Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Speaker Recognition in a Multi-Speaker Environment

Published

Author(s)

Alvin F. Martin, Mark A. Przybocki

Abstract

We discuss the multi-speaker tasks of detection, tracking, and segmentation of speakers as included in recent NIST Speaker Recognition Evaluations. We consider how performance for the two-speaker detection task is related to that for the corresponding one-speaker task. We examine the effects of target speaker speech duration and the gender mix within test segments on results for these tasks. We also relate performance results for the tracking and segmentation tasks, and look at factors affecting segmentation performance.
Proceedings Title
European Conference on Speech Communication and Technology | 7th | | ISCA
Volume
7th
Issue
2
Conference Dates
September 1, 2001
Conference Location
Aalborg, DE
Conference Title
Eurospeech

Keywords

detection cost, multi-speaker test data, NIST evaluations, performance evaluation, speaker detection, speaker identification, speaker recognition, speaker segmentation, speaker tracking

Citation

Martin, A. and Przybocki, M. (2001), Speaker Recognition in a Multi-Speaker Environment, European Conference on Speech Communication and Technology | 7th | | ISCA, Aalborg, DE, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=151526 (Accessed April 18, 2024)
Created September 1, 2001, Updated February 17, 2017