to preserve melody while transferring singer identity. status: strongly_supported confidence: high supporting_papers: - '2411.09943' - interspeech-2025-0305 - interspeech-2025-0816 - interspeech-2025-1397 - interspeech-2025-1531 - '2508.16332' - '2509.15629' contradicting_papers: [] refining_papers: - interspeech-2025-0305 - interspeech-2025-1397 - '2508.16332' caveats: - Speech-derived content and speaker encoders may not cover sustained phonation, wide pitch ranges, and vocal techniques. last_reviewed: '2026-07-28' - id: privacy_conversion_trades_utility_for_unlinkability claim: Speaker anonymization and privacy-oriented conversion trade identity unlinkability against intelligibility and naturalness. status: emerging confidence: medium supporting_papers: - '2506.18296' - '2508.15565' contradicting_papers: [] refining_papers: [] caveats: - Privacy scores depend on the attacker model and may not protect against stronger or cross-domain recognizers. last_reviewed: '2026-07-28' - id: automatic_metrics_do_not_fully_capture_vc_quality claim: Automatic intelligibility, signal, and speaker metrics do not fully capture listener-perceived voice-conversion quality. status: contested confidence: medium supporting_papers: - '2406.02430' - '2507.01348' - '2506.18296' - interspeech-2025-0383 - interspeech-2025-0656 - interspeech-2025-0816 - interspeech-2025-0948 - interspeech-2025-1550 - interspeech-2025-2151 - interspeech-2025-2283 - '2508.16332' - '2507.14534' - '2504.20581' - '2509.15629' contradicting_papers: - interspeech-2025-2283 refining_papers: - '2409.09098' - '2506.18296' - '2507.10985' - 2025.acl-long.87 - '2508.00317' - interspeech-2025-0438 - interspeech-2025-1081 - interspeech-2025-1101 - interspeech-2025-1106 - interspeech-2025-1229 - interspeech-2025-1538 - interspeech-2025-1747 - '2411.19770' - '2509.09201' - '2509.19231' caveats: - Metrics measure different properties; WER can remain useful for intelligibility even when it is insufficient as a global quality measure. last_reviewed: '2026-07-28' - id: data_diversity_drives_unseen_speaker_generalization claim: Training-speaker and acoustic diversity is a major determinant of unseen-speaker voice-conversion generalization. status: strongly_supported confidence: high supporting_papers: - 2025.naacl-short.65 - '2508.02038' - '2411.19770' - '2509.18060' contradicting_papers: [] refining_papers: - '2509.24570' caveats: - Scale effects are frequently confounded with model capacity, pretraining, and data quality. last_reviewed: '2026-07-28' method_families: - id: gan_adversarial_voice_conversion name: GAN and adversarial voice conversion summary: Adversarial encoders and waveform decoders learn speaker transfer while discriminators enforce realism or suppress source identity. papers: - '2104.00355' - '2312.01479' - 2025.naacl-short.65 - '2507.04817' - '2507.01348' - '2508.06890' - interspeech-2025-0815 - interspeech-2025-0902 - interspeech-2025-0998 - interspeech-2025-1081 - interspeech-2025-1106 - interspeech-2025-1531 - interspeech-2025-1550 - interspeech-2025-1625 - interspeech-2025-1639 - interspeech-2025-1747 - interspeech-2025-1763 - interspeech-2025-2151 - '2508.15565' - '2507.14534' - '2509.04667' - '2509.09201' - '2509.19231' - '2509.19812' open_questions: - How can adversarial VC remain stable under large prosodic, accent, or domain shifts? - id: vae_latent_voice_conversion name: VAE latent voice conversion summary: VAE-derived systems factor speech into latent content, speaker, and style variables for reconstruction and conversion. papers: - '2104.00355' - '2312.01479' - '2507.01348' - '2507.09282' - '2507.09310' - '2508.08399' - interspeech-2025-0433 - interspeech-2025-0575 - interspeech-2025-0815 - interspeech-2025-0902 - interspeech-2025-0948 - interspeech-2025-1106 - interspeech-2025-1440 - interspeech-2025-1531 - interspeech-2025-1550 - '2509.07376' - '2509.13068' open_questions: - Which latent constraints separate speaker identity without over-smoothing linguistic and prosodic detail? - id: autoregressive_token_voice_conversion name: Autoregressive token voice conversion summary: Autoregressive models cast conversion or resynthesis as conditional prediction over discrete speech or codec tokens. papers: - '2310.00704' - '2406.02430' - '2502.07243' - '2507.01348' - '2507.09070' - '2507.09282' - '2508.02038' - '2508.08961' - interspeech-2025-0464 - interspeech-2025-0787 - interspeech-2025-1538 - interspeech-2025-1993 - '2508.16332' - '2509.00503' - '2509.13068' - '2509.15462' - '2509.17143' - '2509.24570' open_questions: - Can autoregressive token VC avoid long-form errors and latency without losing in-context speaker fidelity? - id: flow_matching_voice_conversion name: Flow-matching voice conversion summary: Flow-matching systems transform continuous acoustic or latent representations with parallel generation and low-step inference. papers: - '2412.04724' - '2502.07243' - '2507.09070' - 2025.acl-long.790 - 2025.acl-long.87 - '2508.02038' - '2508.04996' - interspeech-2025-0203 - interspeech-2025-0305 - interspeech-2025-1229 - interspeech-2025-1779 - interspeech-2025-2684 - '2508.16332' - '2509.08379' - '2509.14579' - '2509.15462' - '2509.18060' open_questions: - Do flow-matching speed and quality gains persist under matched data, decoder, and reference conditions? - id: diffusion_voice_conversion name: Diffusion voice conversion summary: Diffusion models denoise acoustic or compressed latents under content, pitch, style, and target-speaker conditioning. papers: - '2403.03100' - '2406.02430' - '2411.09943' - '2507.09282' - interspeech-2025-0816 - interspeech-2025-0948 - interspeech-2025-0998 - interspeech-2025-1101 - interspeech-2025-1210 - interspeech-2025-1397 - interspeech-2025-1434 - interspeech-2025-1747 - interspeech-2025-1763 - '2411.19770' - '2509.08379' - '2509.19231' open_questions: - How few denoising steps can preserve identity, pitch, and naturalness for real-time conversion? - id: hybrid_semantic_acoustic_voice_conversion name: Hybrid semantic–acoustic voice conversion summary: Hybrid systems combine semantic content encoders with acoustic, prosodic, or speaker pathways to control what is preserved and replaced. papers: - '2310.00704' - '2403.03100' - '2406.02430' - '2502.07243' - 2025.naacl-short.65 - 2025.acl-demo.37 - '2508.02038' - interspeech-2025-0438 - interspeech-2025-0656 - interspeech-2025-cho25c_interspeech - '2508.16332' - '2507.14534' - '2509.04667' - '2509.16010' - '2509.16195' open_questions: - Where should semantic, speaker, and prosodic information be separated to minimize leakage? - id: transformer_encoder_decoder_voice_conversion name: Transformer encoder–decoder voice conversion summary: Transformer encoder–decoder models convert contextual content representations under explicit target-speaker and style conditioning. papers: - '2411.09943' - '2409.09098' - '2508.06890' - interspeech-2025-0115 - interspeech-2025-0203 - interspeech-2025-0305 - interspeech-2025-0383 - interspeech-2025-1550 - interspeech-2025-2043 - '2509.00503' open_questions: - Do contextual encoders improve unseen-speaker transfer after controlling for pretraining scale and reference duration? reassessment_queue: - id: speaker_similarity_intelligibility_tradeoff type: claim_status reason: The apparent trade-off depends on the speaker and ASR evaluators. trigger: Matched human and automatic evaluations show the trade-off under controlled reference and language conditions. due: 2026-10 current_assessment: strongly_supported watch_for: - Matched similarity–intelligibility ablations - Human identity judgments - id: automatic_metrics_do_not_fully_capture_vc_quality type: benchmark_validity reason: The cluster includes one direct counterclaim that WER is reliable for underrepresented accents. trigger: A shared VC benchmark validates metric behavior across accents, languages, and conversion families. due: 2026-10 current_assessment: contested watch_for: - Accent-stratified metric correlations - Listener-calibrated VC evaluation - id: hybrid_semantic_acoustic_voice_conversion type: method_family reason: The family groups several different placements of semantic, speaker, and acoustic pathways. trigger: Enough matched systems exist to split parallel streams, layer-wise factorization, and semantic-token conditioning. due: 2026-10 current_assessment: active_evidence watch_for: - Matched factorization ablations - Information-leakage probes - id: cross_lingual_conversion_requires_accent_control type: claim_status reason: Language and accent coverage remains narrow and speaker-confounded. trigger: Independent multilingual studies evaluate unseen speakers and accents with balanced language coverage. due: 2026-10 current_assessment: strongly_supported watch_for: - Balanced multilingual VC benchmarks - Speaker–accent disentanglement studies - id: privacy_conversion_trades_utility_for_unlinkability type: claim_status reason: Privacy conclusions depend on attacker strength and evaluation domain. trigger: Adaptive-attacker evaluations reproduce privacy–utility trade-offs across domains. due: 2026-10 current_assessment: strongly_supported watch_for: - Adaptive speaker-recognition attacks - Cross-domain anonymization tests open_questions: - What representation best removes source identity while preserving linguistic content, prosody, accent, and non-verbal vocal events? - How should zero-shot VC evaluations control target-reference duration, recording channel, and speaker familiarity? - Can one conversion model generalize across speech, singing, whispered speech, atypical speech, accents, and cross-lingual conditions? - Which automatic metrics jointly predict intelligibility, target identity, naturalness, style fidelity, and privacy? - When do flow-matching or diffusion backends outperform simpler feed-forward or adversarial converters under matched compute? - How can privacy-oriented conversion state guarantees against adaptive speaker-recognition attacks without obscuring utility losses? trend_notes: - Voice conversion has shifted from paired speaker-specific mappings toward zero-shot any-to-any systems. - Self-supervised and codec representations increasingly replace hand-designed acoustic bottlenecks for content extraction. - Flow-matching and diffusion became prominent conversion backends in 2024–2025, especially for zero-shot and singing settings. - Recent systems increasingly factor timbre, prosody, emotion, accent, and linguistic content rather than treating speaker identity as one embedding. - Evaluation is broadening from MOS and speaker similarity toward intelligibility, accent fidelity, robustness, privacy, and downstream-task behavior.