Text-Independent Speaker Verification in Embedded Environments

Author

Tydlitat, B. ; Navratil, J. ; Pelecanos, J.W. ; Ramaswamy, G.N.

Author_Institution

Voicee Technol. & Syst., IBM Czech Republic, Czech Republic

Volume

4

fYear

2007

fDate

15-20 April 2007

Abstract

A low-resource, text-independent speaker verification (SV) system with an efficient voice model compression technique is described, including its implementation exclusively with integer arithmetic. We describe and discuss the individual algorithmic steps, the integer implementation issues and its error analysis. Performance of the system is evaluated on data collected with iPaq devices and the impact of model compression as well as integer approximation on the accuracy is discussed.

Keywords

approximation theory; data compression; error analysis; speaker recognition; speech coding; embedded environments; error analysis; iPaq devices; integer approximation; integer arithmetic; text-independent speaker verification; voice model compression technique; Acoustic devices; Arithmetic; Cepstral analysis; Computer architecture; Degradation; Embedded system; Hardware; Personal digital assistants; Speech; Vectors; Speaker verification; embedded systems; integer arithmetic; voice model compression;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on

Conference_Location

Honolulu, HI

ISSN

1520-6149

Print_ISBN

1-4244-0727-3

Type

conf

DOI

10.1109/ICASSP.2007.366907

Filename

4218095