Support vector machines approaches and its application to speaker identification

Author

Boujelbene, S. Zribi ; Mezghani, D. Ben Ayed ; Ellouze, N.

Author_Institution

Inf. Dept., FSHST, Tunisia

fYear

2009

Firstpage

662

Lastpage

667

Abstract

This paper proposes a classification approach that incorporates the statistical methods GMM and support vector machines. The proposed GMM-SVM system is presented and experimentally evaluated on text independent speaker identification. Our results prove that the combination approach GMM-SVM is significantly superior than SVM approach. We report improvements of 85,37% amelioration in identification rate compared to the SVM identification rate.

Keywords

Gaussian processes; speaker recognition; statistical analysis; support vector machines; GMM-SVM system; gaussian mixture model; statistical method; support vector machine approach; text independent speaker identification; Ecosystems; Electronic mail; Gaussian processes; Informatics; Intersymbol interference; Power system modeling; Speaker recognition; Speech; Support vector machine classification; Support vector machines; Gaussian mixture models; speaker identification; support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Ecosystems and Technologies, 2009. DEST '09. 3rd IEEE International Conference on

Conference_Location

Istanbul

Print_ISBN

978-1-4244-2345-3

Electronic_ISBN

978-1-4244-2346-0

Type

conf

DOI

10.1109/DEST.2009.5276751

Filename

5276751

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1615402