ICSI´S 2005 speaker recognition system

Author

Mirghafori, Nikki ; Hatch, Andrew O. ; Stafford, Steven ; Boakye, Kofi ; Gillick, Daniel ; Peskin, Barbara

Author_Institution

Int. Comput. Sci. Inst., Berkeley, CA

fYear

2005

fDate

27-27 Nov. 2005

Firstpage

23

Lastpage

28

Abstract

This paper describes ICSI´s 2005 speaker recognition system, which was one of the top performing systems in the NIST 2005 speaker recognition evaluation. The system is a combination of four sub-systems: 1) a keyword conditional HMM system, 2) an SVM-based lattice phone n-gram system, 3) a sequential nonparametric system, and 4) a traditional cepstral GMM System, developed by SRI. The first three systems are designed to take advantage of higher-level and long-term information. We observe that their performance is significantly improved when there is more training data. In this paper, we describe these sub-systems and present results for each system alone and in combination on the speaker recognition evaluation (SRE) 2005 development and evaluation data sets

Keywords

Gaussian processes; cepstral analysis; hidden Markov models; speaker recognition; support vector machines; Gaussian mixture model; HMM system; SVM; cepstral GMM System; lattice phone n-gram system; sequential nonparametric system; speaker recognition evaluation; speaker recognition system; Cepstral analysis; Computer science; Hidden Markov models; Lattices; NIST; Performance evaluation; Power system modeling; Speaker recognition; Testing; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding, 2005 IEEE Workshop on

Conference_Location

San Juan

Print_ISBN

0-7803-9478-X

Electronic_ISBN

0-7803-9479-8

Type

conf

DOI

10.1109/ASRU.2005.1566512

Filename

1566512