Third European Conference on Speech Communication and Technology

Berlin, Germany
September 22-25, 1993


Neural Models for Extracting Speaker Characteristics in Speech Modelization Systems

T. Artieres, P. Gallinari

LAFORIA-IBP UACNRS 1095, Université Paris 6, Paris, France

We analyze in this paper inherent limitations of prediction systems for speaker identification. We introduce different approaches for enhancing these systems and present results of tests on TIMIT with neural net predictive systems.

Keywords: speaker recognition, predictive neural networks, sequence classification

Full Paper

Bibliographic reference.  Artieres, T. / Gallinari, P. (1993): "Neural models for extracting speaker characteristics in speech modelization systems", In EUROSPEECH'93, 2263-2266.