Share Email Print
cover

Proceedings Paper • new

Frame-level speech enhancement based on Wasserstein GAN
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Speech enhancement is a challenging and critical task in the speech processing research area. In this paper, we propose a novel speech enhancement model based on Wasserstein generative adversarial networks, called WSEM. The proposed model operates on frame-level speech segments by using an adjacent frames extension mechanism, to enforce the mapping from noisy speech to the clean target, which makes it distinctly different from other related GAN-based models. We compare the performance of WSEM with related works on benchmark datasets under different signal-to-noise (SNR) conditions, experimental results show that WSEM performs comparable to the state-of-the-art approaches in all the tests, and it performs especially well in low SNR environments.

Paper Details

Date Published: 31 December 2019
PDF: 7 pages
Proc. SPIE 11384, Eleventh International Conference on Signal Processing Systems, 113840G (31 December 2019); doi: 10.1117/12.2559619
Show Author Affiliations
Peng Chuan, Univ. of Electronic Science and Technology of China (China)
Tian Lan, Univ. of Electronic Science and Technology of China (China)
Meng Li, Univ. of Electronic Science and Technology of China (China)
Sen Li, Univ. of Electronic Science and Technology of China (China)
Qiao Liu, Univ. of Electronic Science and Technology of China (China)


Published in SPIE Proceedings Vol. 11384:
Eleventh International Conference on Signal Processing Systems
Kezhi Mao, Editor(s)

© SPIE. Terms of Use
Back to Top