DocumentCode :
730795
Title :
Cross-domain cooperative deep stacking network for speech separation
Author :
Wei Jiang ; Shan Liang ; Like Dong ; Hong Yang ; Wenju Liu ; Yunji Wang
Author_Institution :
Inst. of Autom., Beijing, China
fYear :
2015
fDate :
19-24 April 2015
Firstpage :
5083
Lastpage :
5087
Abstract :
Nowadays supervised speech separation has drawn much attention and shown great promise in the meantime. While there has been a lot of success, existing algorithms perform the task only in one preselected representative domain. In this study, we propose to perform the task in two different time-frequency domains simultaneously and cooperatively, which can model the implicit correlations between different representations of the same speech separation task. Besides, many time-frequency (T-F) units are dominated by noise in low signal-to-noise ratio (SNR) conditions, so more robust features are obtained by stacking features of original mixtures with that extracted from separated speech of each deep stacking network (DSN) block, which can be regarded as a denoised version of the original features. Quantitative experiments show that the proposed cross-domain cooperative deep stacking network (DSN-CDC) has enhanced modeling capability as well as generalization ability, which outperforms a previous algorithm based on standard deep neural networks.
Keywords :
feature extraction; neural nets; signal denoising; signal representation; source separation; speech processing; time-frequency analysis; DSN-CDC; SNR; T-F unit; cross-domain cooperative deep stacking neural network; robust feature extraction; signal-to-noise ratio; speech separation; time-frequency domain; Artificial neural networks; Noise reduction; Speech separation; cross-domain cooperative structure; deep neural network; deep stacking network;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on
Conference_Location :
South Brisbane, QLD
Type :
conf
DOI :
10.1109/ICASSP.2015.7178939
Filename :
7178939
Link To Document :
بازگشت