mlsanityData to 7 Oct 2026

BigVGAN: A Universal Neural Vocoder with Large-Scale Training

arXiv 2206.04658 ↗First posted 9 Jun 2022cs.SD cs.CL cs.LGcited by 245

Not on the map. Why?

Cited by 69 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across various recording environments. In this work, we present BigVGAN, a universal vocoder that generalizes well for various out-of-distribution scenarios without fine-tuning. We introduce periodic activation function and anti-aliased representation into the GAN generator, which brings the desired inductive bias for audio synthesis and significantly improves audio quality. In addition, we train our GAN vocoder at the largest scale up to 112M parameters, which is unprecedented in the literature. We identify and address the failure modes in large-scale GAN training for audio, while maintaining high-fidelity output without over-regularization. Our BigVGAN, trained only on clean speech (LibriTTS), achieves the state-of-the-art performance for various zero-shot (out-of-distribution) conditions, including unseen speakers, languages, recording environments, singing voices, music, and instrumental audio. We release our code and model at: https://github.com/NVIDIA/BigVGAN

Key facts. Cited by 245 papers in the map (data through 7 Oct 2026). Builds on 51 of its 69 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

51 of 69 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  10. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
38 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  5. 2016Least Squares Generative Adversarial Networkscited by 1,000
  6. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  7. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  8. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  9. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  10. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  11. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  12. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  13. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
  14. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  15. 2018Adversarial Audio Synthesiscited by 222
  16. 2018Efficient Neural Audio Synthesiscited by 218
  17. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  18. 2019Direct speech-to-speech translation with a sequence-to-sequence modelcited by 118
  19. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  20. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  21. 2018Neural Voice Cloning with a Few Samplescited by 100
  22. 2020Neural Networks Fail to Learn Periodic Functions and How to Fix Itcited by 97
  23. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  24. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 78
  25. 2021UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generationcited by 71
  26. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  27. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  28. 2018FloWaveNet : A Generative Flow for Raw Audiocited by 54
  29. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  30. 2019A scalable noisy speech dataset and online subjective test frameworkcited by 47
  31. 2021Chunked Autoregressive GAN for Conditional Waveform Synthesiscited by 38
  32. 2020Upsampling artifacts in neural audio synthesiscited by 28
  33. 2020StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalizationcited by 26
  34. 2021Universal Neural Vocoding with Parallel WaveNetcited by 25
  35. 2021GAN Vocoder: Multi-Resolution Discriminator Is All You Needcited by 16
  36. 2020Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditionscited by 14
  37. 2020NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexitycited by 9
  38. 2020Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domainscited by 9

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 27; 2024: 62; 2025: 92; 2026: 60.

245 papers.

Sort:

By area:

  1. 2025Qwen2.5-Omni Technical Reportcited by 704
  2. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  3. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  4. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  5. 2025Kimi-Audio Technical Reportcited by 210
  6. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 159
  7. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 150
  8. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  9. 2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 142
  10. 2024MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesiscited by 134
  11. 2023Audiobox: Unified Audio Generation with Natural Language Promptscited by 120
  12. 2026Qwen3-TTS Technical Reportcited by 106
38 more
  1. 2025Step-Audio 2 Technical Reportcited by 101
  2. 2023Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generationcited by 90
  3. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 88
  4. 2024Recent Advances in Speech Language Models: A Surveycited by 85
  5. 2025IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speechcited by 85
  6. 2025Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generationcited by 76
  7. 2024BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of datacited by 74
  8. 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generationcited by 73
  9. 2023V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Modelscited by 65
  10. 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generationcited by 56
  11. 2024Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generationcited by 54
  12. 2024Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matchingcited by 52
  13. 2024Masked Audio Generation using a Single Non-Autoregressive Transformercited by 50
  14. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 48
  15. 2024SNAC: Multi-Scale Neural Audio Codeccited by 42
  16. 2024Zero-shot Voice Conversion with Diffusion Transformerscited by 39
  17. 2025M-Prometheus: A Suite of Open Multilingual LLM Judgescited by 37
  18. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesiscited by 34
  19. 2024DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factorscited by 31
  20. 2024Taming Data and Transformers for Audio Generationcited by 28
  21. 2023Make-A-Voice: Unified Voice Synthesis With Discrete Representationcited by 27
  22. 2025IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech Systemcited by 27
  23. 2023The Singing Voice Conversion Challenge 2023cited by 25
  24. 2023PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptionscited by 25
  25. 2023ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformercited by 24
  26. 2024EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speechcited by 23
  27. 2023Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representationscited by 22
  28. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
  29. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 22
  30. 2022ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speechcited by 21
  31. 2023StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesiscited by 21
  32. 2024AudioLCM: Text-to-Audio Generation with Latent Consistency Modelscited by 21
  33. 2024FlowSep: Language-Queried Sound Separation with Rectified Flow Matchingcited by 21
  34. 2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
  35. 2023CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Modelscited by 20
  36. 2024Improving Text-To-Audio Models with Synthetic Captionscited by 19
  37. 2024FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generationcited by 19
  38. 2024EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vectorcited by 19

50 most cited of 245 All 245 (JSON)