DocumentCode :
820071
Title :
Hybrid KLT/GMM approach for robust speaker identification
Author :
Chen, C.C.T. ; Chen, C.T. ; Cheng, P.W.
Author_Institution :
Dept. of Electr. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan
Volume :
39
Issue :
21
fYear :
2003
Firstpage :
1552
Lastpage :
1554
Abstract :
A classification scheme that incorporates both the Karhunen-Loeve transform and the Gaussian mixture model for robust speaker identification is proposed. Two hundred speakers from the TIMIT database degraded by noise are used for system evaluation. It is demonstrated that accuracy improvement up to 41% and computational saving up to seven times compared to the conventional GMM model can be achieved.
Keywords :
Karhunen-Loeve transforms; pattern classification; speaker recognition; Gaussian mixture model; Karhunen-Loeve transform; TIMIT database; accuracy improvement; classification scheme; computational saving; hybrid KLT/GMM approach; robust speaker identification; system evaluation;
fLanguage :
English
Journal_Title :
Electronics Letters
Publisher :
iet
ISSN :
0013-5194
Type :
jour
DOI :
10.1049/el:20030925
Filename :
1242827
Link To Document :
بازگشت