DocumentCode :
1281015
Title :
Speaker adaptation technique for HMM model
Author :
Kwong, S. ; He, Q.-H. ; Man, K.F. ; Tang, K.S.
Author_Institution :
City Univ. of Hong Kong, Kowloon, Hong Kong
Volume :
35
Issue :
21
fYear :
1999
fDate :
10/14/1999 12:00:00 AM
Firstpage :
1817
Lastpage :
1818
Abstract :
A new speaker adaptation technique for the hidden Markov model (HMM) based on the maximum model distance (Kwong, 1998; He, 1999) approach is presented. Experimental results have shown that this technique provides good performance even with a small amount of adaptation data. When these results are compared with those from the Baum-Welch approach and the stochastic matching approaches (Sank, 1996), it is found that the presented approach provides the best performance
Keywords :
hidden Markov models; speaker recognition; HMM model; adaptation data; hidden Markov model; maximum model distance; speaker adaptation technique;
fLanguage :
English
Journal_Title :
Electronics Letters
Publisher :
iet
ISSN :
0013-5194
Type :
jour
DOI :
10.1049/el:19991273
Filename :
809990
Link To Document :
بازگشت