Multiple modules speech enhancement in mixed noise and low SNR environments

Tian Lan; Wenzheng Ye; Guoqiang Hui; Sen Li; Qiao Liu

doi:10.1117/12.2559657

31 December 2019 Multiple modules speech enhancement in mixed noise and low SNR environments

Tian Lan, Wenzheng Ye, Guoqiang Hui, Sen Li, Qiao Liu

Proceedings Volume 11384, Eleventh International Conference on Signal Processing Systems; 1138406 (2019) https://doi.org/10.1117/12.2559657
Event: Eleventh International Conference on Signal Processing Systems, 2019, Chengdu, China

Abstract

Achieving stationary speech enhancement in low signal-to-noise ratio (SNR) environments is a challenging problem. Because noise energy is dominant in noisy speech at low SNR level, the existence of numerous obvious random noises may lead neural network to forget some useful information obtained by early training. Moreover, it is difficult for a single neural network to obtain effective speech features and noise features. Therefore, this paper designs to utilize multiple neural networks in two stages to discriminately learn a certain type of noise features and reduce the introduction of interference. Experiment results demonstrate that proposed method leads to consistently better source-to-distortion ratio (SDR) and perceptual evaluation of speech quality (PESQ) than baseline models in low SNR condition. And the results indicate that the method can suppress the forgetting of early information of neural network.

Citation Download Citation

Tian Lan, Wenzheng Ye, Guoqiang Hui, Sen Li, and Qiao Liu "Multiple modules speech enhancement in mixed noise and low SNR environments", Proc. SPIE 11384, Eleventh International Conference on Signal Processing Systems, 1138406 (31 December 2019); https://doi.org/10.1117/12.2559657

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available