mlsanityData to 7 Oct 2026

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

arXiv 2006.05694 ↗First posted 10 Jun 2020eess.AS cs.LG cs.SDcited by 40

Not on the map. Why?

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.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 15; 2023: 4; 2024: 9; 2025: 4; 2026: 1.

40 papers.

Sort:

By area:

  1. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  2. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 58
  3. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  4. 2022SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shapingcited by 37
  5. 2024MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Modelscited by 32
  6. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 31
  7. 2021Learning Audio-Visual Dereverberationcited by 26
  8. 2022Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesiscited by 24
  9. 2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
  10. 2023AV-RIR: Audio-Visual Room Impulse Response Estimationcited by 20
  11. 2022CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editingcited by 15
  12. 2023AdVerb: Visually Guided Audio Dereverberationcited by 15
28 more
  1. 2021Context-Aware Prosody Correction for Text-Based Speech Editingcited by 13
  2. 2022Music Enhancement via Image Translation and Vocodingcited by 11
  3. 2021High Fidelity Speech Regeneration with Application to Speech Enhancementcited by 10
  4. 2021Restoring degraded speech via a modified diffusion modelcited by 10
  5. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocodercited by 10
  6. 2024Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentationcited by 9
  7. 2022Music Separation Enhancement with Generative Modelingcited by 8
  8. 2024FINALLY: fast and universal speech enhancement with studio-like qualitycited by 7
  9. 2025Universal Speech Enhancement with Regression and Generative Mambacited by 7
  10. 2022Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatarcited by 6
  11. 2022SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Maskingcited by 6
  12. 2024Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audiocited by 5
  13. 2022Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberationcited by 3
  14. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  15. 2022Blind Restoration of Real-World Audio by 1D Operational GANscited by 3
  16. 2024Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluationcited by 3
  17. 2021UniTTS: Residual Learning of Unified Embedding Space for Speech Style Controlcited by 1
  18. 2022Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancementcited by 1
  19. 2022NeuralDPS: Neural Deterministic Plus Stochastic Model with Multiband Excitation for Noise-Controllable Waveform Generationcited by 1
  20. 2022Audio Denoising for Robust Audio Fingerprintingcited by 1
  21. 2023CORN: Co-Trained Full- And No-Reference Speech Quality Assessmentcited by 1
  22. 2023D4AM: A General Denoising Framework for Downstream Acoustic Modelscited by 1
  23. 2024LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognitioncited by 1
  24. 2024Selective State Space Model for Monaural Speech Enhancementcited by 1
  25. 2025HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networkscited by 1
  26. 2025Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restorationcited by 1
  27. 2025Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancementcited by 1
  28. 2026A Cold Diffusion Approach for Percussive Dereverberationcited by 0