Speaker Recognition in a Multi-Speaker Environment

Published

September 1, 2001

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

Pub Type

Conferences

Download Paper

Local Download

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 October 15, 2025)