Speaker verification for home security system

Author

Ang, Kwok K. ; Kot, Alex C.

Author_Institution

Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore

fYear

1997

fDate

2-4 Dec 1997

Firstpage

27

Lastpage

30

Abstract

In this paper, we attempt to develop a reliable speaker verification algorithm that is suitable for use in a home security system. A phoneme-based hidden Markov model (HMM) has been adopted for the task of speaker verification with linear predictive cepstral coefficients (LPCC) as feature vectors for our model. Individual codebooks, designed to enhance performance, are also generated for all speakers in the test database. A simple way of combining the individual phoneme scores for text independent verification is also proposed. An equal error rate (ERR) of 10.5% has been achieved using the best phoneme model and 4.5% when using the combined scores of a 4-phoneme set

Keywords

biometrics (access control); cepstral analysis; feature extraction; hidden Markov models; linear predictive coding; speaker recognition; speech coding; 4-phoneme set; ERR; HMM; LPCC; best phoneme model; codebooks; equal error rate; feature vectors; home security system; linear predictive cepstral coefficients; phoneme scores; phoneme-based hidden Markov model; speaker verification; Biometrics; Data security; Hidden Markov models; Information security; Predictive models; Reliability engineering; Robustness; Spatial databases; Testing; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics, 1997. ISCE '97., Proceedings of 1997 IEEE International Symposium on

Print_ISBN

0-7803-4371-9

Type

conf

DOI

10.1109/ISCE.1997.658343

Filename

658343