Data to 7 Oct 2026

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

arXiv 2010.05646 ↗First posted 12 Oct 2020cs.SD cs.LG eess.AScited by 1,139

Not on the map. Why?

Cited by 216 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of autoregressive and flow-based generative models. In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. As speech audio consists of sinusoidal signals with various periods, we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. A subjective human evaluation (mean opinion score, MOS) of a single speaker dataset indicates that our proposed method demonstrates similarity to human quality while generating 22.05 kHz high-fidelity audio 167.9 times faster than real-time on a single V100 GPU. We further show the generality of HiFi-GAN to the mel-spectrogram inversion of unseen speakers and end-to-end speech synthesis. Finally, a small footprint version of HiFi-GAN generates samples 13.4 times faster than real-time on CPU with comparable quality to an autoregressive counterpart.

Key facts. Cited by 1,139 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 70; 2022: 171; 2023: 227; 2024: 272; 2025: 260; 2026: 139.

1,139 papers.

Sort:

By area:

2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
2021SoundStream: An End-to-End Neural Audio Codeccited by 756
2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
2022High Fidelity Neural Audio Compressioncited by 673
2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
2023Scaling Speech Technology to 1,000+ Languagescited by 401
2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 343
2021Generative Spoken Language Modeling from Raw Audiocited by 336
2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Modelscited by 323

38 more

2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 301
2022AudioGen: Textually Guided Audio Generationcited by 292
2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
2022Diffsound: Discrete Diffusion Model for Text-to-sound Generationcited by 256
2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 216
2026LTX-2: Efficient Joint Audio-Visual Foundation Modelcited by 213
2023Any-to-Any Generation via Composable Diffusioncited by 203
2021A Survey on Neural Speech Synthesiscited by 182
2024Fast Timing-Conditioned Latent Audio Diffusioncited by 178
2021SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processingcited by 177
2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 174
2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 169
2023Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modelingcited by 166
2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 156
2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 150
2021Direct speech-to-speech translation with discrete unitscited by 148
2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 147
2023Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Modelcited by 145
2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 142
2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
2023Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Modelscited by 133
2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
2022Generative Spoken Dialogue Language Modelingcited by 125
2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modelingcited by 124
2024Spirit LM: Interleaved Spoken and Written Language Modelcited by 123
2021Textless Speech-to-Speech Translation on Real Datacited by 121
2023Audiobox: Unified Audio Generation with Natural Language Promptscited by 120
2021Text-Free Prosody-Aware Generative Spoken Language Modelingcited by 119
2024VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wildcited by 118
2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 116

50 most cited of 1,139 All 1,139 (JSON)