TY  - CONF
ID  - petr98:ips
T1  - Text-Independent Speaker Verification Using Automatically Labelled Acoustic Segments
A1  - Petrovska, Dijana
A1  - Cernocky, Jan
A1  - Hennebert, Jean
A1  - Chollet, Gérard
TI  - Advances in Phonetics, Proc. of the International Phonetic Sciences conference, Western Washington Univ., Bellingham
Y1  - 1998
SP  - 129
EP  - 136
UR  - http://diuf.unifr.ch/people/henneber/cv/download/sv_automatic_segment_ips_1998.pdf
KW  - Biometrics
KW  - Speaker Verification
N2  - Most of text-independent speaker verification techniques are based on modelling the global probability distribution function (pdf) of speakers in the acoustic vector space. Our paper presents an alternative to this approach with a class-dependent verification system using automatically determined segmental units.
ER  -