SVM-Based Text-Independent Speaker Verification Using Derivative Kernel in the Reference GMM Space

Author

Xu, Minqiang ; Dai, Beiqian ; Xu, Dongxing ; Yang, Shiqing ; Liu, Qingsong

Author_Institution

Dept. of Electron. Sci. & Technol., Univ. of Sci. & Technol. of China, Hefei

fYear

2008

fDate

23-25 May 2008

Firstpage

422

Lastpage

425

Abstract

This paper proposes a new SVM-based method for text-independent speaker verification using derivative kernel in the reference Gaussian mixture model (GMM) space. The model for speaker utilizes the power of SVM and GMM, reference GMM used first, and then SVM followed. Using the reference GMM, not only clusters and compacts the speech, but also distinguishes the reference speaker and imposters. Then, derivative kernel combines SVM and GMM effectively. Experiments on text-independent speaker verification on NIST SRE 2001 dataset show that the equal error rate (EER) of the new method is reduced to 6.51% from 9.88%.

Keywords

Gaussian processes; speaker recognition; support vector machines; SVM-based text-independent speaker verification; derivative kernel; reference Gaussian mixture model space; support vector machine; Information processing; Kernel; NIST; Power generation; Power system modeling; Robustness; Space technology; Speech; Support vector machine classification; Support vector machines; Derivative Kernel; Gaussian Mixture Models; Speaker Verification; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Processing (ISIP), 2008 International Symposiums on

Conference_Location

Moscow

Print_ISBN

978-0-7695-3151-9

Type

conf

DOI

10.1109/ISIP.2008.124

Filename

4554125