Loading...
Loading...

Go to the content (press return)

Time-domain speech enhancement using generative adversarial networks

Author
Pascual, S.; Serra, J.; Bonafonte, A.
Type of activity
Journal article
Journal
Speech communication
Date of publication
2019-11-01
Volume
114
First page
10
Last page
21
DOI
10.1016/j.specom.2019.09.001
Project funding
Deep learning technologies for speech and audio processing
Repository
http://hdl.handle.net/2117/180457 Open in new window
URL
https://www.sciencedirect.com/science/article/abs/pii/S0167639319301359 Open in new window
Abstract
Speech enhancement improves recorded voice utterances to eliminate noise that might be impeding their intelligibility or compromising their quality. Typical speech enhancement systems are based on regression approaches that subtract noise or predict clean signals. Most of them do not operate directly on waveforms. In this work, we propose a generative approach to regenerate corrupted signals into a clean version by using generative adversarial networks on the raw signal. We also explore several ...
Citation
Pascual, S.; Serra, J.; Bonafonte, A. Time-domain speech enhancement using generative adversarial networks. "Speech communication", 1 Novembre 2019, vol. 114, p. 10-21.
Keywords
Audio transformation, Generative adversarial network, Neural networks, Speech enhancement
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Participants