Efficient Speaker Recognition based on Multi-class Twin Support Vector Machines and GMMs

Author

Cong, Hanhan ; Yang, Chengfu ; Pu, Xiaorong

Author_Institution

Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol., Chengdu

fYear

2008

fDate

21-24 Sept. 2008

Firstpage

348

Lastpage

352

Abstract

This paper proposes a new approach for text-independent speaker recognition using twin support vector machines (TWSVMs) and feature extraction based on Gaussian mixture models (GMMs). Because of the perfect discriminability and the ability of managing large scale dataset, the proposed approach performs better than the traditional support vector machines (SVMs) on Ahumada Biometric Database and Gaudi Biometric Database.

Keywords

Gaussian processes; speaker recognition; support vector machines; Ahumada Biometric Database; Gaudi Biometric Database; Gaussian mixture models; feature extraction; multi-class twin support vector machines; speaker recognition; Biometrics; Computational intelligence; Data mining; Feature extraction; Laboratories; Large-scale systems; Spatial databases; Speaker recognition; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics, Automation and Mechatronics, 2008 IEEE Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-1675-2

Electronic_ISBN

978-1-4244-1676-9

Type

conf

DOI

10.1109/RAMECH.2008.4681433

Filename

4681433

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3484183