DocumentCode
1436973
Title
Stereophonic speech recognition in noise using compensated hidden Markov models
Author
Brookes, D.M. ; Leung, M.H.
Author_Institution
Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
Volume
34
Issue
19
fYear
1998
fDate
9/17/1998 12:00:00 AM
Firstpage
1827
Lastpage
1829
Abstract
A novel procedure is presented for noise compensation in hidden Markov model speech recognisers. The procedure uses two microphone signals and, unlike previous approaches, does not require the noise spectrum to be stationary even in the short term. Results are presented showing that the performance of the compensated system equals or exceeds that obtained using matched training
Keywords
Markov processes; speech recognition; compensated hidden Markov models; matched training; microphone signals; stereophonic speech recognition;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
DOI
10.1049/el:19981271
Filename
722360
Link To Document