POLYCOST: A telephone-speech database for speaker recognition

J. Hennebert; H. Melin; D. Petrovska; D. Genoud

doi:10.1016/S0167-6393(99)00082-5

POLYCOST: A telephone-speech database for speaker recognition

J. Hennebert
, H. Melin
, D. Petrovska
, D. Genoud

Institute of the Physics of Biological Systems
ENAC-IIC-GEL
KTH Royal Institute of Technology
Idiap Research Institute

Research output: Contribution to journal › Article › peer-review

41 Citations (Scopus)

Abstract

This article presents an overview of the POLYCOST database dedicated to speaker recognition applications over the telephone network. The main characteristics of this database are: medium mixed speech corpus size (>100 speakers), English spoken by foreigners, mainly digits with some free speech, collected through international telephone lines, and minimum of nine sessions for 85% of the speakers.

Original language	English
Pages (from-to)	265-270
Number of pages	6
Journal	Speech Communication
Volume	31
Issue number	2
DOIs	https://doi.org/10.1016/S0167-6393(99)00082-5
Publication status	Published - 1 Jan 2000
Externally published	Yes

Access to Document

10.1016/S0167-6393(99)00082-5

Cite this

@article{e92ebd837d694cb2b49748b7ef74e288,

title = "POLYCOST: A telephone-speech database for speaker recognition",

abstract = "This article presents an overview of the POLYCOST database dedicated to speaker recognition applications over the telephone network. The main characteristics of this database are: medium mixed speech corpus size (>100 speakers), English spoken by foreigners, mainly digits with some free speech, collected through international telephone lines, and minimum of nine sessions for 85\% of the speakers.",

author = "J. Hennebert and H. Melin and D. Petrovska and D. Genoud",

year = "2000",

month = jan,

day = "1",

doi = "10.1016/S0167-6393(99)00082-5",

language = "English",

volume = "31",

pages = "265--270",

journal = "Speech Communication",

issn = "0167-6393",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - POLYCOST

T2 - A telephone-speech database for speaker recognition

AU - Hennebert, J.

AU - Melin, H.

AU - Petrovska, D.

AU - Genoud, D.

PY - 2000/1/1

Y1 - 2000/1/1

N2 - This article presents an overview of the POLYCOST database dedicated to speaker recognition applications over the telephone network. The main characteristics of this database are: medium mixed speech corpus size (>100 speakers), English spoken by foreigners, mainly digits with some free speech, collected through international telephone lines, and minimum of nine sessions for 85% of the speakers.

AB - This article presents an overview of the POLYCOST database dedicated to speaker recognition applications over the telephone network. The main characteristics of this database are: medium mixed speech corpus size (>100 speakers), English spoken by foreigners, mainly digits with some free speech, collected through international telephone lines, and minimum of nine sessions for 85% of the speakers.

U2 - 10.1016/S0167-6393(99)00082-5

DO - 10.1016/S0167-6393(99)00082-5

M3 - Article

AN - SCOPUS:0033729411

SN - 0167-6393

VL - 31

SP - 265

EP - 270

JO - Speech Communication

JF - Speech Communication

IS - 2

ER -

POLYCOST: A telephone-speech database for speaker recognition

Abstract

Access to Document

Fingerprint

Cite this