mlsanityData to 7 Oct 2026

Parallel Tacotron: Non-Autoregressive and Controllable TTS

arXiv 2010.11439 ↗First posted 22 Oct 2020cs.SD eess.AScited by 49

Not on the map. Why?

Abstract (arXiv)

Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented with a variational autoencoder-based residual encoder. This model, called Parallel Tacotron, is highly parallelizable during both training and inference, allowing efficient synthesis on modern parallel hardware. The use of the variational autoencoder relaxes the one-to-many mapping nature of the text-to-speech problem and improves naturalness. To further improve the naturalness, we use lightweight convolutions, which can efficiently capture local contexts, and introduce an iterative spectrogram loss inspired by iterative refinement. Experimental results show that Parallel Tacotron matches a strong autoregressive baseline in subjective evaluations with significantly decreased inference time.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 16; 2022: 15; 2023: 10; 2024: 7; 2025: 1.

49 papers.

Sort:

By area:

  1. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  2. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  3. 2021A Survey on Neural Speech Synthesiscited by 182
  4. 2022MAESTRO: Matched Speech Text Representations through Modality Matchingcited by 79
  5. 2021Translatotron 2: High-quality direct speech-to-speech translation with voice preservationcited by 69
  6. 2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTScited by 52
  7. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANscited by 43
  8. 2023E3 TTS: Easy End-to-End Diffusion-based Text to Speechcited by 30
  9. 2022A Review on Methods and Applications in Multimodal Deep Learningcited by 29
  10. 2021Recent Advances and Trends in Multimodal Deep Learning: A Reviewcited by 26
  11. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 22
  12. 2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
37 more
  1. 2021DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021cited by 19
  2. 2022Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speechcited by 15
  3. 2021Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speechcited by 14
  4. 2022Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASRcited by 13
  5. 2021FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesiscited by 12
  6. 2021More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speechcited by 12
  7. 2023Let There Be Sound: Reconstructing High Quality Speech from Silent Videoscited by 12
  8. 2023Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Codingcited by 10
  9. 2021On-device neural speech synthesiscited by 9
  10. 2021Hierarchical prosody modeling and control in non-autoregressive parallel neural TTScited by 9
  11. 2022Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesiscited by 7
  12. 2023Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesiscited by 7
  13. 2024DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Modelscited by 7
  14. 2024VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processingcited by 7
  15. 2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
  16. 2022Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesiscited by 6
  17. 2022Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguationcited by 6
  18. 2023High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Modelscited by 6
  19. 2022Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Modelscited by 4
  20. 2023Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Videocited by 4
  21. 2024TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizerscited by 4
  22. 2023Using Text Injection to Improve Recognition of Personal Identifiers in Speechcited by 3
  23. 2023Prosody Analysis of Audiobookscited by 3
  24. 2024Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesiscited by 3
  25. 2021Axial Residual Networks for CycleGAN-based Voice Conversioncited by 2
  26. 2022DeepGraviLens: a Multi-Modal Architecture for Classifying Gravitational Lensing Datacited by 2
  27. 2023An End-to-End Neural Network for Image-to-Audio Transformationcited by 2
  28. 2023Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speechcited by 2
  29. 2024ASTRA: Aligning Speech and Text Representations for Asr without Samplingcited by 2
  30. 2021A study on the efficacy of model pre-training in developing neural text-to-speech systemcited by 1
  31. 2022Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Featurescited by 1
  32. 2025Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesiscited by 1
  33. 2021Sprachsynthese -- State-of-the-Art in englischer und deutscher Sprachecited by 0
  34. 2021PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Controlcited by 0
  35. 2022AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modelingcited by 0
  36. 2022Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesiscited by 0
  37. 2022Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanismcited by 0