mlsanityData to 7 Oct 2026

WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration

arXiv 2210.01029 ↗First posted 3 Oct 2022eess.AS cs.LG cs.SDcited by 20

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework and adversarial training, respectively. This study proposes a fast and high-quality neural vocoder called textitWaveFit, which integrates the essence of GANs into a DDPM-like iterative framework based on fixed-point iteration. WaveFit iteratively denoises an input signal, and trains a deep neural network (DNN) for minimizing an adversarial loss calculated from intermediate outputs at all iterations. Subjective (side-by-side) listening tests showed no statistically significant differences in naturalness between human natural speech and those synthesized by WaveFit with five iterations. Furthermore, the inference speed of WaveFit was more than 240 times faster than WaveRNN. Audio demos are available at urlgoogle.github.io/df-conformer/wavefit/.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 59 of its 71 references that are in the map. First posted on arXiv 3 Oct 2022.

Builds on

59 of 71 references.

Closest ancestors · 6

Same direction, newest first

  1. 2022SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping31 Mar
  2. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis25 Mar
  3. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training8 Feb
  4. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs28 Jan
  5. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior11 Jun
  6. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  8. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  9. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  10. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  11. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  12. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
38 more
  1. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  2. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  3. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  4. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  5. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  6. 2018Adversarial Audio Synthesiscited by 222
  7. 2018Efficient Neural Audio Synthesiscited by 218
  8. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  9. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
  10. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  11. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  12. 2021Direct speech-to-speech translation with discrete unitscited by 148
  13. 2019Direct speech-to-speech translation with a sequence-to-sequence modelcited by 118
  14. 2020An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learningcited by 111
  15. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  16. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  17. 2021UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generationcited by 71
  18. 2021Translatotron 2: High-quality direct speech-to-speech translation with voice preservationcited by 69
  19. 2020Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modelingcited by 65
  20. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  21. 2020Learning Maximally Monotone Operators for Image Recoverycited by 62
  22. 2017Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibriumcited by 58
  23. 2020Regularization by Denoising via Fixed-Point Projection (RED-PRO)cited by 55
  24. 2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTScited by 52
  25. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  26. 2021VoiceFixer: Toward General Speech Restoration with Neural Vocodercited by 50
  27. 2020Parallel Tacotron: Non-Autoregressive and Controllable TTScited by 49
  28. 2020A Spectral Energy Distance for Parallel Speech Synthesiscited by 42
  29. 2020HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networkscited by 40
  30. 2020SEANet: A Multi-modal Speech Enhancement Networkcited by 35
  31. 2017Wavenet based low rate speech codingcited by 32
  32. 2022iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transformcited by 30
  33. 2022Avocodo: Generative Adversarial Network for Artifact-free Vocodercited by 18
  34. 2019A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNetcited by 16
  35. 2020Fixed Point Strategies in Data Sciencecited by 16
  36. 2021GAN Vocoder: Multi-Resolution Discriminator Is All You Needcited by 16
  37. 2022A Comparative Study of Self-supervised Speech Representation Based Voice Conversioncited by 9
  38. 2019Parametric Resynthesis with neural vocoderscited by 8

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 7; 2025: 2; 2026: 3.

20 papers.

Sort:

By area:

  1. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  2. 2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 116
  3. 2023Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMcited by 92
  4. 2024Recent Advances in Speech Language Models: A Surveycited by 85
  5. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  6. 2023Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representationscited by 22
  7. 2024FLEURS-R: A Restored Multilingual Speech Corpus for Generation Taskscited by 13
  8. 2023Translatotron 3: Speech to Speech Translation with Monolingual Datacited by 12
  9. 2024PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generationcited by 12
  10. 2023Geometry of Score Based Generative Modelscited by 7
  11. 2024FINALLY: fast and universal speech enhancement with studio-like qualitycited by 7
  12. 2024Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimizationcited by 4
8 more
  1. 2023iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNNcited by 3
  2. 2023FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder With Multiple STFTscited by 1
  3. 2025Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restorationcited by 1
  4. 2024Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminatorcited by 0
  5. 2024Zero-Shot Mono-to-Binaural Speech Synthesiscited by 0
  6. 2026WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Modelscited by 0
  7. 2026Iterative Audio Separation with Mixture Consistency via MIMO Model Extensioncited by 0
  8. 2026Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Wave-Trainer-Fit: Neural Vocoder with Trainable Prior and Fixed-Point Iteration towards High-Quality Speech Generation from SSL features ↗
  2. 2024PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model
  3. 2023Voice Conversion with Denoising Diffusion Probabilistic GAN Models
  4. 2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
  5. 2024Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model
  6. 2023Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS
  7. 2021Restoring degraded speech via a modified diffusion model
  8. 2025WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching