mlsanityData to 7 Oct 2026

Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

arXiv 2103.14574 ↗First posted 26 Mar 2021cs.SD eess.AScited by 31

Not on the map. Why?

Abstract (arXiv)

This paper introduces Parallel Tacotron 2, a non-autoregressive neural text-to-speech model with a fully differentiable duration model which does not require supervised duration signals. The duration model is based on a novel attention mechanism and an iterative reconstruction loss based on Soft Dynamic Time Warping, this model can learn token-frame alignments as well as token durations automatically. Experimental results show that Parallel Tacotron 2 outperforms baselines in subjective naturalness in several diverse multi speaker evaluations. Its duration control capability is also demonstrated.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Mar 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 7; 2024: 0; 2025: 3; 2026: 4.

31 papers.

Sort:

By area:

  1. 2021A Survey on Neural Speech Synthesiscited by 182
  2. 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
  3. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  4. 2021Translatotron 2: High-quality direct speech-to-speech translation with voice preservationcited by 69
  5. 2022StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesiscited by 32
  6. 2022Musika! Fast Infinite Waveform Music Generationcited by 24
  7. 2022Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speechcited by 13
  8. 2022Heterogeneous Target Speech Separationcited by 13
  9. 2021More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speechcited by 12
  10. 2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generationcited by 11
  11. 2021Neural HMMs are all you need (for high-quality attention-free TTS)cited by 8
  12. 2025LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLMcited by 7
19 more
  1. 2022Regotron: Regularizing the Tacotron2 architecture via monotonic alignment losscited by 3
  2. 2023Prosody Analysis of Audiobookscited by 3
  3. 2025LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Contextcited by 3
  4. 2022AdaVocoder: Adaptive Vocoder for Custom Voicecited by 2
  5. 2023An End-to-End Neural Network for Image-to-Audio Transformationcited by 2
  6. 2022Karaoker: Alignment-free singing voice synthesis with speech training datacited by 1
  7. 2022Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speechcited by 1
  8. 2023Cross-Utterance Conditioned VAE for Speech Generationcited by 1
  9. 2023DurIAN-E: Duration Informed Attention Network For Expressive Text-to-Speech Synthesiscited by 1
  10. 2025CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloningcited by 1
  11. 2021PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Controlcited by 0
  12. 2022AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modelingcited by 0
  13. 2022Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speechcited by 0
  14. 2022SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speechcited by 0
  15. 2023MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Settingcited by 0
  16. 2026ADVOSYNTH: A Synthetic Multi-Advocate Dataset for Speaker Identification in Courtroom Scenarioscited by 0
  17. 2026MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Controlcited by 0
  18. 2026PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbingcited by 0
  19. 2026Distill Locally, Schedule Globally: Flow Maps for Few-Step Text-to-Speechcited by 0