concept: transformer-enc-dec-tts last_updated: '2026-07-30' paper_count: 28 papers: - id: '1703.10135' published_date: "2017-03-29" entry_date: '2026-07-30' year: 2017 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - evaluation_caution current_role: foundational method_family: - transformer_encoder_decoder_tts claims: - claim_id: end_to_end_tts_models_trained_from_characters_with_seq2seq role: supports claim: End-to-end TTS models trained from characters with seq2seq attention can match or exceed production statistical parametric systems in subjective naturalness without hand-engineered linguistic features. source: §5.2, Table 2 evidence: End-to-end TTS models trained from characters with seq2seq attention can match or exceed production statistical parametric systems in subjective naturalness without hand-engineered linguistic features. confidence: high relevance: high - claim_id: training_stability_and_alignment_quality_in_character_level_seq2seq_tts role: supports claim: Training stability and alignment quality in character-level seq2seq TTS improve substantially when the decoder emits multiple output frames per attention step rather than one. source: §3.3 evidence: Training stability and alignment quality in character-level seq2seq TTS improve substantially when the decoder emits multiple output frames per attention step rather than one. confidence: high relevance: high - claim_id: cbhg_style_encoders_combining_multi_scale_convolution_highway_networks_and role: supports claim: CBHG-style encoders combining multi-scale convolution, highway networks, and bidirectional recurrence yield more robust text representations than standard RNN encoders, reducing mispronunciation rates. source: §3.2, §5.1 evidence: CBHG-style encoders combining multi-scale convolution, highway networks, and bidirectional recurrence yield more robust text representations than standard RNN encoders, reducing mispronunciation rates. confidence: high relevance: medium - claim_id: post_processing_networks_with_access_to_the_full_decoded_sequence role: supports claim: Post-processing networks with access to the full decoded sequence improve harmonic structure in predicted spectrograms compared to frame-level-only decoding. source: §3.4, §5.1 evidence: Post-processing networks with access to the full decoded sequence improve harmonic structure in predicted spectrograms compared to frame-level-only decoding. confidence: high relevance: medium limitations: - Evaluated on a single internal speaker in a controlled studio environment. No multi-speaker, out-of-domain, or noisy-data experiments are reported. The internal dataset is not released, making direct replication impossible. - Griffin-Lim waveform synthesis introduces audible artefacts that depress MOS scores and prevent fair comparison against systems using neural vocoders. The authors explicitly flag this as a known limitation and describe neural inversion as ongoing work. The reduction factor r is fixed at inference; the paper does not explore adaptive or learned stopping. The model still requires clean text-normalised input; robustness to raw text (numbers, abbreviations, punctuation) is handled by a rule-based preprocessing step rather than learned normalisation. caveats: [] - id: '1712.05884' published_date: "2017-12-16" entry_date: '2026-07-30' year: 2017 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant current_role: foundational method_family: - transformer_encoder_decoder_tts claims: - claim_id: a_compact_low_level_acoustic_intermediate_representation_can_bridge_text role: supports claim: A compact low-level acoustic intermediate representation can bridge text encoding and neural vocoder synthesis without requiring hand-crafted linguistic features, enabling fully end-to-end neural TTS at human-quality levels. source: §2.1, Table 1 evidence: A compact low-level acoustic intermediate representation can bridge text encoding and neural vocoder synthesis without requiring hand-crafted linguistic features, enabling fully end-to-end neural TTS at human-quality levels. confidence: high relevance: low - claim_id: location_sensitive_attention_which_incorporates_cumulative_attention_weights_as_a role: supports claim: Location-sensitive attention, which incorporates cumulative attention weights as a conditioning signal, reduces failure modes such as repetition and omission compared to standard additive attention in autoregressive TTS decoders. source: §2.2 evidence: Location-sensitive attention, which incorporates cumulative attention weights as a conditioning signal, reduces failure modes such as repetition and omission compared to standard additive attention in autoregressive TTS decoders. confidence: high relevance: low - claim_id: a_pre_net_information_bottleneck_in_the_autoregressive_decoder_is role: supports claim: A pre-net information bottleneck in the autoregressive decoder is essential for stable attention alignment during training. source: §2.2 evidence: A pre-net information bottleneck in the autoregressive decoder is essential for stable attention alignment during training. confidence: high relevance: medium - claim_id: training_the_vocoder_on_predicted_rather_than_ground_truth_intermediate role: supports claim: Training the vocoder on predicted rather than ground-truth intermediate features is necessary because predicted features are systematically oversmoothed; vocoders trained on clean features degrade when exposed to predicted inputs. source: §3.3.1, Table 2 evidence: Training the vocoder on predicted rather than ground-truth intermediate features is necessary because predicted features are systematically oversmoothed; vocoders trained on clean features degrade when exposed to predicted inputs. confidence: high relevance: low - claim_id: neural_vocoders_conditioned_on_compact_mel_spectrograms_can_operate_with role: supports claim: Neural vocoders conditioned on compact mel spectrograms can operate with substantially smaller receptive fields than those conditioned on linguistic features, enabling significant architecture simplification without quality loss. source: §3.3.4, Table 4 evidence: Neural vocoders conditioned on compact mel spectrograms can operate with substantially smaller receptive fields than those conditioned on linguistic features, enabling significant architecture simplification without quality loss. confidence: high relevance: medium limitations: - All experiments use a single proprietary speaker and an internal dataset. The paper provides no evidence of generalisation to multiple speakers, different languages, or recording conditions, and no training or evaluation data is publicly released, limiting independent reproducibility. - 'Prosody remains imperfect: 23 of 100 test sentences are rated as containing unnatural prosody (wrong emphasis, unnatural pitch), and occasional mispronunciations are identified as the main gap between the system and human speech. The paper''s authors explicitly identify prosody modeling as the primary remaining challenge.' - 'The two-stage training setup, while producing high quality, introduces a train/inference mismatch that the ablations expose: the vocoder trained on predicted spectrograms is specifically tuned to the oversmoothed distribution of the encoder-decoder output. Any change to the first stage (retraining, fine-tuning) requires retraining the vocoder independently. Joint end-to-end training is left as future work.' - Real-time synthesis is not addressed; WaveNet inference was known to be slow at the time of publication. caveats: [] - id: '2006.04558' published_date: "2020-06-08" entry_date: '2026-07-30' year: 2020 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - acceleration_evidence current_role: influential method_family: - transformer_encoder_decoder_tts claims: - claim_id: explicit_variance_conditioning_on_pitch_energy_and_duration_in_non role: supports claim: Explicit variance conditioning on pitch, energy, and duration in non-autoregressive TTS reduces the information gap between text and speech, enabling quality matching or surpassing autoregressive models without autoregressive inference. source: §2.2, §3.2.1, Table 1 evidence: Explicit variance conditioning on pitch, energy, and duration in non-autoregressive TTS reduces the information gap between text and speech, enabling quality matching or surpassing autoregressive models without autoregressive inference. confidence: high relevance: low - claim_id: phoneme_durations_derived_from_forced_alignment_are_substantially_more_accurate role: supports claim: Phoneme durations derived from forced alignment are substantially more accurate than those extracted from autoregressive teacher attention maps, and this accuracy difference directly improves output voice quality. source: §3.2.2, Table 5 evidence: Phoneme durations derived from forced alignment are substantially more accurate than those extracted from autoregressive teacher attention maps, and this accuracy difference directly improves output voice quality. confidence: high relevance: medium - claim_id: modeling_pitch_in_the_frequency_domain_via_continuous_wavelet_transform role: supports claim: Modeling pitch in the frequency domain via continuous wavelet transform produces more natural pitch distributions in synthesized speech than direct time-domain F0 regression. source: §2.3, §3.2.3, Table 3 evidence: Modeling pitch in the frequency domain via continuous wavelet transform produces more natural pitch distributions in synthesized speech than direct time-domain F0 regression. confidence: high relevance: medium - claim_id: removing_teacher_student_distillation_from_non_autoregressive_tts_training_can role: supports claim: Removing teacher-student distillation from non-autoregressive TTS training can simultaneously simplify the pipeline, reduce training time, and improve output quality relative to the distillation approach. source: §1, §3.2.1, Table 2 evidence: Removing teacher-student distillation from non-autoregressive TTS training can simultaneously simplify the pipeline, reduce training time, and improve output quality relative to the distillation approach. confidence: high relevance: low - claim_id: end_to_end_parallel_text_to_waveform_generation_is_technically role: supports claim: End-to-end parallel text-to-waveform generation is technically feasible but more sensitive to variance conditioning than mel-spectrogram-based acoustic models, particularly in the pitch dimension. source: §2.4, §3.2.3, Table 6 evidence: End-to-end parallel text-to-waveform generation is technically feasible but more sensitive to variance conditioning than mel-spectrogram-based acoustic models, particularly in the pitch dimension. confidence: high relevance: medium limitations: - All experiments use a single studio-quality English speaker (LJSpeech). Generalisation to multi-speaker, emotional, noisy, or cross-lingual conditions is untested. The paper does not include speaker similarity metrics or speaker-conditioned variants. - The variance adaptor relies on an external forced alignment tool (MFA) and pitch extraction (PyWorldVocoder) at training time; these are not learned end-to-end, which limits the system from being fully self-contained. The authors acknowledge this and note future work toward eliminating external alignment tools. - FastSpeech 2s requires the mel-spectrogram decoder during training even though it is discarded at inference. This coupling adds training complexity and means the waveform decoder benefits from a pre-trained mel-spectrogram branch, creating a two-stage dependency that partially reintroduces the pipeline complexity the paper otherwise avoids. - The CMOS evaluation protocol is used for ablation comparisons rather than the more interpretable absolute MOS, which makes it harder to assess the magnitude of individual component contributions in absolute terms. caveats: [] - id: '2105.06337' published_date: "2021-05-13" entry_date: '2026-07-30' year: 2021 venue: arXiv task: - TTS architecture: - diffusion - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - acceleration_evidence - evaluation_caution current_role: influential method_family: - diffusion_augmented_acoustic_decoders - transformer_encoder_decoder_tts claims: - claim_id: diffusion_based_acoustic_feature_generators_can_match_autoregressive_tts_naturalness role: supports claim: Diffusion-based acoustic feature generators can match autoregressive TTS naturalness while enabling flexible inference-time speed-quality trade-offs not available in single-pass models. source: §4.1, Table 2 evidence: Diffusion-based acoustic feature generators can match autoregressive TTS naturalness while enabling flexible inference-time speed-quality trade-offs not available in single-pass models. confidence: high relevance: low - claim_id: initialising_reverse_diffusion_from_a_text_conditioned_noise_distribution_rather role: supports claim: Initialising reverse diffusion from a text-conditioned noise distribution rather than standard Gaussian substantially reduces the number of steps required for high-quality synthesis. source: §3.1, Table 1 evidence: Initialising reverse diffusion from a text-conditioned noise distribution rather than standard Gaussian substantially reduces the number of steps required for high-quality synthesis. confidence: high relevance: low - claim_id: diffusion_models_can_achieve_higher_data_log_likelihood_on_mel role: supports claim: Diffusion models can achieve higher data log-likelihood on mel-spectrograms than normalising-flow models with larger decoder capacity explicitly trained for maximum likelihood. source: §4.2, Table 2 evidence: Diffusion models can achieve higher data log-likelihood on mel-spectrograms than normalising-flow models with larger decoder capacity explicitly trained for maximum likelihood. confidence: high relevance: low - claim_id: subjective_quality_in_diffusion_based_mel_spectrogram_synthesis_improves_diminishingly role: supports claim: Subjective quality in diffusion-based mel-spectrogram synthesis improves diminishingly with reverse-diffusion step count, with most quality gain recovered by 10 steps rather than 1000. source: §4.1, Table 2 evidence: Subjective quality in diffusion-based mel-spectrogram synthesis improves diminishingly with reverse-diffusion step count, with most quality gain recovered by 10 steps rather than 1000. confidence: high relevance: low limitations: - Evaluation is restricted to a single-speaker English dataset (LJSpeech); no multi-speaker, zero-shot, or multilingual capability is demonstrated, leaving generalisation of the diffusion framework to diverse speakers untested. - Training requires approximately 1.7 million iterations on a single GPU (NVIDIA RTX 2080 Ti), and slow convergence of the diffusion loss is noted as a necessary condition for quality. The paper does not report total training time or wall-clock comparisons with baselines. - The end-to-end variant (replacing the mel-spectrogram output with raw waveform via a WaveGrad decoder) does not reach the quality of the two-stage system and is excluded from the main listening test, leaving the end-to-end direction as a preliminary result. - The noise schedule is a simple linear function of time; the paper acknowledges that more principled schedule design and loss weighting are open questions that could improve sample quality and training efficiency. caveats: [] - id: '2106.15561' published_date: "2021-06-29" entry_date: '2026-07-30' year: 2021 venue: arXiv task: - TTS architecture: - autoregressive-LM - flow-matching - diffusion - GAN - VAE - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence - infrastructure current_role: influential method_family: - autoregressive_token_decoders - flow_matching_acoustic_decoders - diffusion_augmented_acoustic_decoders - gan_augmented_encoder_decoder_systems - vae_latent_encoder_decoder_systems - transformer_encoder_decoder_tts claims: - claim_id: the_transition_from_attention_based_alignment_to_explicit_duration_prediction role: supports claim: The transition from attention-based alignment to explicit duration prediction in non-autoregressive acoustic models eliminates word skipping and repeating artefacts while enabling parallel mel-spectrogram generation. source: §3.4, Table 11 evidence: The transition from attention-based alignment to explicit duration prediction in non-autoregressive acoustic models eliminates word skipping and repeating artefacts while enabling parallel mel-spectrogram generation. confidence: high relevance: medium - claim_id: modelling_variation_information_prosody_style_speaker_at_multiple_granularities_from role: supports claim: Modelling variation information (prosody, style, speaker) at multiple granularities from frame to utterance level improves expressiveness while fine-grained control remains difficult when relying on implicit latent representations. source: §3.5.1, §3.5.3 evidence: Modelling variation information (prosody, style, speaker) at multiple granularities from frame to utterance level improves expressiveness while fine-grained control remains difficult when relying on implicit latent representations. confidence: high relevance: medium - claim_id: diffusion_based_vocoders_achieve_high_perceptual_quality_but_suffer_from role: supports claim: Diffusion-based vocoders achieve high perceptual quality but suffer from slow inference due to iterative reverse diffusion, motivating step-reduction methods. source: §2.4, Table 6 evidence: Diffusion-based vocoders achieve high perceptual quality but suffer from slow inference due to iterative reverse diffusion, motivating step-reduction methods. confidence: high relevance: low - claim_id: zero_shot_speaker_adaptation_that_relies_solely_on_a_speaker role: supports claim: Zero-shot speaker adaptation that relies solely on a speaker encoder without any fine-tuning produces noticeably lower voice quality than few-shot adaptation, particularly for speakers distant from the training distribution. source: §3.6.2 evidence: Zero-shot speaker adaptation that relies solely on a speaker encoder without any fine-tuning produces noticeably lower voice quality than few-shot adaptation, particularly for speakers distant from the training distribution. confidence: high relevance: medium - claim_id: low_resource_tts_benefits_from_cross_lingual_transfer_because_human role: supports claim: Low-resource TTS benefits from cross-lingual transfer because human languages share vocal organs and phonetic structures, though phoneme set mismatches require explicit bridging. source: §3.3 evidence: Low-resource TTS benefits from cross-lingual transfer because human languages share vocal organs and phonetic structures, though phoneme set mismatches require explicit bridging. confidence: high relevance: low limitations: - 'The coverage horizon is mid-2021, which means the survey predates several paradigm shifts: neural codec-based discrete speech tokenisation, large language model-based TTS (VALL-E, NaturalSpeech 2), flow-matching acoustic models, and the instruction-conditioned and zero-shot capabilities that came with LLM-scale training. The survey''s taxonomy (acoustic model + vocoder pipeline) is also less applicable to fully codec-native systems where this separation dissolves.' - The survey focuses on English and Mandarin and, while noting multilingual coverage, does not deeply address the orthographic diversity or tonal complexity of the majority of the world's languages. Evaluation methodology is discussed mainly by cataloguing metrics rather than analysing their reliability or mutual disagreement, which limits the survey's utility for assessing evaluation practices. - 'Open questions identified include: better variation information modeling that reconciles controllability and expressiveness, casual and spontaneous speech synthesis, parameter-efficient adaptation at scale, and energy-efficient training and inference.' caveats: [] - id: 2025.coling-main.352 published_date: "2025-01-19" entry_date: '2026-07-30' year: 2025 venue: COLING task: - TTS architecture: - diffusion - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence - evaluation_caution current_role: active_evidence method_family: - diffusion_augmented_acoustic_decoders - transformer_encoder_decoder_tts claims: - claim_id: applying_diffusion_based_classifier_free_guidance_to_low_dimensional_prosodic role: supports claim: Applying diffusion-based classifier-free guidance to low-dimensional prosodic features (pitch, energy, duration) rather than the full Mel-spectrogram achieves faster inference than Mel-diffusion baselines while retaining prosodic diversity benefits over regression-based models. source: §3.2, Table 1 evidence: Applying diffusion-based classifier-free guidance to low-dimensional prosodic features (pitch, energy, duration) rather than the full Mel-spectrogram achieves faster inference than Mel-diffusion baselines while retaining prosodic diversity benefits over regression-based models. confidence: high relevance: low - claim_id: hierarchical_conditioning_combining_coarse_grained_implicit_style_tokens_with_fine role: supports claim: Hierarchical conditioning combining coarse-grained implicit style tokens with fine-grained explicit prosodic diffusion outperforms both purely regression-based and discriminator-constrained diffusion baselines on naturalness and prosodic distribution accuracy. source: §3.2, Table 1 evidence: Hierarchical conditioning combining coarse-grained implicit style tokens with fine-grained explicit prosodic diffusion outperforms both purely regression-based and discriminator-constrained diffusion baselines on naturalness and prosodic distribution accuracy. confidence: high relevance: low - claim_id: classifier_free_guidance_scale_controls_a_trade_off_between_prosodic role: complicates claim: Classifier-free guidance scale controls a trade-off between prosodic diversity and naturalness quality in diffusion-based prosody prediction, with distortion artefacts emerging at high guiding scales. source: §3.3, Table 2 evidence: Classifier-free guidance scale controls a trade-off between prosodic diversity and naturalness quality in diffusion-based prosody prediction, with distortion artefacts emerging at high guiding scales. confidence: high relevance: low - claim_id: dynamic_thresholding_applied_to_cfg_noise_outputs_effectively_mitigates_phoneme role: supports claim: Dynamic thresholding applied to CFG noise outputs effectively mitigates phoneme distortion caused by excessive guiding scales in prosodic diffusion models. source: §2.2, §3.3 evidence: Dynamic thresholding applied to CFG noise outputs effectively mitigates phoneme distortion caused by excessive guiding scales in prosodic diffusion models. confidence: high relevance: low - claim_id: gst_based_implicit_style_conditioning_enables_meaningful_prosodic_transfer_across role: supports claim: GST-based implicit style conditioning enables meaningful prosodic transfer across speakers, outperforming both regression-based style transfer and discriminator-constrained diffusion in subjective preference evaluations. source: §3.4, Table 3 evidence: GST-based implicit style conditioning enables meaningful prosodic transfer across speakers, outperforming both regression-based style transfer and discriminator-constrained diffusion in subjective preference evaluations. confidence: high relevance: low limitations: - Speaker timbre and prosody are not disentangled — the model can transfer prosodic style but cannot fully separate it from speaker identity. The GST tokens show partial overlap in t-SNE visualizations, indicating shared prosodic modes and incomplete independence. The evaluation is conducted on a private Mandarin Chinese dataset (9 male speakers from similar genres), limiting generalization claims across languages, genders, or more varied speaking styles. The 200-step diffusion process at inference is still far slower than FastSpeech2, and no acceleration scheme (consistency models, flow-matching) is explored. Whether the CFG approach generalises to cross-lingual or highly emotional speech remains untested. caveats: [] - id: 2025.coling-main.518 published_date: "2025-01-19" entry_date: '2026-07-30' year: 2025 venue: COLING task: - TTS architecture: - flow-matching - hybrid relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - flow_matching_acoustic_decoders - hybrid_acoustic_generation_pipelines claims: - claim_id: applying_conditional_flow_matching_to_a_self_supervised_prosody_latent role: supports claim: Applying conditional flow matching to a self-supervised prosody latent space rather than to full acoustic features enables diverse prosody generation at inference without requiring a reference utterance. source: §2.3, §3.3 evidence: Applying conditional flow matching to a self-supervised prosody latent space rather than to full acoustic features enables diverse prosody generation at inference without requiring a reference utterance. confidence: high relevance: low - claim_id: self_supervised_speech_representations_wavlm_provide_a_more_effective_prosody role: supports claim: Self-supervised speech representations (WavLM) provide a more effective prosody conditioning signal for TTS than conventional pitch and energy predictors, as shown by ablation. source: §3.4, Table 3 evidence: Self-supervised speech representations (WavLM) provide a more effective prosody conditioning signal for TTS than conventional pitch and energy predictors, as shown by ablation. confidence: high relevance: low - claim_id: flow_matching_in_a_prosody_latent_space_achieves_comparable_quality role: supports claim: Flow matching in a prosody latent space achieves comparable quality to diffusion-based prosody modeling with substantially lower computational cost. source: §3.4, Table 3 evidence: Flow matching in a prosody latent space achieves comparable quality to diffusion-based prosody modeling with substantially lower computational cost. confidence: high relevance: low - claim_id: a_small_number_of_flow_matching_function_evaluations_n_1 role: supports claim: A small number of flow matching function evaluations (n=1) is sufficient to match or exceed legacy TTS baselines on MOS and WER, confirming the sample efficiency of flow matching for prosody. source: §3.3, Table 2 evidence: A small number of flow matching function evaluations (n=1) is sufficient to match or exceed legacy TTS baselines on MOS and WER, confirming the sample efficiency of flow matching for prosody. confidence: high relevance: low limitations: - The model is validated only on single-speaker LJSpeech; extension to multi-speaker and zero-shot settings is explicitly acknowledged as future work. The model architecture size is not reported. WavLM parameters are frozen throughout training, which may limit adaptation to unusual prosody distributions. The comparison set does not include the most recent flow matching TTS systems (Voicebox, Matcha-TTS, E2 TTS) — only legacy baselines (FastSpeech 2, VITS, StyleTTS 2) and one diffusion model (DiffProsody). The absence of speaker diversity means the prosody variability shown may primarily reflect intra-speaker diversity of LJSpeech rather than generalizable prosodic modeling. caveats: [] - id: iclr-2025-hQvX9MBowC published_date: "2025-04-24" entry_date: '2026-07-30' year: 2025 venue: ICLR task: - TTS architecture: - diffusion - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: influential method_family: - diffusion_augmented_acoustic_decoders - transformer_encoder_decoder_tts claims: - claim_id: diffusion_transformer_backbones_are_better_suited_to_tts_than_u role: supports claim: Diffusion Transformer backbones are better suited to TTS than U-Net backbones once domain-specific conditioning factors (phonemes, durations) are removed. source: §5.2, Table 4 evidence: Under matched training conditions, replacing the DiT backbone with a U-Net (and a U-Net variant without down/up-sampling) increases WER from 2.93 to 3.7 and drops SIM-r from 0.588 to 0.389 on the English cross-sentence task. confidence: high relevance: low - claim_id: predicting_total_target_length_and_generating_variable_length_sequences_outperforms role: supports claim: Predicting total target length and generating variable-length sequences outperforms fixed-length generation with padding in diffusion-based TTS. source: §5.2, Table 5 evidence: Fixed-length modeling with padding reaches WER 6.81-8.89, while a learned speech length predictor with variable-length generation reaches WER 5.36-5.58 under otherwise identical settings. confidence: high relevance: low - claim_id: aligning_text_and_speech_latent_representations_improves_cross_attention_conditioned role: supports claim: Aligning text and speech latent representations improves cross-attention-conditioned generation quality, independent of model or training-data scale. source: §5.2, Tables 6-7 evidence: A speech codec fine-tuned with an auxiliary language-modeling loss against a frozen text encoder (Mel-VAE++) improves WER/SIM over the unaligned codec regardless of which text encoder (ByT5 or SpeechT5) is paired with it, and a jointly text-speech-trained text encoder (SpeechT5, 85M params) outperforms a larger text-only encoder (ByT5-base, 415M params) trained on more data. confidence: high relevance: medium - claim_id: removing_domain_specific_alignment_factors_from_ldm_based_tts_narrows role: complicates claim: Removing domain-specific alignment factors from LDM-based TTS narrows but does not eliminate the gap to phoneme-duration-based systems in speaker similarity. source: §5.1, Table 2 evidence: DiTTo-en-XL reaches SIM-r 0.6554 on the cross-sentence task, below Voicebox's reported 0.681 (a phoneme/duration-based non-autoregressive model), even though DiTTo-en-XL is faster and matches or exceeds Voicebox on WER. confidence: high relevance: low - claim_id: codec_compression_ratio_not_codec_reconstruction_quality_alone_determines_suitability role: complicates claim: Codec compression ratio, not codec-reconstruction quality alone, determines suitability as a diffusion target for variable-length TTS. source: §5.2, Table 7 evidence: DAC achieves higher PESQ and ViSQOL codec-reconstruction scores than Mel-VAE, but its 7-8x longer latent sequences make training and inference substantially less efficient and degrade end-to-end WER/SIM relative to the more compressed but lower-fidelity Mel-VAE. confidence: high relevance: low limitations: - Code and pretrained weights are not released at publication (only demo samples), and most baseline comparisons (Voicebox, VALL-E, NaturalSpeech 2/3) use numbers copied from the original papers' reported results rather than reproduced under DiTTo's own evaluation pipeline, limiting independent verification of head-to-head rankings. - The speaker-similarity gap to phoneme-duration-based systems like Voicebox persists even at the largest model scale tested, suggesting that removing domain-specific factors trades off some speaker-identity preservation for simplicity and speed. The paper also does not explore natural-language instruction following or fine-grained prosody control, both noted as future directions rather than addressed in this work. Multilingual results are reported on only 100 held-out examples per language, which is a narrow evaluation slice given nine languages with very different phonological properties. caveats: [] - id: 2025.naacl-long.591 published_date: "2025-04-29" entry_date: '2026-07-30' year: 2025 venue: NAACL task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - evaluation_caution current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: monotonic_alignment_can_be_learned_end_to_end_as_a role: supports claim: Monotonic alignment can be learned end-to-end as a latent property of an encoder-decoder TTS model via backpropagation, without requiring forced alignments or dynamic programming during training. source: §3.3, §3.4 evidence: VAT's alignment layer learns continuous alignment positions through interpolated relative position biases (IRPBs); alignment trajectories emerge from joint training with no external supervision, and generalise to utterances far longer than the training distribution. confidence: high relevance: high - claim_id: augmenting_cross_attention_with_a_learned_monotonic_alignment_position_enables role: supports claim: Augmenting cross-attention with a learned monotonic alignment position enables unbounded length generalisation in encoder-decoder TTS without degrading naturalness relative to an unmodified Transformer baseline. source: §5.1, §5.2, §5.3, Table 1 evidence: VAT achieves near-zero CER on inputs up to 1500 characters (~90 seconds) despite training only on utterances up to 9.6 seconds, while matching the T5 baseline in side-by-side naturalness evaluations (SxS -0.06 ± 0.14 on Lessac, 0.01 ± 0.14 on LibriTTS). confidence: high relevance: high - claim_id: standard_mos_evaluations_are_insufficient_to_surface_robustness_failures_in role: complicates claim: Standard MOS evaluations are insufficient to surface robustness failures in autoregressive TTS because raters cannot detect dropped or repeated words without access to target transcripts. source: §5.1, §5.2, Table 1 evidence: The T5 baseline achieves overlapping MOS with VAT (3.75 vs. 3.68 on Lessac) while producing a CER of 10.2 versus VAT's 3.3; the perceptual quality rating is statistically indistinguishable despite systematic robustness failures. confidence: high relevance: low - claim_id: autoregressive_transformer_tts_without_explicit_alignment_guidance_fails_on_repeated role: complicates claim: Autoregressive Transformer TTS without explicit alignment guidance fails on repeated words even within training sequence length limits. source: §5.4 evidence: The T5 baseline makes errors on 14 of 27 (52%) repeated-word test phrases, including phrases with as few as 2 repetitions of a single word, while VAT makes zero errors across all 27 templates. confidence: high relevance: high - claim_id: duration_based_tts_achieves_better_asr_measured_character_error_rates role: refines claim: Duration-based TTS achieves better ASR-measured character error rates than expressive autoregressive models, but the gain is attributable to hyper-intelligible, monotone synthesis rather than superior text coverage. source: §5.3, Table 1 evidence: NAT achieves CER 3.3 on LibriTTS, below both VAT (4.6) and ground truth (3.6), yet VAT is preferred over NAT in naturalness side-by-sides because NAT's unsupervised duration predictor produces robotic, monotonous prosody. confidence: high relevance: low limitations: - Training speed is affected by the need to compute alignment positions serially during training, imposing a 12-20% slowdown relative to the T5 baseline depending on model scale. All experiments use English and a speaker-conditioned (non-zero-shot) setting; generalisation to other languages and to audio-prompted zero-shot scenarios is untested. Evaluation compares against T5, Tacotron-GMMA, and NAT; no direct comparison with codec LM systems (VALL-E, SPEAR-TTS, MQTTS) is provided, which the paper attributes to incompatible dataset scales and evaluation protocols. Hyper-parameter choices for the alignment layer, IRPB initialization, and maximum distance penalty are reported but not systematically ablated. caveats: [] - id: 2025.americasnlp-1.1 published_date: "2025-05-04" entry_date: '2026-07-30' year: 2025 venue: AmericasNLP 2025 task: - TTS architecture: - transformer-enc-dec - GAN relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: active_evidence method_family: - transformer_encoder_decoder_tts - gan_augmented_encoder_decoder_systems claims: - claim_id: transfer_learning_from_a_closely_related_language_can_enable_intelligible role: supports claim: Transfer learning from a closely related language can enable intelligible TTS for an indigenous language with fewer than 5 hours of training data. source: §4.1, §5.1 evidence: Transfer learning from a closely related language can enable intelligible TTS for an indigenous language with fewer than 5 hours of training data. confidence: high relevance: low - claim_id: subjective_evaluation_by_native_speakers_is_necessary_when_objective_metrics role: supports claim: Subjective evaluation by native speakers is necessary when objective metrics such as PESQ and POLQA cannot be applied due to absent high-quality reference recordings. source: §5.3 evidence: Subjective evaluation by native speakers is necessary when objective metrics such as PESQ and POLQA cannot be applied due to absent high-quality reference recordings. confidence: high relevance: low - claim_id: pronunciation_drift_in_a_native_speaker_living_outside_the_language role: supports claim: Pronunciation drift in a native speaker living outside the language community can cause natural speech to score lower on intelligibility than synthetic speech on standardised evaluation. source: §5.4 evidence: Pronunciation drift in a native speaker living outside the language community can cause natural speech to score lower on intelligibility than synthetic speech on standardised evaluation. confidence: high relevance: low - claim_id: gan_based_vocoders_initialized_from_a_universal_pretrained_model_converge role: supports claim: GAN-based vocoders initialized from a universal pretrained model converge rapidly when the target speaker is similar to the pretraining distribution. source: §4.2, §5.2 evidence: GAN-based vocoders initialized from a universal pretrained model converge rapidly when the target speaker is similar to the pretraining distribution. confidence: high relevance: low limitations: - '- Corpus is only 4h 37m from a single female speaker, limiting prosodic and phonetic diversity and voice coverage. - Transfer learning from Spanish may introduce Spanish phonotactic biases that are not present in Shipibo-Konibo. - Evaluation relied entirely on subjective metrics (no PESQ/POLQA due to lack of reference data); subjectivity and evaluator bias are acknowledged. - Two writing conventions for Shipibo-Konibo exist; the 2015 standard was used, limiting applicability in communities using older orthographies. - The speaker''s extended residence in Lima introduced pronunciation drift that complicates the natural vs. synthetic comparison. - The model has not been tested on adaptation to other Panoan or Amazonian languages yet, though the framework is intended to generalize.' caveats: [] - id: '2507.04598' published_date: "2025-07-07" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: hierarchical_dependency_aware_emotion_prediction_yields_better_emotional_naturalness_and role: supports claim: Hierarchical, dependency-aware emotion prediction yields better emotional naturalness and intelligibility than treating prosodic granularities independently. source: §5.1.1, Table 1 evidence: VA (Multi-Step) achieves MUSHRA naturalness 62.2 vs. 57.5 (single-step VA) with ground-truth ED, and WER 2.45 vs. 4.61 with predicted ED on LibriTTS-R. confidence: high relevance: medium - claim_id: multi_level_emotion_intensity_control_when_implemented_at_the_phoneme role: supports claim: Multi-level emotion intensity control, when implemented at the phoneme and word levels, enables fine-grained and quantifiable manipulation of prosodic features consistent with perceptual expectations. source: §5.2, Table 4, Figure 6 evidence: BWS controllability tests show the proposed model more consistently associates low intensity with least-expressive and high intensity with most-expressive ratings across all five emotions compared to MsEmoTTS, and prosodic trend analysis (duration, pitch mean/std, energy) confirms expected acoustic correlates at each level. confidence: high relevance: medium - claim_id: sequential_multi_step_prediction_across_hierarchical_levels_introduces_error_accumulation role: complicates claim: Sequential multi-step prediction across hierarchical levels introduces error accumulation that can degrade pitch and duration alignment even when overall naturalness improves. source: §5.1.2, Table 2 evidence: In the VA setting, multi-step prediction does not outperform single-step on pitch distortion or frame disturbance metrics, attributed to cascaded prediction error and increased sensitivity from joint training with ED difference loss. confidence: high relevance: medium - claim_id: the_gap_between_ground_truth_and_text_predicted_emotion_distributions role: refines claim: The gap between ground-truth and text-predicted emotion distributions at the word level is smaller than at the phoneme level, suggesting that phoneme-level emotion is harder to infer from text. source: §5.1.3, Table 3 evidence: Table 3 shows mean absolute ED differences are lower for words than phonemes in the multi-step (Predicted) condition, and the authors interpret this as the model prioritizing cross-segment dependencies over precise ED matching. confidence: high relevance: medium limitations: - The system is evaluated exclusively on English data, and the authors identify extension to additional languages as future work. Both training datasets (LibriTTS-R, ESD) are relatively clean, and the method's robustness in noisy or spontaneous conditions is untested. The MsEmoTTS baseline is re-implemented within the FastSpeech2 framework rather than evaluated in its original form, which introduces a potential confound in the emotion editing comparison. The external module's claim of compatibility with arbitrary TTS systems is not verified against any system other than FastSpeech2. Model size and computational cost are not reported. caveats: [] - id: 2025.conll-1.9 published_date: "2025-07-31" entry_date: '2026-07-30' year: 2025 venue: CoNLL task: - TTS - evaluation architecture: [] relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: [] claims: - claim_id: naturalness_ratings_do_not_fully_reflect_whether_tts_prosody_is role: complicates claim: Naturalness ratings do not fully reflect whether TTS prosody is linguistically appropriate. source: §5.3, Figure 3 evidence: Syntactic Sensitivity Score precision and recall diverge from the MOS ranking across Tacotron2, SpeechT5, and Parler-TTS; specifically, recall does not follow MOS order, revealing that missed boundary errors have less impact on perceived naturalness than spurious boundary errors — a dimension MOS does not capture independently. confidence: high relevance: low - claim_id: punctuation_marks_are_the_dominant_surface_cue_for_intonational_boundary role: supports claim: Punctuation marks are the dominant surface cue for intonational boundary placement in TTS systems, overriding syntactic and semantic information in ambiguous contexts. source: §4.4, §5.3 evidence: All three systems place boundaries reliably only when commas are present; without comma cues in garden path and attachment ambiguity sentences, systems default to the statistically most frequent pattern regardless of the intended structure, and semantic bias in prepositional phrase attachment has no measurable effect on boundary placement. confidence: high relevance: low - claim_id: transformer_based_tts_architectures_encode_partial_clause_boundary_information_for role: supports claim: Transformer-based TTS architectures encode partial clause boundary information for prosody that LSTM-based systems do not. source: §6.1, Figure 4 evidence: LASSO regression selects `is_clause_boundary` as a significant predictor of pause duration for SpeechT5 and Parler-TTS but not for Tacotron2, which relies more on token position and length features. confidence: high relevance: low - claim_id: increasing_tts_training_exposure_to_syntactically_diverse_speech_can_improve role: refines claim: Increasing TTS training exposure to syntactically diverse speech can improve prosodic alignment with syntactic structure for structural cues, but not for semantic disambiguation cues. source: §7.3, Figure 5 evidence: Fine-tuning Parler-TTS on Jenny corpus prepositional phrase data produces more differentiated pause patterns correlated with syntactic function of ambiguous words; fine-tuning on synthetic semantic-bias data increases pause duration generally but does not teach the model to distinguish high from low attachment based on semantic context. confidence: high relevance: low limitations: - The study measures intonational boundaries through duration proxies only (pause insertion and pre-boundary lengthening), omitting pitch contour and intensity changes that also contribute to boundary perception. The ToBI framework identifies multiple boundary strength levels that this methodology cannot distinguish. - Evaluation is limited to English and to three specific TTS systems trained on audiobook speech, which under-represents prosodically disambiguating speech patterns relative to conversational speech. - The Parler-TTS model supports natural-language voice conditioning, but only a single fixed voice description was used. How voice conditioning interacts with syntactic sensitivity is unexplored. - 'The fine-tuning results are diagnostic rather than prescriptive: datasets are small (~6 hours), and the synthetic data experiment suggests that semantic disambiguation remains out of reach even with targeted exposure.' caveats: [] - id: '2508.11273' published_date: "2025-08-15" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: discretizing_self_supervised_speech_features_via_k_means_produces_more role: supports claim: Discretizing self-supervised speech features via k-means produces more stable prosodic control signals than retaining continuous SSL representations in encoder-decoder TTS. source: §5.6, Table 1 evidence: Discretizing self-supervised speech features via k-means produces more stable prosodic control signals than retaining continuous SSL representations in encoder-decoder TTS. confidence: high relevance: high - claim_id: combining_continuous_spherical_emotion_vectors_with_discrete_ssl_prosody_tokens role: supports claim: Combining continuous spherical emotion vectors with discrete SSL prosody tokens improves both naturalness and intelligibility compared to spherical emotion vectors alone. source: §5.1, §5.3, Tables 1–2 evidence: Combining continuous spherical emotion vectors with discrete SSL prosody tokens improves both naturalness and intelligibility compared to spherical emotion vectors alone. confidence: high relevance: medium - claim_id: speaker_independent_prosody_conditioning_via_ssl_tokens_can_generalize_across role: supports claim: Speaker-independent prosody conditioning via SSL tokens can generalize across reference speakers with minimal degradation, enabling robust cross-speaker emotion transfer. source: §5.6, Table 1 evidence: Speaker-independent prosody conditioning via SSL tokens can generalize across reference speakers with minimal degradation, enabling robust cross-speaker emotion transfer. confidence: high relevance: medium - claim_id: semantic_text_encoders_contribute_to_emotional_and_prosodic_consistency_in role: supports claim: Semantic text encoders contribute to emotional and prosodic consistency in multilingual TTS even when they do not serve as direct decoder inputs. source: §5.6, Table 1 evidence: Semantic text encoders contribute to emotional and prosodic consistency in multilingual TTS even when they do not serve as direct decoder inputs. confidence: high relevance: low limitations: - '- Evaluations are limited to single-speaker datasets in two languages, making it unclear whether EmoSSLSphere generalises to multi-speaker, low-resource, or unseen-language scenarios. - Subjective listener panels are small, and emotional authenticity is assessed primarily via AVD RMSE as a proxy rather than direct perceptual emotion ratings. - Speaker similarity (SPK-SIM) is not evaluated, making it hard to quantify speaker fidelity claims. - Cross-speaker emotion transfer is described but not formally evaluated; inference always uses same-speaker reference audio. - Separate per-language encoder instances do not scale to many-language settings without significant parameter overhead. - Integration with semi-supervised training (EmoSphere++) and extension to zero-shot speaker scenarios are listed as future work.' caveats: [] - id: '2508.12001' published_date: "2025-08-16" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - VAE - GAN - hybrid relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - vae_latent_encoder_decoder_systems - gan_augmented_encoder_decoder_systems - hybrid_acoustic_generation_pipelines claims: - claim_id: applying_mixture_of_experts_routing_to_the_duration_predictor_of role: supports claim: Applying Mixture-of-Experts routing to the duration predictor of a non-autoregressive TTS system produces phoneme duration distributions that more closely match ground-truth speaker-specific prosodic variation than deterministic or stochastic single-path predictors. source: §IV-C, Table III evidence: Applying Mixture-of-Experts routing to the duration predictor of a non-autoregressive TTS system produces phoneme duration distributions that more closely match ground-truth speaker-specific prosodic variation than deterministic or stochastic single-path predictors. confidence: high relevance: high - claim_id: improving_duration_prediction_diversity_in_nar_tts_without_upgrading_the role: supports claim: Improving duration prediction diversity in NAR TTS without upgrading the vocoder degrades synthesis quality, because richer prosodic information exceeds the artifact-rejection capacity of standard GAN discriminators. source: §IV-A, Table I evidence: Improving duration prediction diversity in NAR TTS without upgrading the vocoder degrades synthesis quality, because richer prosodic information exceeds the artifact-rejection capacity of standard GAN discriminators. confidence: high relevance: low - claim_id: frequency_domain_and_multi_band_discriminators_combd_and_sbd_are role: supports claim: Frequency-domain and multi-band discriminators (CoMBD and SBD) are more effective than HiFi-GAN's multi-period discriminator at suppressing spectral artifacts when a more expressive duration predictor is used. source: §V-B, Table II evidence: Frequency-domain and multi-band discriminators (CoMBD and SBD) are more effective than HiFi-GAN's multi-period discriminator at suppressing spectral artifacts when a more expressive duration predictor is used. confidence: high relevance: high - claim_id: word_error_rate_is_an_unreliable_proxy_for_prosody_modeling role: supports claim: Word Error Rate is an unreliable proxy for prosody modeling quality in TTS, as simpler prosodic patterns can yield lower WER by reducing ASR system disruption. source: §IV-C, §III evidence: Word Error Rate is an unreliable proxy for prosody modeling quality in TTS, as simpler prosodic patterns can yield lower WER by reducing ASR system disruption. confidence: high relevance: low limitations: - '- The MoE-DP requires the discriminator upgrade to yield any net benefit; neither module alone suffices, which raises questions about robustness when either component is replaced or updated independently. - Evaluation is limited to English datasets; whether MoE-DP''s speaker-specific prosody gains transfer to more typologically diverse languages with different prosodic structures is untested. - The paper notes that current vocoders still struggle under highly diverse prosodic patterns (disharmony components persist even with CoMBD+SBD), pointing to an open challenge for future vocoder designs. - WER is shown to be an unreliable proxy for prosody quality, but the proposed duration-accuracy metric (MFA-based classification) requires ground-truth phoneme duration annotations, limiting its generalizability. - No code or demo links are provided, limiting reproducibility. - Inference RTF on CPU (0.046) is not compared directly against autoregressive or diffusion-based competitors that operate on the same hardware, making efficiency claims difficult to contextualize.' caveats: [] - id: interspeech-2025-1098 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech 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_tts claims: - claim_id: bert_based_prosody_predictors_for_pitch_accent_languages_can_be role: supports claim: BERT-based prosody predictors for pitch-accent languages can be extended to multi-speaker settings through speaker style embedding injection without requiring accent label annotation. source: §2.1, §3.4, Table 2, Table 3 evidence: GST-BERT-TTS integrates averaged GST vectors into BERT token embeddings via a linear adaptor, reducing log f0 MSE from 0.773 (fo-BERT) to 0.266 and raising top-level accent correctness from 47.5% to 65% on Hi-Fi-CAPTAIN. confidence: high relevance: medium - claim_id: speaker_style_embeddings_derived_from_seen_speaker_averages_do_not role: complicates claim: Speaker style embeddings derived from seen-speaker averages do not generalise well to unseen speakers in label-free prosody prediction. source: §4.1 evidence: The authors report that using the GST embedding of an unseen speaker during inference produced flat, monotonous prosody, attributing the failure to insufficient speaker diversity in the training corpus and limited coverage of GST's latent space. confidence: high relevance: medium - claim_id: improvements_in_prosody_prediction_accuracy_and_accent_correctness_do_not role: complicates claim: Improvements in prosody prediction accuracy and accent correctness do not automatically translate into higher overall MOS in multi-speaker TTS. source: §3.4, Figure 3 evidence: GST-BERT-TTS outperforms fo-BERT on MSE and accent correctness, yet MOS scores remain lower than TTS+Accent; the authors attribute this partly to vocoder artefacts on a high-variability multi-speaker corpus and to the fact that MOS conflates naturalness and audio clarity with prosodic correctness. confidence: high relevance: low - claim_id: multi_task_prosody_prediction_covering_fundamental_frequency_energy_and_duration role: supports claim: Multi-task prosody prediction covering fundamental frequency, energy, and duration jointly improves over pitch-only prediction when speaker conditioning is present. source: §3.4, Table 2 evidence: Adding energy and duration prediction to fo-BERT (full params.) had minimal impact on log f0 MSE (0.773 vs. 0.776), whereas GST-BERT (full params.) showed a synergistic improvement over GST-BERT (log f0 only), reducing log f0 MSE from 0.302 to 0.266. confidence: high relevance: medium limitations: - Evaluation uses a proprietary internal Japanese corpus; the accent correctness listening test involves only two speakers. Generalisation of the approach to other pitch-accent languages, larger speaker sets, or publicly available benchmarks is untested. - GST embeddings fail to provide useful conditioning for genuinely unseen speakers, limiting the method's zero-shot applicability. Addressing this may require a larger and more diverse speaker pool or a different style representation strategy. The authors acknowledge a tension between BERT's strength in contextual linguistic modelling and its suitability for constrained, character-level prosodic parameter regression, and identify integration with large language models as a direction requiring future methodological work. caveats: [] - id: interspeech-2025-1122 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - GAN - transformer-enc-dec relevance: low evidence_role: - historical_context current_role: minor method_family: - gan_augmented_encoder_decoder_systems - transformer_encoder_decoder_tts claims: - claim_id: quantisation_aware_training_is_more_effective_than_parameter_reduction_via role: supports claim: Quantisation-aware training is more effective than parameter reduction via channel shrinkage for achieving compact TTS models at equivalent model sizes. source: §3.3.1, Table 1 evidence: Quantisation-aware training is more effective than parameter reduction via channel shrinkage for achieving compact TTS models at equivalent model sizes. confidence: high relevance: low - claim_id: the_vocoder_stage_of_a_tts_pipeline_is_more_sensitive role: supports claim: The vocoder stage of a TTS pipeline is more sensitive to aggressive weight quantisation than the acoustic model, making it a disproportionate source of quality degradation. source: §3.3.1 evidence: The vocoder stage of a TTS pipeline is more sensitive to aggressive weight quantisation than the acoustic model, making it a disproportionate source of quality degradation. confidence: high relevance: low - claim_id: extremely_low_bit_1_2_bit_weight_quantisation_can_preserve role: supports claim: Extremely low-bit (1–2 bit) weight quantisation can preserve intelligible and reasonably natural speech synthesis when applied selectively to convolutional layers. source: §3.3.1, Table 1 evidence: Extremely low-bit (1–2 bit) weight quantisation can preserve intelligible and reasonably natural speech synthesis when applied selectively to convolutional layers. confidence: high relevance: low - claim_id: hardware_aware_packing_schemes_are_necessary_to_realise_the_theoretical role: supports claim: Hardware-aware packing schemes are necessary to realise the theoretical storage savings of sub-byte quantisation on devices that operate in 8-bit units. source: §2.3 evidence: Hardware-aware packing schemes are necessary to realise the theoretical storage savings of sub-byte quantisation on devices that operate in 8-bit units. confidence: high relevance: medium limitations: - All experiments use a single TTS architecture (JETS with convolutional blocks) trained on a single corpus (LibriTTS-R). Whether these findings generalise to transformer-heavy or autoregressive architectures, or to lower-resource languages, is not addressed. - The subjective evaluation uses only 15 raters and 30 utterances, which is at the lower end of statistical power for MOS comparisons. The index distribution is heavily non-uniform (indices 0, 121, 242 — representing all-zero, all-one, all-minus-one blocks — are overrepresented), suggesting that further compression via entropy coding (e.g. Huffman) is feasible but unexplored. Inference speed does not improve relative to the full 32-bit base model because weight reconstruction from indices adds overhead; achieving both compact storage and fast inference simultaneously requires dedicated hardware or kernel-level support that is not demonstrated. caveats: [] - id: interspeech-2025-1334 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: multi_scale_neural_feature_extraction_that_captures_cross_frequency_coupling role: supports claim: Multi-scale neural feature extraction that captures cross-frequency coupling improves iEEG-to-speech intelligibility over single-band or handcrafted acoustic feature approaches. source: §2.1.1, §2.1.2, Table 1 evidence: MiSTR's wavelet encoder (DWT with Daubechies-4) combined with Phase-Amplitude Coupling features achieves Pearson correlation 0.91 and STOI 0.73, compared to 0.72 and 0.61 for a regression baseline relying on simpler acoustic features from the same dataset. confidence: high relevance: medium - claim_id: transformer_based_sequence_decoders_outperform_rnn_and_cnn_architectures_for role: supports claim: Transformer-based sequence decoders outperform RNN and CNN architectures for Mel spectrogram reconstruction from neural signals. source: §2.2.2, §3.3, Table 1 evidence: MiSTR Transformer decoder achieves STOI 0.73 against 0.48 (bLSTM), 0.52 (CNN), 0.56 (3D-CNN), 0.59 (Seq2Seq), and 0.64 (encoder-decoder) on the same iEEG dataset under identical evaluation conditions. confidence: high relevance: medium - claim_id: harmonic_phase_constrained_iterative_phase_reconstruction_reduces_spectral_artifacts_in role: supports claim: Harmonic-phase-constrained iterative phase reconstruction reduces spectral artifacts in neural speech synthesis compared to unconstrained vocoding. source: §2.3, §4, Table 1, Figure 2 evidence: 'IHPR achieves HNR 12.7 dB, over 1.6 dB above the best baseline (encoder-decoder: 11.1 dB), and MiSTR''s spectrograms preserve harmonic structures in high-frequency regions where baselines exhibit blurring and artifact distortions.' confidence: high relevance: low - claim_id: automated_perceptual_quality_estimators_used_as_proxies_for_human_listening role: complicates claim: Automated perceptual quality estimators used as proxies for human listening tests may not provide sufficient validation for clinical or neuroprosthetics applications of neural speech synthesis. source: §3.3, §4 evidence: MiSTR reports perceptual quality solely through MOSA-Net (MOSA-Net score 3.38), explicitly framing it as an alternative to "time-consuming listening tests." No human listener evaluation is conducted, leaving the perceptual validity of the improvements in intelligibility and naturalness unverified. confidence: high relevance: low limitations: - The evaluation is conducted on a single dataset of 10 participants with pharmacoresistant epilepsy implanted with depth electrodes (Dutch, iEEG). All perceptual quality comparisons rely on MOSA-Net rather than human listener tests. No cross-subject generalization to unseen individuals is assessed. - The dataset's clinical and linguistic specificity (Dutch epilepsy patients with implanted electrodes) limits how broadly the results generalize. iEEG-based speech synthesis requires invasive electrode placement, making large-scale data collection and multi-subject generalization substantially more difficult than standard TTS. The paper uses an F0 proxy derived from the neural signal rather than actual acoustic F0, which may limit the fidelity of the prosodic features. Future directions proposed by the authors include end-to-end decoding without intermediate representations and integration of diffusion-based waveform generation. caveats: [] - id: interspeech-2025-1394 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: self_supervised_distillation_with_emotion_specific_inductive_biases_can_learn role: supports claim: Self-supervised distillation with emotion-specific inductive biases can learn speaker-independent emotion embeddings more effectively than GRL-based or VQ-based disentanglement. source: §3.4, Table 1 evidence: DiEmo-TTS surpasses Trans-GRL, Trans-VQ, and Trans-Ort on eMOS across all four emotion categories in subjective evaluation, without requiring explicit speaker labels during emotion encoder training. confidence: high relevance: medium - claim_id: formant_based_speaker_perturbation_is_more_effective_for_disentangling_speaker role: supports claim: Formant-based speaker perturbation is more effective for disentangling speaker identity from emotion than non-targeted noise augmentation in cross-speaker emotion transfer. source: §3.6, Table 2 evidence: Replacing formant perturbation with MUSAN/RIR noise augmentation in the ablation increases WER and degrades SECS, whereas formant perturbation exploits the timbre-formant correlation to distort identity while preserving emotional expression. confidence: high relevance: medium - claim_id: multi_factor_conditioning_via_shared_attention_mechanisms_produces_better_balance role: supports claim: Multi-factor conditioning via shared attention mechanisms produces better balance between speaker fidelity and emotional expressiveness than concatenation conditioning in transformer-based TTS. source: §3.6, Table 2 evidence: Adding the DCT block improves eMOS from 3.89 to 4.07 while keeping sMOS comparable in the ablation; the block applies weight-sharing multi-head attention per style signal and fuses outputs via MLP. confidence: high relevance: low - claim_id: achieving_speaker_independent_emotion_representations_via_self_supervised_methods_still role: complicates claim: Achieving speaker-independent emotion representations via self-supervised methods still depends on labeled auxiliary data for emotion space definition. source: §4, §3.2 evidence: The emotion clustering step requires a WavLM-based emotional attribute predictor fine-tuned on the MSP-Podcast labeled corpus; the authors identify dependence on this predictor as a limitation for generalising to unseen speakers. confidence: high relevance: medium limitations: - Evaluation uses only 2 target speakers (one male, one female from ESD), both trained exclusively on neutral utterances. Generalisation to speakers trained on mixed emotional data or to out-of-domain voices is not assessed. - WER of 16.16% indicates non-trivial intelligibility degradation compared to clean TTS; the source of this degradation (emotion conditioning, model architecture, or dataset characteristics) is not explicitly discussed. The emotional attribute predictor is fine-tuned on MSP-Podcast, a separate labeled corpus, introducing a labeled-data dependency that the authors acknowledge as a target for future unsupervised replacement. Scalability to languages beyond English and to larger multi-emotion multi-speaker datasets remains undemonstrated. caveats: [] - id: interspeech-2025-1494 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: visual_features_extracted_from_video_carry_prosodic_information_that_complements role: supports claim: Visual features extracted from video carry prosodic information that complements text-derived features for pitch and duration prediction in TTS. source: §3.2, Table 2; §3.3, Table 3 evidence: A feedforward network trained solely on Omnivore visual features achieves substantially lower pitch and energy MSE than a mean-predictor baseline on CMD2, and combining visual features with text reduces pitch MSE from 0.43 to 0.39 and duration MSE by 3% relative over text-only PED prediction. confidence: high relevance: low - claim_id: visual_context_conditioning_does_not_uniformly_improve_all_acoustic_dimensions role: complicates claim: Visual context conditioning does not uniformly improve all acoustic dimensions in prosody prediction. source: §3.3, Table 3; §3.4, Table 4 evidence: Adding visual features to the text-based PED predictor degrades energy MSE from 0.50 (text-only) to 0.59 (Text+VF-Omnivore), and energy improvements in the full TTS system are the smallest of the three prosody dimensions (5% relative vs. 33% for pitch and 49% for duration). confidence: high relevance: medium - claim_id: objective_prosody_metrics_are_insufficient_to_verify_perceptual_quality_gains role: complicates claim: Objective prosody metrics are insufficient to verify perceptual quality gains in visually-conditioned TTS systems. source: §3.4, Table 5 evidence: VisualSpeech is evaluated entirely on MCD, Log F0 RMSE, pitch/energy/duration MSE, and STOI/PESQ; no human listening test or MOS study is reported, leaving the perceptual significance of the measured improvements unconfirmed. confidence: high relevance: low - claim_id: cross_attention_fusion_between_visual_and_text_encoder_representations_enables role: supports claim: Cross-attention fusion between visual and text encoder representations enables modality integration in sequence-to-sequence prosody prediction without requiring equal-length sequences. source: §2.3 evidence: The visual-text fusion module addresses the length mismatch between the phoneme sequence and the variable-length visual feature sequence by using text queries attending to visual key-value pairs, with output aligned to the phoneme level for per-phone PED prediction. confidence: high relevance: high limitations: - No human evaluation is conducted. All improvements are measured on objective metrics (MCD, Log F0 RMSE, prosody MSE), and it is unknown whether the observed gains translate to perceptibly more natural or contextually appropriate speech for listeners. - The CMD2 dataset is derived from movie audio which contains residual noise, music, and variable recording conditions despite preprocessing; the paper acknowledges this directly as a limitation of the current study. The approach is tested only on English speech from a movie domain, and generalisability to other languages, read speech, or clean studio recordings is untested. The visual features used (Omnivore, ResNet50) are general-purpose video and image recognition models, not speech-specific; whether domain-adapted visual encoders would yield larger prosody gains is an open question. The paper does not address how VisualSpeech would operate when video is unavailable at inference time, which limits its applicability to scenarios where visual input is always present. caveats: [] - id: interspeech-2025-1940 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - transformer-enc-dec - flow-matching relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts - flow_matching_acoustic_decoders claims: - claim_id: stochastic_prosody_predictors_achieve_naturalness_parity_with_human_recordings_while role: supports claim: Stochastic prosody predictors achieve naturalness parity with human recordings while enabling prosodic diversity that deterministic predictors cannot produce. source: §3.4, Figure 5, Figure 6 evidence: RF at 0.4 temperature shows no statistically significant difference from human naturalness ratings (Kruskal-Wallis, Dunn post-hoc); the deterministic baseline achieves highest naturalness but lowest diversity across 40 Prolific raters on ADEPT. confidence: high relevance: medium - claim_id: for_explicit_prosody_modeling_cascaded_prediction_of_prosodic_features_outperforms role: refines claim: For explicit prosody modeling, cascaded prediction of prosodic features outperforms joint prediction for duration but the ordering of pitch and energy within the cascade has negligible impact. source: §3.3, Table 1 evidence: Table 1 shows joint prediction yields 17% higher duration JS divergence (0.562) vs. cascading (0.481), while pitch-first and energy-first orderings differ by less than 0.005 across all prosodic parameters. confidence: high relevance: medium - claim_id: naturalness_and_prosodic_diversity_are_inversely_correlated_constraining_simultaneous_optimization role: complicates claim: Naturalness and prosodic diversity are inversely correlated, constraining simultaneous optimization of both properties in TTS. source: §3.4, Figure 5, Figure 6 evidence: Subjective ratings show no system achieves both maximal naturalness and maximal diversity; even human speech exhibits this trade-off, with the human baseline scoring highest on diversity but not on naturalness. confidence: high relevance: low - claim_id: sampling_temperature_in_generative_prosody_predictors_enables_effective_runtime_control role: supports claim: Sampling temperature in generative prosody predictors enables effective runtime control over prosodic variability without retraining. source: §3.3, Figure 2, Figure 3 evidence: Pitch contour variance and duration variance increase monotonically with temperature for all stochastic methods (NF, CFM, RF), following a near-exponential relationship that allows a log-linear temperature axis for more intuitive user control. confidence: high relevance: medium limitations: - Experiments are restricted to read speech (LibriTTS), with conversational speech explicitly deferred to future work. Prior work found significant benefits for stochastic duration prediction specifically in conversational scenarios, so the present findings may not generalize to that more demanding setting. The stochastic models do not yet capture the full diversity of human prosodic distributions, with synthetic KDE distributions consistently narrower and more unimodal than human reference distributions from RAVDESS; the authors hypothesize that larger predictor modules could close this gap. caveats: [] - id: interspeech-2025-2189 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts claims: - claim_id: combining_acoustic_context_with_text_conditioning_in_a_masked_prediction role: supports claim: Combining acoustic context with text conditioning in a masked prediction framework produces more accurate prosody prediction than style encoders or emotion representations adapted to the task. source: §4.1, Table 1 evidence: ProMode outperforms StyleTTS2*, Wav2Vec2-SER*, and Emotion2Vec* across all F0 and energy metrics at frame and phoneme level on GigaSpeech Test; since all models share the same decoder, performance differences isolate the encoder contribution. confidence: high relevance: medium - claim_id: self_supervised_representations_trained_for_emotion_recognition_do_not_transfer role: complicates claim: Self-supervised representations trained for emotion recognition do not transfer effectively to prosody prediction, even after full fine-tuning on prosody-labelled data. source: §4.1, Table 1 evidence: Emotion2Vec* and Wav2Vec2-SER* show markedly lower F0 RPA and higher RMSE than StyleTTS2* and ProMode; Emotion2Vec* underperforms Wav2Vec2-SER* despite training on more labeled emotion data, suggesting the SER pre-training introduces a representation bias that hinders prosody regression. confidence: high relevance: medium - claim_id: a_dual_decoder_architecture_with_an_auxiliary_acoustic_only_loss role: supports claim: A dual-decoder architecture with an auxiliary acoustic-only loss prevents the prosody encoder from collapsing onto text context in masked prediction, where removing the loss causes catastrophic degradation. source: §4.3, Table 1 evidence: Ablation removing AOL drops F0 RPA from 43.9% to 25.8% (the largest degradation of any ablation), confirming that without AOL the decoder attends exclusively to text and the prosody encoder's contribution is suppressed. confidence: high relevance: medium - claim_id: task_agnostic_prosody_models_that_predict_f0_independently_can_improve role: supports claim: Task-agnostic prosody models that predict F0 independently can improve both naturalness and prosody preference in downstream TTS systems without requiring joint end-to-end training. source: §4.2, Table 2, §4.2.2 evidence: Replacing FluentSpeech's built-in pitch predictor with ProMode-predicted pitch improves UTMOS from 3.00 to 3.10, WER from 4.41% to 3.99%, and AutoPCP from 2.47 to 2.64; ABX prosody preference is statistically significant over all three baselines. confidence: high relevance: low limitations: - All experiments are conducted on English GigaSpeech (read and spontaneous speech); the authors identify multilingual extension as future work but provide no cross-lingual evidence. ProMode requires ground-truth phoneme durations from a forced aligner during evaluation, which creates a dependency on accurate alignment at inference time. The downstream integration only tests replacement of the pitch predictor within FluentSpeech; whether the benefit holds for other TTS backbones or for energy-conditioned synthesis is unevaluated. The model size is not reported, making compute cost comparisons to baselines unclear. caveats: [] - id: interspeech-2025-2586 published_date: "2025-08-17" entry_date: '2026-07-30' year: 2025 venue: Interspeech task: - TTS architecture: - transformer-enc-dec - GAN relevance: medium evidence_role: - architecture_variant - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts - gan_augmented_encoder_decoder_systems claims: - claim_id: restricting_style_quantization_to_acoustically_informative_voiced_speech_regions_improves role: supports claim: Restricting style quantization to acoustically informative (voiced) speech regions improves both style expressiveness and prosodic accuracy in reference-based TTS. source: §4.4.1, Table 4.3 evidence: On ESD, removing voiced extraction raises RMSE_F0 from 8.27 to 11.48 Hz and WER from 12.64 to 14.06; the full model achieves the best style similarity MOS (3.84) over all baselines. confidence: high relevance: low - claim_id: pairing_style_disentanglement_with_a_complementary_prosody_preserving_loss_stabilises role: supports claim: Pairing style disentanglement with a complementary prosody-preserving loss stabilises training and prevents prosody degradation from aggressive content removal. source: §4.4.2, Table 4.3 evidence: Removing only the SP loss raises pitch error to 9.74 Hz; removing both SD and SP degrades nMOS to 3.66 and WER to 15.38, with the SP-only-removed condition showing worse prosody than the case with no disentanglement losses at all. confidence: high relevance: medium - claim_id: asymmetric_biased_self_attention_in_unvoiced_region_filling_allowing_information role: supports claim: Asymmetric (biased) self-attention in unvoiced region filling, allowing information flow from voiced to unvoiced positions but not the reverse, outperforms symmetric or fully blocked alternatives for prosodic continuity. source: §4.4.3, Table 4.4 evidence: Standard self-attention in the UF module degrades pitch error to 16.38 Hz and F1 v/uv to 0.6668; binary masking partially recovers at 13.19 Hz versus 8.27 Hz for biased attention. confidence: high relevance: medium - claim_id: style_transfer_quality_gains_from_region_specific_quantization_have_been role: complicates claim: Style transfer quality gains from region-specific quantization have been established only within a controlled emotional corpus, leaving open the question of whether the approach generalises to broader speaking styles or modern generative architectures. source: §4.1, Table 4.1 evidence: All baselines are FastSpeech 2 variants evaluated solely on ESD (10 speakers, 5 discrete emotions); no comparison with flow-matching, diffusion, or large-scale systems is provided. confidence: high relevance: medium limitations: - All evaluations are conducted on a single English emotional speech corpus (ESD, 10 speakers, 5 emotions). Baselines are restricted to FastSpeech 2-based systems; no comparison with flow-matching or diffusion TTS is included, and there is no evidence of generalisation to multilingual or out-of-domain speech. - Model size is not reported. The voiced/unvoiced segmentation depends on pre-extracted V/UV flags, introducing a dependency on external pitch tracking that may degrade under noisy or spontaneous speech conditions. Non-parallel style transfer performance, while positive, consistently trails the parallel setting, indicating residual sensitivity to content mismatch even after disentanglement. The rotation trick hyperparameters and UF module depth are fixed without sensitivity analysis. caveats: [] - id: '2508.13028' published_date: "2025-08-18" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: minor method_family: - transformer_encoder_decoder_tts claims: - claim_id: feedback_loss_from_a_sarcasm_classifier_can_be_integrated_into role: supports claim: Feedback loss from a sarcasm classifier can be integrated into TTS training to bias synthesized speech toward detector-recognizable sarcastic prosody. source: §2.2, §4.2, Table 2 evidence: Feedback loss from a sarcasm classifier can be integrated into TTS training to bias synthesized speech toward detector-recognizable sarcastic prosody. confidence: high relevance: low - claim_id: bi_modal_sarcasm_detection_that_combines_acoustic_features_and_text role: supports claim: Bi-modal sarcasm detection that combines acoustic features and text substantially outperforms audio-only detection, suggesting that sarcasm in speech is often semantically encoded and not recoverable from prosody alone. source: §4.1, Table 1 evidence: Bi-modal sarcasm detection that combines acoustic features and text substantially outperforms audio-only detection, suggesting that sarcasm in speech is often semantically encoded and not recoverable from prosody alone. confidence: high relevance: medium - claim_id: two_stage_fine_tuning_from_neutral_read_speech_to_conversational role: supports claim: Two-stage fine-tuning — from neutral read speech to conversational speech and then to target style — provides a viable data strategy for low-resource expressive speech synthesis. source: §2.3, §3.1 evidence: Two-stage fine-tuning — from neutral read speech to conversational speech and then to target style — provides a viable data strategy for low-resource expressive speech synthesis. confidence: high relevance: low - claim_id: subjective_sarcasm_perception_in_listening_tests_is_difficult_to_isolate role: supports claim: Subjective sarcasm perception in listening tests is difficult to isolate from the sarcastic content of the text, creating ambiguity in whether listeners respond to prosody or semantics. source: §5, §4.3 evidence: Subjective sarcasm perception in listening tests is difficult to isolate from the sarcastic content of the text, creating ambiguity in whether listeners respond to prosody or semantics. confidence: high relevance: medium limitations: - 'The evaluation design has a critical circularity: the same detector architecture trained on the same data distribution is used both as the training feedback signal and as the primary objective metric. Improvements in detection score on synthesized outputs are therefore expected by construction and cannot be treated as independent evidence of sarcasm-aware synthesis.' - The paper does not include an ablation that isolates the contribution of the feedback loss from the two-stage fine-tuning; it is therefore unclear which component drives the reported gains. The subjective study is small (13 listeners) and does not report MOS confidence intervals, making statistical significance uncertain. All evaluation stimuli are drawn from a sarcasm corpus, which may prime listener responses. The system has not been compared against more expressive modern TTS models (e.g., flow-matching or diffusion-based systems with style conditioning). Finally, the system is English-only and trained on North American sitcom speech, limiting generalizability to other languages, speakers, or sarcasm conventions. caveats: [] - id: '2508.17031' published_date: "2025-08-23" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - transformer-enc-dec - GAN relevance: medium evidence_role: - architecture_variant - acceleration_evidence - control_evidence current_role: active_evidence method_family: - transformer_encoder_decoder_tts - gan_augmented_encoder_decoder_systems claims: - claim_id: cross_modal_attention_between_phoneme_and_audio_representations_is_more role: supports claim: Cross-modal attention between phoneme and audio representations is more effective than global speaker embeddings for preserving localised prosodic and acoustic context in speech insertion tasks. source: §4.3, Table 3 evidence: Cross-modal attention between phoneme and audio representations is more effective than global speaker embeddings for preserving localised prosodic and acoustic context in speech insertion tasks. confidence: high relevance: medium - claim_id: non_autoregressive_tts_architectures_with_duration_prediction_can_infer_variable role: supports claim: Non-autoregressive TTS architectures with duration prediction can infer variable-length insertion segments without explicit phoneme-level alignment at inference time. source: §3.1, §3.2 evidence: Non-autoregressive TTS architectures with duration prediction can infer variable-length insertion segments without explicit phoneme-level alignment at inference time. confidence: high relevance: low - claim_id: combining_local_and_global_adversarial_losses_with_a_triplet_based role: supports claim: Combining local and global adversarial losses with a triplet-based style matching loss reduces perceptual artefacts in synthesised speech segments that L1 reconstruction loss alone cannot eliminate. source: §3.3, §4.3 evidence: Combining local and global adversarial losses with a triplet-based style matching loss reduces perceptual artefacts in synthesised speech segments that L1 reconstruction loss alone cannot eliminate. confidence: high relevance: medium - claim_id: speech_insertion_quality_degrades_more_gracefully_with_insertion_length_when role: supports claim: Speech insertion quality degrades more gracefully with insertion length when the model conditions directly on local audio context rather than full-utterance speaker embeddings. source: §4.2, Table 1 evidence: Speech insertion quality degrades more gracefully with insertion length when the model conditions directly on local audio context rather than full-utterance speaker embeddings. confidence: high relevance: medium limitations: - Code and demos are not publicly released with the preprint, and model size is not reported, making independent evaluation and comparison difficult. - 'Evaluation is limited to LibriTTS dev-clean and dev-other; both are clean read-speech corpora, so generalisation to noisy or spontaneous speech is untested. The user study comprises only 15 utterances rated by 6 annotators — a small sample that limits statistical power. MCD is used as the primary objective metric, but it is an indirect measure of naturalness quality and is known to correlate imperfectly with perceptual preference. The comparison set is narrow: SpeechPainter is referenced in the related work but not included in the quantitative evaluation because it uses a fixed-duration formulation, leaving the question of how well RephraseTTS would perform relative to more recent neural audio inpainting approaches unanswered. Duration quality of the inserted segment relative to ground truth is not measured directly.' caveats: [] - id: '2509.01391' published_date: "2025-09-01" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - transformer-enc-dec relevance: medium evidence_role: - architecture_variant - control_evidence - evaluation_caution current_role: minor method_family: - transformer_encoder_decoder_tts claims: - claim_id: ssl_derived_discrete_tokens_can_substitute_phoneme_sequences_as_input role: supports claim: SSL-derived discrete tokens can substitute phoneme sequences as input representations in a TTS front-end without a substantial naturalness penalty in automatic evaluation. source: §V.B, Table II evidence: SSL-derived discrete tokens can substitute phoneme sequences as input representations in a TTS front-end without a substantial naturalness penalty in automatic evaluation. confidence: high relevance: low - claim_id: g2p_free_tts_pipelines_that_learn_text_to_token_mappings role: supports claim: G2P-free TTS pipelines that learn text-to-token mappings from paired speech data avoid the language-specific resource burden of phoneme dictionaries and morphological analysers. source: §I, §III evidence: G2P-free TTS pipelines that learn text-to-token mappings from paired speech data avoid the language-specific resource burden of phoneme dictionaries and morphological analysers. confidence: high relevance: low - claim_id: in_an_ssl_token_based_tts_pipeline_the_spectral_predictor role: supports claim: In an SSL-token-based TTS pipeline, the spectral predictor contributes more to naturalness differences than the text-to-token mapping stage. source: §V.B, Table II evidence: In an SSL-token-based TTS pipeline, the spectral predictor contributes more to naturalness differences than the text-to-token mapping stage. confidence: high relevance: low - claim_id: ssl_based_speech_representations_preserve_sufficient_acoustic_quality_through_a role: supports claim: SSL-based speech representations preserve sufficient acoustic quality through a discretise-then-synthesise pipeline to remain competitive with G2P-derived representations on codec-style quality metrics. source: §V.C, Table II evidence: SSL-based speech representations preserve sufficient acoustic quality through a discretise-then-synthesise pipeline to remain competitive with G2P-derived representations on codec-style quality metrics. confidence: high relevance: low limitations: - All evaluations use automatic metrics only (UTMOS, CER, WARP-Q, SDR) on 100 utterances from a single speaker subset of JVS. No subjective MOS or preference tests are reported; the conclusions about naturalness parity are therefore tentative. - The system is demonstrated exclusively on Japanese and does not yet extend to multilingual settings. The T5 tokenizer is language-specific (tohoku-BERTv3), which the authors acknowledge as a barrier to multilingual scalability. Future directions involve BPE tokenizers (mT5, ByT5) to reduce this dependency. The oracle's counter-intuitive lower UTMOS than the proposed system is left unexplained and may indicate an interaction between SSL token sequence statistics and FastSpeech 2's duration predictor. Individual contribution analysis of duration, pitch, and accent inputs to FastSpeech 2 is identified as missing. caveats: [] - id: '2509.06074' published_date: "2025-09-07" entry_date: '2026-07-30' year: 2025 venue: EMNLP 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_tts claims: - claim_id: word_level_semantic_and_prosodic_context_modeling_in_dialogue_history role: supports claim: Word-level semantic and prosodic context modeling in dialogue history improves prosody expressiveness in conversational TTS over utterance-level context encoders. source: §3.5, Table 1; §3.6, Table 2 evidence: MFCIG-CSS achieves N-DMOS 3.980 and P-DMOS 3.899 on DailyTalk, outperforming seven baselines that operate at the utterance level by 0.122 and 0.104 respectively; ablation removing both graph modules causes the largest performance collapse across all metrics. confidence: high relevance: low - claim_id: graph_neural_networks_with_sequential_cross_turn_aggregation_can_encode role: supports claim: Graph neural networks with sequential cross-turn aggregation can encode complementary semantic and prosodic interaction patterns from multimodal dialogue history for prosody-aware TTS. source: §3.6, Table 2 evidence: 'SIG and PIG are independently ablated: removing SIG reduces N-DMOS by 0.147 and P-DMOS by 0.106; removing PIG produces comparable drops. Both modules contribute distinctly and their combined use provides the strongest performance.' confidence: high relevance: low - claim_id: objective_energy_error_and_subjective_prosody_quality_metrics_can_rank role: complicates claim: Objective energy error and subjective prosody quality metrics can rank conversational TTS systems differently. source: §3.5, Table 1 evidence: MFCIG-CSS achieves best N-DMOS (3.980) and P-DMOS (3.899) on DailyTalk but ranks second on MAE-E (0.314 vs. 0.310 for MSRGCN-CSS), indicating that signal-level energy accuracy does not fully predict human prosody quality judgments. confidence: high relevance: low - claim_id: prosody_modeling_gains_demonstrated_with_acoustic_feature_based_tts_backbones role: complicates claim: Prosody modeling gains demonstrated with acoustic-feature-based TTS backbones may not transfer to codec-token-based or flow-based architectures. source: §5 Limitations evidence: MFCIG-CSS is validated only on a FastSpeech 2 backbone; the authors explicitly identify extension to VITS-based architectures and discrete token-based speech encoders as future work, acknowledging that the current validation scope limits generalizability claims. confidence: high relevance: low limitations: - MFCIG-CSS is evaluated on a single English dialogue dataset (DailyTalk, approximately 20 hours) with a FastSpeech 2 backbone, leaving generalization to other languages, longer conversations, noisy conditions, and modern autoregressive or codec-based TTS systems untested. The interaction graphs operate on frame-averaged acoustic features from Wav2Vec 2.0 and do not yet model fine-grained intra-word acoustic cues such as emotion, emphasis, or pauses. Extension to VITS-based architectures and discrete token-based speech encoders is the primary open direction identified by the authors. caveats: [] - id: '2509.11084' published_date: "2025-09-14" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - flow-matching relevance: medium evidence_role: - architecture_variant current_role: active_evidence method_family: - flow_matching_acoustic_decoders claims: - claim_id: length_normalized_positional_encoding_in_cross_attention_tts_substantially_improves role: supports claim: Length-normalized positional encoding in cross-attention TTS substantially improves alignment accuracy for long-form speech synthesis, where standard absolute-index RoPE degrades. source: §4.2, Table 1 evidence: LARoPE with K_e=4 reduces WER on tc-long (10–30s) from 4.98% to 2.16%, while RoPE's WER on tc-long is nearly double that of tc-short (2.41%), indicating progressive degradation with utterance length. confidence: high relevance: low - claim_id: a_diagonal_inductive_bias_in_cross_attention_positional_embeddings_accelerates role: supports claim: A diagonal inductive bias in cross-attention positional embeddings accelerates text-speech alignment learning during training. source: §4.3, Figure 2 evidence: At 200k training iterations without batch expansion, LARoPE reduces CER from 2.00% to 1.23% versus RoPE, with the performance gap maintained throughout 700k iterations. confidence: high relevance: medium - claim_id: standard_rope_is_suboptimal_in_cross_attention_tts_because_relative role: complicates claim: Standard RoPE is suboptimal in cross-attention TTS because relative positional distances based on absolute indices do not align diagonally when query and key sequence lengths differ, violating the monotonic text-speech alignment structure. source: §3, Figure 1 evidence: Analysis of relative upper bounds shows that RoPE's attention score map loses diagonal structure whenever L_q ≠ L_k (e.g., L_q=64, L_k=256), whereas LARoPE preserves the diagonal regardless of length ratio. confidence: high relevance: low - claim_id: compact_attention_based_tts_systems_can_achieve_pronunciation_accuracy_competitive role: supports claim: Compact attention-based TTS systems can achieve pronunciation accuracy competitive with models more than an order of magnitude larger through improved positional embedding design rather than parameter scaling. source: §4.5, Table 3 evidence: The 19M-parameter LARoPE model achieves 2.25% WER on LibriSpeech test-clean, outperforming E2 TTS (333M params, 2.95% WER), F5-TTS (336M, 2.42%), and DiTTo-TTS (740M, 2.56%) at RTF 0.05. confidence: high relevance: high - claim_id: existing_rope_extensions_position_interpolation_yarn_longrope_address_self_attention role: refines claim: Existing RoPE extensions (position interpolation, YaRN, LongRoPE) address self-attention length extrapolation but leave the cross-attention alignment problem in TTS unresolved. source: §5.1 evidence: The paper identifies that all prior RoPE extensions are designed for self-attention and do not modify the relative distance formulation for cross-attention with differing query and key lengths; LARoPE specifically targets this gap. confidence: high relevance: low limitations: - The evaluation is conducted entirely within the SupertonicTTS framework; generalisability to other cross-attention TTS architectures (such as masked diffusion or AR codec models with cross-attention) is asserted but not tested. The paper does not benchmark LARoPE against alternative alignment improvement strategies such as guided attention loss or diagonal priors in monotonic alignment search, leaving its relative advantage over the broader toolkit unclear. The scaling hyperparameter γ is set to 10 without ablation across values. All experiments use English-language data, and performance on morphologically diverse or tonal languages with different text-to-speech length ratios is unknown. caveats: [] - id: '2509.19592' published_date: "2025-09-23" entry_date: '2026-07-30' year: 2025 venue: arXiv task: - TTS architecture: - autoregressive-LM relevance: medium evidence_role: - architecture_variant - acceleration_evidence current_role: active_evidence method_family: - autoregressive_token_decoders claims: - claim_id: decoding_codebooks_of_a_multi_codebook_acoustic_frame_with_explicit role: supports claim: Decoding codebooks of a multi-codebook acoustic frame with explicit intra-frame dependencies (iteratively) yields a generated token distribution closer to the ground truth than decoding all codebooks in parallel under an independence assumption. source: §3.3.1, Fig. 2e evidence: Across all tested frame-stacking factors (1, 2, 4), every autoregressive- or MaskGIT-local-transformer configuration achieves lower Fréchet Distance than every parallel-sampled configuration, including the unstacked parallel baseline. confidence: high relevance: medium - claim_id: offloading_intra_frame_codebook_decoding_to_a_small_auxiliary_transformer role: supports claim: Offloading intra-frame codebook decoding to a small auxiliary transformer lets a primary acoustic decoder predict multiple codec frames per generation step, substantially increasing throughput without retraining the underlying codec at a lower frame rate. source: §2.4, §3.3.2, Table 1, Fig. 2f evidence: At a frame-stacking factor of 2, the autoregressive local-transformer model reaches 2.1x throughput over the unstacked parallel baseline while improving Fréchet Distance and keeping WER, speaker similarity, and MOS within or better than baseline; the MaskGIT variant reaches 3.1x throughput at comparable quality. confidence: high relevance: low - claim_id: parallel_independent_codebook_prediction_degrades_disproportionately_not_just_proportionally_as role: complicates claim: Parallel independent codebook prediction degrades disproportionately, not just proportionally, as more codebook information is packed into a single decoding step. source: §3.3.2 evidence: Applying parallel sampling to a 2x frame-stacked model (instead of routing through the local transformer) increases unseen-speaker Fréchet Distance by 67% relative to the unstacked parallel baseline and lowers MOS. confidence: high relevance: medium - claim_id: the_throughput_gains_of_iterative_masked_prediction_decoding_for_acoustic role: complicates claim: The throughput gains of iterative masked-prediction decoding for acoustic codebooks come at a quality cost that grows sharply once the number of sampling steps is small relative to the number of tokens being resolved per step. source: §3.3.2, Fig. 2a evidence: At a stacking factor of 4, the MaskGIT local transformer with 3 sampling steps decoding 32 tokens per step (8 codebooks × 4 stacked frames) shows a significant MOS drop relative to baseline, while the autoregressive local transformer at the same stacking factor does not exhibit this drop. confidence: high relevance: medium limitations: - 'Robustness to unseen speakers degrades substantially at higher frame-stacking factors: unseen-speaker speaker similarity falls from 0.765 at stacking factor 1 to 0.642 (AR LT) and 0.624 (MaskGIT LT) at stacking factor 4, which the authors themselves flag by recommending high stacking only "when not needing zero-shot functionality."' - All experiments build on a single base system (Koel-TTS) and a single codec (NanoCodec, FSQ-based, 8 codebooks at 21.5 fps); it is untested whether the same tradeoffs hold for RVQ-based codecs, different codebook counts, or other primary-decoder architectures. The MaskGIT local transformer's degradation at high stacking is attributed to using only 3 sampling steps, but the paper does not run the ablation that would confirm more steps recover quality, leaving the speed-quality Pareto frontier for MaskGIT only partially characterized. Training data is described only as "the same 18k hours of data as in the Koel-TTS paper," with no further specification of language, speaker count, or domain in this paper itself. caveats: [] claim_clusters: - id: end_to_end_seq2seq_reduces_feature_engineering claim: End-to-end sequence-to-sequence TTS can match conventional pipelines without hand-engineered linguistic features. status: emerging confidence: medium supporting_papers: - '1703.10135' contradicting_papers: [] refining_papers: [] caveats: - Early evidence is concentrated in clean, single-speaker settings. last_reviewed: '2026-07-30' - id: decoder_reduction_and_bottlenecks_stabilize_attention claim: Decoder reduction factors and pre-net bottlenecks improve attention stability in autoregressive encoder–decoder TTS. status: emerging confidence: medium supporting_papers: - '1703.10135' - '1712.05884' contradicting_papers: [] refining_papers: [] caveats: - The mechanism is specific to autoregressive acoustic decoders and does not remove long-form failure modes. last_reviewed: '2026-07-30' - id: multi_scale_encoders_and_postnets_improve_acoustics claim: Multi-scale text encoders and sequence-level post-nets improve representation robustness and acoustic detail. status: emerging confidence: medium supporting_papers: - '1703.10135' - interspeech-2025-1334 contradicting_papers: [] refining_papers: [] caveats: - Gains from encoder and post-net changes are often evaluated jointly. last_reviewed: '2026-07-30' - id: mel_intermediates_simplify_waveform_generation claim: Compact mel-spectrogram intermediates simplify neural waveform generation while preserving synthesis quality. status: emerging confidence: medium supporting_papers: - '1712.05884' contradicting_papers: [] refining_papers: [] caveats: - Mel intermediates can constrain phase, bandwidth, and fine temporal detail. last_reviewed: '2026-07-30' - id: explicit_duration_prediction_improves_parallel_tts claim: Explicit duration prediction enables parallel acoustic generation and reduces skipping and repetition failures. status: strongly_supported confidence: high supporting_papers: - '2006.04558' - '2106.15561' - '2508.12001' contradicting_papers: [] refining_papers: [] caveats: - Duration errors can shift rather than eliminate alignment failures. last_reviewed: '2026-07-30' - id: forced_alignment_durations_outperform_teacher_attention claim: Forced-alignment durations can be more accurate than durations extracted from autoregressive teacher attention. status: emerging confidence: medium supporting_papers: - '2006.04558' contradicting_papers: [] refining_papers: [] caveats: - This advantage depends on aligner quality and language resources. last_reviewed: '2026-07-30' - id: monotonic_alignment_supports_long_form_generalization claim: Learned monotonic alignment and position tracking improve repeated-word and long-form reliability. status: emerging confidence: medium supporting_papers: - 2025.naacl-long.591 contradicting_papers: [] refining_papers: [] caveats: - Unbounded synthetic tests do not establish robustness on unconstrained discourse. last_reviewed: '2026-07-30' - id: positional_bias_accelerates_text_speech_alignment claim: Diagonal or monotonic positional biases accelerate text–speech alignment and can reduce the model capacity required for accurate pronunciation. status: emerging confidence: medium supporting_papers: - '2509.11084' contradicting_papers: [] refining_papers: [] caveats: - Compact-model comparisons remain sensitive to training data and front-end normalization. last_reviewed: '2026-07-30' - id: parallel_generation_needs_variance_modeling claim: Parallel acoustic generation requires explicit modeling of duration, pitch, and other sources of speech variation. status: emerging confidence: medium supporting_papers: - '2006.04558' - '2508.12001' contradicting_papers: [] refining_papers: [] caveats: - Better variance modeling does not guarantee fine-grained or interpretable control. last_reviewed: '2026-07-30' - id: hierarchical_prosody_modeling_improves_expressiveness claim: Hierarchical and multi-granular prosody modeling improves expressiveness and supports localized control. status: strongly_supported confidence: high supporting_papers: - '2106.15561' - '2507.04598' - interspeech-2025-1098 contradicting_papers: [] refining_papers: - '2507.04598' caveats: - Sequential hierarchical prediction can accumulate errors across levels. last_reviewed: '2026-07-30' - id: stochastic_prosody_models_increase_diversity claim: Stochastic prosody predictors increase acoustic diversity while retaining competitive naturalness. status: emerging confidence: medium supporting_papers: - interspeech-2025-1940 contradicting_papers: [] refining_papers: [] caveats: - Diversity metrics may not distinguish useful expressiveness from instability. last_reviewed: '2026-07-30' - id: discrete_ssl_features_support_prosody_control claim: Discretized self-supervised speech features provide stable, transferable prosody-control signals. status: emerging confidence: medium supporting_papers: - '2508.11273' contradicting_papers: [] refining_papers: [] caveats: - Token stability depends on the upstream representation, clustering, and reference domain. last_reviewed: '2026-07-30' - id: unseen_speaker_prosody_generalization_remains_hard claim: Prosody and style conditioning learned from seen speakers often generalizes poorly to unseen speakers. status: emerging confidence: medium supporting_papers: - '2508.11273' contradicting_papers: [] refining_papers: - interspeech-2025-1098 caveats: - Speaker encoders and reference representations are evaluated under heterogeneous enrollment conditions. last_reviewed: '2026-07-30' - id: cross_attention_fuses_multimodal_and_local_context claim: Cross-attention effectively fuses text with visual, acoustic, or local speech context for prosody prediction and editing. status: strongly_supported confidence: high supporting_papers: - interspeech-2025-1494 - interspeech-2025-2189 - '2508.17031' - '2509.11084' contradicting_papers: [] refining_papers: [] caveats: - Additional context does not improve every acoustic dimension uniformly. last_reviewed: '2026-07-30' - id: disentanglement_needs_complementary_preservation_losses claim: Style and emotion disentanglement benefits from complementary preservation losses and targeted augmentation. status: strongly_supported confidence: high supporting_papers: - interspeech-2025-1394 - interspeech-2025-2586 - '2508.17031' contradicting_papers: [] refining_papers: [] caveats: - Auxiliary labels and controlled corpora limit conclusions about broad style generalization. last_reviewed: '2026-07-30' - id: adversarial_objectives_restore_acoustic_detail claim: Frequency-aware and local adversarial objectives improve acoustic detail beyond reconstruction losses alone. status: emerging confidence: medium supporting_papers: - '2508.12001' - '2508.17031' contradicting_papers: [] refining_papers: [] caveats: - Adversarial gains can be entangled with stronger duration or context models. last_reviewed: '2026-07-30' - id: compression_and_parallel_decoding_have_hardware_quality_limits claim: Compression and parallel acoustic-token decoding face hardware-realization and quality limits. status: emerging confidence: medium supporting_papers: - interspeech-2025-1122 contradicting_papers: [] refining_papers: - '2509.19592' caveats: - Nominal compression and throughput gains may not translate to common integer hardware or low-step decoding. last_reviewed: '2026-07-30' method_families: - id: transformer_encoder_decoder_tts name: Transformer encoder–decoder TTS summary: Encoder–decoder TTS maps text or auxiliary context to acoustic representations through attention, explicit alignment, or parallel duration expansion. papers: - '1703.10135' - '1712.05884' - '2006.04558' - '2105.06337' - '2106.15561' - 2025.coling-main.352 - iclr-2025-hQvX9MBowC - 2025.naacl-long.591 - 2025.americasnlp-1.1 - '2507.04598' - '2508.11273' - interspeech-2025-1098 - interspeech-2025-1122 - interspeech-2025-1334 - interspeech-2025-1394 - interspeech-2025-1494 - interspeech-2025-1940 - interspeech-2025-2189 - interspeech-2025-2586 - '2508.13028' - '2508.17031' - '2509.01391' - '2509.06074' open_questions: - Which alignment and conditioning mechanisms remain most reliable for long, expressive, and out-of-domain inputs? - id: gan_augmented_encoder_decoder_systems name: GAN-augmented encoder–decoder systems summary: Adversarial losses and waveform decoders sharpen acoustic detail or regularize style and reconstruction in encoder–decoder pipelines. papers: - '2106.15561' - 2025.americasnlp-1.1 - '2508.12001' - interspeech-2025-1122 - interspeech-2025-2586 - '2508.17031' open_questions: - How should adversarial objectives be balanced against alignment, prosody, and reconstruction losses? - id: diffusion_augmented_acoustic_decoders name: Diffusion-augmented acoustic decoders summary: Diffusion components replace or refine deterministic acoustic decoding while retaining transformer conditioning and alignment. papers: - '2105.06337' - '2106.15561' - 2025.coling-main.352 - iclr-2025-hQvX9MBowC open_questions: - When does iterative acoustic generation justify its additional inference cost? - id: flow_matching_acoustic_decoders name: Flow-matching acoustic decoders summary: Flow-matching decoders model continuous acoustic or prosodic variation conditioned by transformer text representations. papers: - '2106.15561' - 2025.coling-main.518 - interspeech-2025-1940 - '2509.11084' open_questions: - Can flow decoders improve variation without weakening explicit alignment or controllability? - id: autoregressive_token_decoders name: Autoregressive token decoders summary: Autoregressive systems decode acoustic frames or codebooks sequentially, preserving dependencies at a throughput cost. papers: - '2106.15561' - '2509.19592' open_questions: - Which dependencies require serial decoding and which can be parallelized safely? - id: vae_latent_encoder_decoder_systems name: VAE latent encoder–decoder systems summary: Variational encoder–decoder systems represent speaker, style, or prosody through learned latent variables. papers: - '2106.15561' - '2508.12001' open_questions: - How can latent factors remain interpretable and controllable without posterior collapse or leakage? - id: hybrid_acoustic_generation_pipelines name: Hybrid acoustic-generation pipelines summary: Hybrid systems combine explicit predictors, neural acoustic models, and generative or adversarial decoders. papers: - 2025.coling-main.518 - '2508.12001' open_questions: - Which module boundaries provide the best balance of quality, diagnosability, and end-to-end optimization? reassessment_queue: - id: end_to_end_seq2seq_reduces_feature_engineering type: claim_status reason: Foundational evidence predates modern multilingual and expressive benchmarks. trigger: Controlled modern studies isolate encoder–decoder design from data and vocoder scale. due: 2026-10 current_assessment: emerging watch_for: - Modern Tacotron-style replications - Matched conventional-pipeline comparisons - id: monotonic_alignment_supports_long_form_generalization type: claim_status reason: Long synthetic sequences and repeated-word tests may not represent unconstrained discourse. trigger: Independent systems reproduce long-form gains on multilingual paragraph and dialogue tests. due: 2026-10 current_assessment: emerging watch_for: - Long-form multilingual tests - Repeated-token alignment benchmarks - id: explicit_duration_prediction_improves_parallel_tts type: claim_status reason: Duration supervision quality and prosody coupling remain confounded. trigger: Matched studies compare learned, teacher-derived, and forced-aligned durations across languages. due: 2026-10 current_assessment: strongly_supported watch_for: - Matched duration-source ablations - Low-resource alignment studies - id: discrete_ssl_features_support_prosody_control type: claim_status reason: Evidence is concentrated in a small number of representations and emotion-transfer tasks. trigger: Independent systems show stable cross-speaker and cross-language control with discrete SSL features. due: 2026-10 current_assessment: emerging watch_for: - Cross-language SSL prosody tests - Tokenizer and clustering ablations - id: compression_and_parallel_decoding_have_hardware_quality_limits type: benchmark_validity reason: Reported efficiency depends on packing support, decoding schedule, and deployment hardware. trigger: Hardware-normalized benchmarks jointly report storage, throughput, and listener quality. due: 2026-10 current_assessment: emerging watch_for: - On-device packing benchmarks - Quality–throughput codebook studies open_questions: - Which alignment mechanism is most robust to repeated text, long-form synthesis, and low-resource languages? - When should encoder–decoder TTS use explicit durations rather than latent or attention-based alignment? - How should prosody be represented across phoneme, word, phrase, and utterance timescales? - Can discrete SSL controls transfer across speakers and languages without leaking identity or content? - Which transformer components remain useful when diffusion, flow, or codec-token decoders replace mel prediction? - How should compact encoder–decoder systems be evaluated under real hardware and memory constraints? trend_notes: - Encoder–decoder TTS has shifted from autoregressive attention toward explicit duration and monotonic alignment mechanisms. - Transformer conditioning increasingly persists as a front end while diffusion, flow, GAN, or token decoders replace deterministic mel generation. - Prosody work is moving from utterance-level style vectors toward hierarchical, stochastic, and context-aware predictors. - Cross-attention is expanding beyond text–speech alignment to visual context, local acoustic editing, and neural-signal decoding. - Compact and quantized systems increasingly expose the difference between theoretical efficiency and realizable hardware gains.