# HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

arXiv: https://arxiv.org/abs/2006.05694 · HTML: https://mlsanity.com/paper/2006.05694/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2020.

## Built on by (most cited first, 30 of 40)

- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [CDPAM: Contrastive learning for perceptual audio similarity](https://mlsanity.com/paper/2102.05109/) (2021)
- [SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping](https://mlsanity.com/paper/2203.16749/) (2022)
- [MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models](https://mlsanity.com/paper/2402.06178/) (2024)
- [The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio](https://mlsanity.com/paper/2405.04880/) (2024)
- [Learning Audio-Visual Dereverberation](https://mlsanity.com/paper/2106.07732/) (2021)
- [Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis](https://mlsanity.com/paper/2203.17263/) (2022)
- [WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration](https://mlsanity.com/paper/2210.01029/) (2022)
- [AV-RIR: Audio-Visual Room Impulse Response Estimation](https://mlsanity.com/paper/2312.00834/) (2023)
- [CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing](https://mlsanity.com/paper/2202.09950/) (2022)
- [AdVerb: Visually Guided Audio Dereverberation](https://mlsanity.com/paper/2308.12370/) (2023)
- [Context-Aware Prosody Correction for Text-Based Speech Editing](https://mlsanity.com/paper/2102.08328/) (2021)
- [Music Enhancement via Image Translation and Vocoding](https://mlsanity.com/paper/2204.13289/) (2022)
- [High Fidelity Speech Regeneration with Application to Speech Enhancement](https://mlsanity.com/paper/2102.00429/) (2021)
- [Restoring degraded speech via a modified diffusion model](https://mlsanity.com/paper/2104.11347/) (2021)
- [Hierarchical Diffusion Models for Singing Voice Neural Vocoder](https://mlsanity.com/paper/2210.07508/) (2022)
- [Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation](https://mlsanity.com/paper/2410.13198/) (2024)
- [Music Separation Enhancement with Generative Modeling](https://mlsanity.com/paper/2208.12387/) (2022)
- [FINALLY: fast and universal speech enhancement with studio-like quality](https://mlsanity.com/paper/2410.05920/) (2024)
- [Universal Speech Enhancement with Regression and Generative Mamba](https://mlsanity.com/paper/2505.21198/) (2025)
- [Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar](https://mlsanity.com/paper/2210.06877/) (2022)
- [SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking](https://mlsanity.com/paper/2211.12623/) (2022)
- [Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio](https://mlsanity.com/paper/2406.08112/) (2024)
- [Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation](https://mlsanity.com/paper/2205.08455/) (2022)
- [Deep neural network techniques for monaural speech enhancement: state of the art analysis](https://mlsanity.com/paper/2212.00369/) (2022)
- [Blind Restoration of Real-World Audio by 1D Operational GANs](https://mlsanity.com/paper/2212.14618/) (2022)
- [Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation](https://mlsanity.com/paper/2408.16126/) (2024)
- [UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control](https://mlsanity.com/paper/2106.11171/) (2021)
- [Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement](https://mlsanity.com/paper/2202.11918/) (2022)

## Abstract (arXiv)

Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new speech content, and new environments. It significantly outperforms state-of-the-art baseline methods in both objective and subjective experiments.