Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

Text-Dependent Speaker Verification Using Dynamic Time Warping and Vector Quantization of LSF

J.-L. Bonifas (1), I. Hernaez Rioja (2), B. Etxebarria Gonzalez (2), S. Saoudi (1)

(1) Ecole Nationale Superieure des telecommunications de Bretagne (Dpt. S.C.), Brest, France
(2) Escuela Tecnica Superior de Ingenieros Industrials e Ingenieros de Telecomunicacion, Dpto de Electronica y Telecomunicaciones, Bilbao, Spain

This paper describes a text-dependent speaker verification system based on the use of DTW and VQ connected in series. It describes the algorithms and the extraction of the used LSF parameters. This way of using two classical algorithms makes it possible to reach high discrimination rates and particularly to eliminate the most dangerous category of impostors: those who could enter without knowing someone else's key. By this means, the system performances obtain a 95% recognition rate versus 2.3% false admission rate for a database recorded over telephone lines.

Full Paper

Bibliographic reference.  Bonifas, J.-L. / Hernaez Rioja, I. / Etxebarria Gonzalez, B. / Saoudi, S. (1995): "Text-dependent speaker verification using dynamic time warping and vector quantization of LSF", In EUROSPEECH-1995, 359-362.