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

Jiaqi Su, Zeyu Jin, Adam Finkelstein


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.


 DOI: 10.21437/Interspeech.2020-2143

Cite as: Su, J., Jin, Z., Finkelstein, A. (2020) HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks. Proc. Interspeech 2020, 4506-4510, DOI: 10.21437/Interspeech.2020-2143.


@inproceedings{Su2020,
  author={Jiaqi Su and Zeyu Jin and Adam Finkelstein},
  title={{HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={4506--4510},
  doi={10.21437/Interspeech.2020-2143},
  url={http://dx.doi.org/10.21437/Interspeech.2020-2143}
}