Evaluation of GMM-based features for SVM speaker verification

Author

Liu, Minghui ; Huang, Zhongwei

Author_Institution

Phonetic Lab., Shenzhen Univ., Shenzhen

fYear

2008

fDate

25-27 June 2008

Firstpage

5027

Lastpage

5030

Abstract

This paper compares several feature extraction approaches based on Gaussian mixture model (GMM) for support vector machine (SVM) in text-independent speaker verification. Because of excellent scalability, GMM can be used to extract fixed number of typical feature vectors from various length speech data. Experiments with different GMM-based features in SVM speaker verification system were performed on the NISTpsila04 1side-1side database and compared with the baseline GMM-UBM.

Keywords

Gaussian processes; feature extraction; speaker recognition; support vector machines; Gaussian mixture model; NISTpsila04 1side-1side database; feature extraction approaches; support vector machine; text-independent speaker verification; Automation; Data mining; Feature extraction; Intelligent control; Laboratories; Scalability; Spatial databases; Speech; Support vector machine classification; Support vector machines; Gaussian Mixture Model; SVM; Speaker verification; feature extraction;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4244-2113-8

Electronic_ISBN

978-1-4244-2114-5

Type

conf

DOI

10.1109/WCICA.2008.4593744

Filename

4593744

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2490950