ESCA Workshop on Automatic Speaker Recognition, Identification, and Verification

Martigny, Switzerland
April 7-9, 1994

Connectionist Approaches for Automatic Speaker Recognition

Younès Bennani (1), Patrick Gallinari (2)

(1) LIPN, CNRS-URA 1507, University of Paris 13, France
(2) LAFORIA, CNRS-URA 1095, University of Paris 6, France

This article reviews current research on neural network systems for speaker recognition tasks. We consider two main approaches, the first one relies on direct classification and the second performs speaker modelization. The potential of connectionist models for speaker recognition is first presented and the main algorithms from the two families are then reviewed. We discuss their respective performances and potential for speaker recognition. We compare these techniques to more conventional methods like vector quantization and Hidden Markov models. The paper ends with a summary and suggestions.

Full Paper

Bibliographic reference.  Bennani, Younès / Gallinari, Patrick (1994): "Connectionist approaches for automatic speaker recognition", In ASRIV-1994, 95-102.