A New Hybrid GMM/SVM for Speaker Verification

Author

Liu, Minghui ; Xie, Yanlu ; Yao, Zhiqiang ; Dai, Beiqian

Author_Institution

MOE-Microsoft Key Lab. of Multimedia Comput. & Commun., Univ. of Sci. & Technol. of China, Hefei

Volume

4

fYear

0

fDate

0-0 0

Firstpage

314

Lastpage

317

Abstract

This paper proposes a new combination approach between Gaussian mixture model (GMM) and support vector machine (SVM) by feature extraction based on adapted GMM for SVM in text-independent speaker verification. Because of excellent scalability, adapted GMM was used to extract a small quantity of typical feature vectors from large numbers of speech data for SVM speaker verification. Using this new combination approach, our speaker verification system performed significantly better than the current state-of-the-art GMM-UBM system on the NIST´04 Iside-Iside database

Keywords

Gaussian processes; feature extraction; speaker recognition; speech processing; support vector machines; Gaussian mixture model; feature extraction; feature vectors; hybrid GMM/SVM; speech data; support vector machine; text-independent speaker verification; Data mining; Feature extraction; Laboratories; Multimedia computing; Robustness; Scalability; Spatial databases; Speech; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.118

Filename

1699843