@inproceedings{b4b59b11ea2f4f0a8ba90aa9ed22143c,
title = "HiFi-GAN: High-fidelity denoising and dereverberation based on speech deep features in adversarial networks",
abstract = "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.",
keywords = "Deep features, Denoising, Dereverberation, Generative adversarial networks, Speech enhancement",
author = "Jiaqi Su and Zeyu Jin and Adam Finkelstein",
note = "Publisher Copyright: Copyright {\textcopyright} 2020 ISCA; 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",
year = "2020",
doi = "10.21437/Interspeech.2020-2143",
language = "English (US)",
isbn = "9781713820697",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association",
pages = "4506--4510",
booktitle = "Interspeech 2020",
}