Share Email Print

Proceedings Paper

Text-dependent speaker verification using data fusion and channel detection
Author(s): Khaled T. Assaleh; Kevin R. Farrell; M. S. Zilovic; Manish Sharma; Devang K. Naik; Richard J. Mammone
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new system is presented for text-dependent speaker verification. The system uses data fusion concepts to combine the results of distortion-based and discriminant-based classifiers. Hence, both intraspeaker and interspeaker information are utilized in the final decision. The distortion and discriminant-based classifiers used are dynamic time warping and the neural tree network, respectively. The system is evaluated with several hundred one word utterances collected over a telephone channel. All handsets considered in this experiment use electret microphones. The new system is found to perform exceptionally well for this task. A second experiment uses handsets having both electret and carbon button microphones. Here, a channel detection scheme is proposed that improves performance under these conditions.

Paper Details

Date Published: 25 October 1994
PDF: 11 pages
Proc. SPIE 2277, Automatic Systems for the Identification and Inspection of Humans, (25 October 1994); doi: 10.1117/12.191869
Show Author Affiliations
Khaled T. Assaleh, Rutgers Univ. and SPEAKEZ (United States)
Kevin R. Farrell, Rutgers Univ. and SPEAKEZ (United States)
M. S. Zilovic, Rutgers Univ. (United States)
Manish Sharma, Rutgers Univ. (United States)
Devang K. Naik, Rutgers Univ. (United States)
Richard J. Mammone, Rutgers Univ. and SPEAKEZ (United States)

Published in SPIE Proceedings Vol. 2277:
Automatic Systems for the Identification and Inspection of Humans
Richard J. Mammone; J. David Murley, Editor(s)

© SPIE. Terms of Use
Back to Top