Text-independent speaker recognition using probabilistic SVM with GMM adjustment

Author

Hou, Fenglei ; Wang, Bingxi

Author_Institution

Dept. of Inf. Sci., Inf. Eng. Univ., Zhengzhou, China

fYear

2003

fDate

26-29 Oct. 2003

Firstpage

305

Lastpage

308

Abstract

There are two most popular techniques in pattern recognition, discriminative classifiers and generative model classifiers. Combining them together could improve the performance of the recognition system. We present a novel method for text-independent speaker recognition. This system uses the output of the Gaussian mixture model to adjust the probabilistic output of the support vector machine. The new probabilistic SVM/GMM model based speaker recognition system is tested on the NIST 2003 speaker recognition evaluation database. Results on text-independent speaker identification and verification are provided to demonstrate the effectiveness of such systems.

Keywords

Gaussian distribution; speaker recognition; support vector machines; Gaussian mixture model; discriminative classifiers; generative model classifiers; pattern recognition; probabilistic support vector machine; speaker identification; speaker verification; text-independent speaker recognition; Artificial neural networks; Databases; Hidden Markov models; Information science; NIST; Pattern recognition; Speaker recognition; Support vector machine classification; Support vector machines; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003 International Conference on

Conference_Location

Beijing, China

Print_ISBN

0-7803-7902-0

Type

conf

DOI

10.1109/NLPKE.2003.1275919

Filename

1275919