Speaker Verification using Vector Quantization and Hidden Markov Model

Author

Ilyas, Mohd Zaizu ; Samad, Salina Abdul ; Hussain, Aini ; Ishak, Khairul Anuar

Author_Institution

Univ. Kebangsaan Malaysia, Bangi

fYear

2007

fDate

12-11 Dec. 2007

Firstpage

1

Lastpage

5

Abstract

This paper presents a speaker verification system using a combination of vector quantization (VQ) and hidden Markov model (HMM) to improve the HMM performance. A Malay spoken digit database which contains 100 speakers is used for the testing and validation modules. It is shown that, by using the proposed combination technique, a total success rate (TSR) of 99.97% is achieved and it is an improvement of 11.24% in performance compared to HMM. For speaker verification, true speaker rejection rate, impostor acceptance rate and equal error rate (EER) are also improved significantly compared to HMM.

Keywords

hidden Markov models; speaker recognition; speech coding; vector quantisation; Malay spoken digit database; equal error rate; hidden Markov model; speaker verification; vector quantization; Access control; Application software; Artificial neural networks; Cepstrum; Databases; Hidden Markov models; Linear predictive coding; Research and development; Speech recognition; Vector quantization; Speaker recognition; hidden Markov model; speaker verification; vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Research and Development, 2007. SCOReD 2007. 5th Student Conference on

Conference_Location

Selangor, Malaysia

Print_ISBN

978-1-4244-1469-7

Electronic_ISBN

978-1-4244-1470-3

Type

conf

DOI

10.1109/SCORED.2007.4451419

Filename

4451419