SERGAN : speech enhancement using relativistic generative adversarial networks with gradient penalty
- Author
- Deepak Baby (UGent) and Sarah Verhulst (UGent)
- Organization
- Project
-
- RobSpear (Speech Encoding in Impaired Hearing)
- Abstract
- Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Recently, conditional generative adversarial networks (cGANs) have shown promise in addressing the phase mismatch problem by directly mapping the raw noisy speech waveform to the underlying clean speech signal. However, stabilizing and training cGAN systems is difficult and they still fall short of the performance achieved by spectral enhancement approaches. This paper introduces relativistic GANs with a relativistic cost function at its discriminator and gradient penalty to improve time-domain speech enhancement. Simulation results show that relativistic discriminators provide a more stable training of cGANs and yield a better generator network for improved speech enhancement performance.
- Keywords
- speech enhancement, relativistic GAN, convolutional neural networks
Downloads
-
(...).pdf
- full text
- |
- UGent only
- |
- |
- 806.37 KB
-
ACOUST 512a.pdf
- full text
- |
- open access
- |
- |
- 795.32 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8613639
- MLA
- Baby, Deepak, and Sarah Verhulst. “SERGAN : Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty.” 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, pp. 106–10, doi:10.1109/ICASSP.2019.8683799.
- APA
- Baby, D., & Verhulst, S. (2019). SERGAN : speech enhancement using relativistic generative adversarial networks with gradient penalty. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 106–110. https://doi.org/10.1109/ICASSP.2019.8683799
- Chicago author-date
- Baby, Deepak, and Sarah Verhulst. 2019. “SERGAN : Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty.” In 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 106–10. https://doi.org/10.1109/ICASSP.2019.8683799.
- Chicago author-date (all authors)
- Baby, Deepak, and Sarah Verhulst. 2019. “SERGAN : Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty.” In 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 106–110. doi:10.1109/ICASSP.2019.8683799.
- Vancouver
- 1.Baby D, Verhulst S. SERGAN : speech enhancement using relativistic generative adversarial networks with gradient penalty. In: 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). 2019. p. 106–10.
- IEEE
- [1]D. Baby and S. Verhulst, “SERGAN : speech enhancement using relativistic generative adversarial networks with gradient penalty,” in 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), Brighton, ENGLAND, 2019, pp. 106–110.
@inproceedings{8613639,
abstract = {{Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Recently, conditional generative adversarial networks (cGANs) have shown promise in addressing the phase mismatch problem by directly mapping the raw noisy speech waveform to the underlying clean speech signal. However, stabilizing and training cGAN systems is difficult and they still fall short of the performance achieved by spectral enhancement approaches. This paper introduces relativistic GANs with a relativistic cost function at its discriminator and gradient penalty to improve time-domain speech enhancement. Simulation results show that relativistic discriminators provide a more stable training of cGANs and yield a better generator network for improved speech enhancement performance.}},
author = {{Baby, Deepak and Verhulst, Sarah}},
booktitle = {{2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)}},
isbn = {{9781538646588}},
issn = {{1520-6149}},
keywords = {{speech enhancement,relativistic GAN,convolutional neural networks}},
language = {{eng}},
location = {{Brighton, ENGLAND}},
pages = {{106--110}},
title = {{SERGAN : speech enhancement using relativistic generative adversarial networks with gradient penalty}},
url = {{http://dx.doi.org/10.1109/ICASSP.2019.8683799}},
year = {{2019}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: