POLYCOST: A telephone-speech database for speaker recognition

Authors
Hennebert, J Melin, H Petrovska, D Genoud, D
Citation
J. Hennebert et al., POLYCOST: A telephone-speech database for speaker recognition, SPEECH COMM, 31(2-3), 2000, pp. 265-270
Citations number
4
Categorie Soggetti
Computer Science & Engineering
Journal title
SPEECH COMMUNICATION
ISSN journal
01676393 → ACNP
Volume
31
Issue
2-3
Year of publication
2000
Pages
265 - 270
Database
ISI
SICI code
0167-6393(200006)31:2-3<265:PATDFS>2.0.ZU;2-1
Abstract
This article presents an overview of the POLYCOST database dedicated to spe aker recognition applications over the telephone network. The main characte ristics of this database are: medium mixed speech corpus size (>100 speaker s), English spoken by foreigners, mainly digits with some free speech, coll ected through international telephone lines, and minimum of nine sessions f or 85% of the speakers. (C) 2000 Published by Elsevier Science B.V. All rig hts reserved.