Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

A Hierarchical Approach to Large-Scale Speaker Recognition

Homayoon S. M. Beigi, Stéphane H. Maes, Upendra V. Chaudhari, Jeffrey S. Sorensen

Human Language Technologies Group, IBM Research, T.J. Watson Center P.O. Box 218, Yorktown Heights, NY, USA

This paper presents a hierarchical approach to the Large-Scale Speaker Recognition problem. In here the authors present a binary tree data-base approach for arranging the trained speaker models based on a distance measure designed for comparing two sets of distributions. The combination of this hierarchical structure and the distance measure [1] provide the means for conducting a large-scale verification task. In addition, two techniques are presented for creating a model of the complement-space to the cohort which is used for rejection purposes. Results are presented for the drastic improvements achieved mainly in reducing the false-acceptance of the speaker verification system without any significant false-rejection degradation.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Beigi, Homayoon S. M. / Maes, Stéphane H. / Chaudhari, Upendra V. / Sorensen, Jeffrey S. (1999): "A hierarchical approach to large-scale speaker recognition", In EUROSPEECH'99, 2203-2206.