DocumentCode :
467843
Title :
A Second-Order Feature Window Method for Blind Separation of Speech Signals Corrupted by Color Noise
Author :
Liu, Yu-Lin ; Xu, Shun ; Li, Ming-Qi
Author_Institution :
Chongqing Commun. Coll., Chongqing
Volume :
6
fYear :
2007
fDate :
19-22 Aug. 2007
Firstpage :
3454
Lastpage :
3458
Abstract :
A second-order feature window (SOFW) method is proposed for blind separation of speech signals corrupted by color background noise based on the short-time stationarity property of speech signals. At first the new prewhitening algorithm is developed to remove the effect of color noise, then the prewhitened data is partitioned continually by feature window with the length equal to the cycle of the fundamental tone of speech signals, after that the speech signal can be separated blindly by estimating the Givens rotation parameters based on the joint approximately diagonalization theory. This novel second order statistics-based method exploits the temporal structure inherent in speech signals, it is simple and can be used as the preprocessing stage for speech recognition systems. Simulation results show that it outperforms the existing typical blind source separation algorithm for speech signals contaminated by color noise.
Keywords :
blind source separation; noise; speech processing; blind source separation algorithm; color background noise; diagonalization theory; prewhitened data; prewhitening algorithm; second-order feature window method; speech recognition system; speech signal blind separation; Background noise; Blind source separation; Colored noise; Cybernetics; Digital signal processing; Machine learning; Source separation; Speech enhancement; Speech recognition; Statistical distributions; Blind separation; Color noise; Second-order feature window method; Speech signals;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
Type :
conf
DOI :
10.1109/ICMLC.2007.4370745
Filename :
4370745
Link To Document :
بازگشت