DocumentCode
2957845
Title
Enhanced speech in noisy multiple speaker environment
Author
Kwan, C. ; Chu, S. ; Yin, J. ; Liu, X. ; Kruger, M. ; Sityar, I.
Author_Institution
Signal Process. Inc., Rockville, MD
fYear
2008
fDate
1-8 June 2008
Firstpage
1640
Lastpage
1643
Abstract
Noisy environments seriously degrade the performance of speech recognition systems. Here we implement a high performance speech enhancement algorithm. Data from speech separation challenge were used to evaluate the method. It was observed that the enhanced speech significantly improved the recognition performance. In 2 out of 4 SNR cases, over 100% relative percentage improvements were achieved. Standalone software prototype has been developed and evaluated.
Keywords
software prototyping; speech enhancement; speech recognition; high performance speech enhancement algorithm; noisy multiple speaker environment; speech recognition systems; speech separation challenge; standalone software prototype; Background noise; Degradation; Energy states; Filters; Microphones; Software prototyping; Speech analysis; Speech enhancement; Speech recognition; Working environment noise;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location
Hong Kong
ISSN
1098-7576
Print_ISBN
978-1-4244-1820-6
Electronic_ISBN
1098-7576
Type
conf
DOI
10.1109/IJCNN.2008.4634017
Filename
4634017
Link To Document