mlsanityData to 7 Oct 2026

PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control

arXiv 2110.04486 ↗First posted 9 Oct 2021cs.SD cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Sequence expansion between encoder and decoder is a critical challenge in sequence-to-sequence TTS. Attention-based methods achieve great naturalness but suffer from unstable issues like missing and repeating phonemes, not to mention accurate duration control. Duration-informed methods, on the contrary, seem to easily adjust phoneme duration but show obvious degradation in speech naturalness. This paper proposes PAMA-TTS to address the problem. It takes the advantage of both flexible attention and explicit duration models. Based on the monotonic attention mechanism, PAMA-TTS also leverages token duration and relative position of a frame, especially countdown information, i.e. in how many future frames the present phoneme will end. They help the attention to move forward along the token sequence in a soft but reliable control. Experimental results prove that PAMA-TTS achieves the highest naturalness, while has on-par or even better duration controllability than the duration-informed model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 9 Oct 2021.

Builds on

16 of 21 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  3. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  4. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  5. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  6. 2020End-to-End Adversarial Text-to-Speechcited by 77
  7. 2020Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modelingcited by 65
  8. 2020Parallel Tacotron: Non-Autoregressive and Controllable TTScited by 49
  9. 2019Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesiscited by 44
  10. 2019Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTScited by 33
  11. 2019DurIAN: Duration Informed Attention Network For Multimodal Synthesiscited by 33
  12. 2021Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modelingcited by 31
4 more
  1. 2020AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignmentcited by 20
  2. 2018Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesiscited by 17
  3. 2020JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignmentcited by 13
  4. 2021VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesiscited by 7

Built on by

Not cited yet.