Effects of device mismatch, language mismatch and environmental mismatch on speaker verification

Bin Ma; Helen M. Meng; Man Wai Mak

doi:10.1109/ICASSP.2007.366909

Effects of device mismatch, language mismatch and environmental mismatch on speaker verification

Bin Ma
, Helen M. Meng
, Man Wai Mak

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

11 Citations (Scopus)

Abstract

Device, language and environmental mismatch adversely affect speaker verification (SV) performance. We investigate such effects empirically based on the M3 (multibiometric, multilingual and multi-device) Corpus [1]. Device mismatch (among 3G phone, PocketPC and a desktop PC plug-in microphone) brings relative performance degradation of 523%; language mismatch (between English and Cantonese) brings 284% and environmental mismatch (between office environment and recording studio) brings 109%. In particular, verification with wide-band models on narrow-band test data outperforms narrow-band models on wide-band test data. The 3G phone's SV performance is generally low, but remains stable across environments. Additionally, durational variations within two-second utterances may cause a relative change of 633% in SV performance.

Original language	English
Title of host publication	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Volume	4
DOIs	https://doi.org/10.1109/ICASSP.2007.366909
Publication status	Published - 6 Aug 2007
Event	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, United States Duration: 15 Apr 2007 → 20 Apr 2007

Conference

Conference	2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Country/Territory	United States
City	Honolulu, HI
Period	15/04/07 → 20/04/07

Keywords

Biometrics corpus
M3 speaker verification evaluation
Speaker verification

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

More information

10.1109/ICASSP.2007.366909

Cite this

@inproceedings{b1b6b1ae4c74487688641b41dea87469,

title = "Effects of device mismatch, language mismatch and environmental mismatch on speaker verification",

abstract = "Device, language and environmental mismatch adversely affect speaker verification (SV) performance. We investigate such effects empirically based on the M3 (multibiometric, multilingual and multi-device) Corpus [1]. Device mismatch (among 3G phone, PocketPC and a desktop PC plug-in microphone) brings relative performance degradation of 523\%; language mismatch (between English and Cantonese) brings 284\% and environmental mismatch (between office environment and recording studio) brings 109\%. In particular, verification with wide-band models on narrow-band test data outperforms narrow-band models on wide-band test data. The 3G phone's SV performance is generally low, but remains stable across environments. Additionally, durational variations within two-second utterances may cause a relative change of 633\% in SV performance.",

keywords = "Biometrics corpus, M3 speaker verification evaluation, Speaker verification",

author = "Bin Ma and Meng, \{Helen M.\} and Mak, \{Man Wai\}",

year = "2007",

month = aug,

day = "6",

doi = "10.1109/ICASSP.2007.366909",

language = "English",

isbn = "1424407281",

volume = "4",

booktitle = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07",

note = "2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 ; Conference date: 15-04-2007 Through 20-04-2007",

}

Ma, B, Meng, HM & Mak, MW 2007, Effects of device mismatch, language mismatch and environmental mismatch on speaker verification. in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. vol. 4, 4218097, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, Honolulu, HI, United States, 15/04/07. https://doi.org/10.1109/ICASSP.2007.366909

Effects of device mismatch, language mismatch and environmental mismatch on speaker verification. / Ma, Bin; Meng, Helen M.; Mak, Man Wai.
2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07. Vol. 4 2007. 4218097.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Effects of device mismatch, language mismatch and environmental mismatch on speaker verification

AU - Ma, Bin

AU - Meng, Helen M.

AU - Mak, Man Wai

PY - 2007/8/6

Y1 - 2007/8/6

N2 - Device, language and environmental mismatch adversely affect speaker verification (SV) performance. We investigate such effects empirically based on the M3 (multibiometric, multilingual and multi-device) Corpus [1]. Device mismatch (among 3G phone, PocketPC and a desktop PC plug-in microphone) brings relative performance degradation of 523%; language mismatch (between English and Cantonese) brings 284% and environmental mismatch (between office environment and recording studio) brings 109%. In particular, verification with wide-band models on narrow-band test data outperforms narrow-band models on wide-band test data. The 3G phone's SV performance is generally low, but remains stable across environments. Additionally, durational variations within two-second utterances may cause a relative change of 633% in SV performance.

AB - Device, language and environmental mismatch adversely affect speaker verification (SV) performance. We investigate such effects empirically based on the M3 (multibiometric, multilingual and multi-device) Corpus [1]. Device mismatch (among 3G phone, PocketPC and a desktop PC plug-in microphone) brings relative performance degradation of 523%; language mismatch (between English and Cantonese) brings 284% and environmental mismatch (between office environment and recording studio) brings 109%. In particular, verification with wide-band models on narrow-band test data outperforms narrow-band models on wide-band test data. The 3G phone's SV performance is generally low, but remains stable across environments. Additionally, durational variations within two-second utterances may cause a relative change of 633% in SV performance.

KW - Biometrics corpus

KW - M3 speaker verification evaluation

KW - Speaker verification

UR - https://www.scopus.com/pages/publications/34547511149

U2 - 10.1109/ICASSP.2007.366909

DO - 10.1109/ICASSP.2007.366909

M3 - Conference article published in proceeding or book

SN - 1424407281

SN - 9781424407286

VL - 4

BT - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

T2 - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07

Y2 - 15 April 2007 through 20 April 2007

ER -

Effects of device mismatch, language mismatch and environmental mismatch on speaker verification

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this