SVM-based Speaker Classification in the GMM Models Space

Author

Krause, Nir ; Gazit, Ran

Author_Institution

Persay Ltd.

fYear

2006

fDate

28-30 June 2006

Firstpage

1

Lastpage

5

Abstract

This paper describes a new approach to speaker classification, based on using an SVM classifier over the GMM models space. Adaptation of a speaker-independent GMM universal background model with speaker specific data creates a speaker-dependent GMM model. The vector representation of this model is used by an SVM classifier to recognize the speaker. When used with multiple, channel-specific background models, this scheme has the potential to improve speaker recognition performance in channel mismatch conditions. Performance improvement is demonstrated over a multi-channel corpus, as well as over the NIST 2004 evaluation data

Keywords

Gaussian distribution; signal classification; signal representation; speaker recognition; support vector machines; GMM; Gaussian mixture model; NIST 2004 evaluation data; SVM-based speaker classification; channel mismatch condition; multichannel corpus; speaker recognition; support vector machine; universal background model; vector representation; Cepstrum; Hilbert space; Kernel; NIST; Polynomials; Radio access networks; Speaker recognition; Support vector machine classification; Support vector machines; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Speaker and Language Recognition Workshop, 2006. IEEE Odyssey 2006: The

Conference_Location

San Juan

Print_ISBN

1-424400471-1

Electronic_ISBN

1-4244-0472-X

Type

conf

DOI

10.1109/ODYSSEY.2006.248138

Filename

4013555