5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Text-Independent Speaker Identification and Verification Using the TIMIT Database

Nuala C. Ward (1), Dominik R. Dersch (2)

(1) Alcatel Australia, Australia
(2) Department of Electrical Engineering, University of Sydney, Australia

This paper presents a neural network inspired approach to speaker recognition using speaker models constructed from full data sets. A similarity measure between data sets is used for text-independent speaker identification and verification. In order to reduce the computational effort in calculating the similarity measure, a fuzzy Vector Quantisation procedure is applied. This method has previously been successfully applied to a database of 108 Australian English speakers. The purpose of this paper is to apply this method to a larger benchmark database of 630 speakers (TIMIT Database). Using the full 630-speaker database, an accuracy of 98.2% (one test sentence) and 99.7% (two test sentences) was achieved for text-independent speaker identification. On a 462-speaker subset of the database a 98.5% successful acceptance and 96.9% successful rejection rate for text-independent speaker verification was achieved.

Full Paper

Bibliographic reference.  Ward, Nuala C. / Dersch, Dominik R. (1998): "Text-independent speaker identification and verification using the TIMIT database", In ICSLP-1998, paper 0291.