Text-Independent Speaker Verification Using Artificially Generated GMMs for Cohorts
Summary :
This paper presents a text-independent speaker verification method using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Artificial cohorts are used instead of those from speaker databases, and GMMs for artificial cohorts are generated by changing model parameters of the GMM for a claimed speaker. Equal error rates by the proposed method are about 60% less than those by a conventional method which also uses only utterances of enrolled speakers.
- Publication
- IEICE TRANSACTIONS on Information Vol.E91-D No.10 pp.2536-2539
- Publication Date
- 2008/10/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e91-d.10.2536
- Type of Manuscript
- LETTER
- Category
- Speech and Hearing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yuuji MUKAI, Hideki NODA, Michiharu NIIMI, Takashi OSANAI, "Text-Independent Speaker Verification Using Artificially Generated GMMs for Cohorts" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 10, pp. 2536-2539, October 2008, doi: 10.1093/ietisy/e91-d.10.2536.
Abstract: This paper presents a text-independent speaker verification method using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Artificial cohorts are used instead of those from speaker databases, and GMMs for artificial cohorts are generated by changing model parameters of the GMM for a claimed speaker. Equal error rates by the proposed method are about 60% less than those by a conventional method which also uses only utterances of enrolled speakers.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.10.2536/_p
Copy
@ARTICLE{e91-d_10_2536,
author={Yuuji MUKAI, Hideki NODA, Michiharu NIIMI, Takashi OSANAI, },
journal={IEICE TRANSACTIONS on Information},
title={Text-Independent Speaker Verification Using Artificially Generated GMMs for Cohorts},
year={2008},
volume={E91-D},
number={10},
pages={2536-2539},
abstract={This paper presents a text-independent speaker verification method using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Artificial cohorts are used instead of those from speaker databases, and GMMs for artificial cohorts are generated by changing model parameters of the GMM for a claimed speaker. Equal error rates by the proposed method are about 60% less than those by a conventional method which also uses only utterances of enrolled speakers.},
keywords={},
doi={10.1093/ietisy/e91-d.10.2536},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Text-Independent Speaker Verification Using Artificially Generated GMMs for Cohorts
T2 - IEICE TRANSACTIONS on Information
SP - 2536
EP - 2539
AU - Yuuji MUKAI
AU - Hideki NODA
AU - Michiharu NIIMI
AU - Takashi OSANAI
PY - 2008
DO - 10.1093/ietisy/e91-d.10.2536
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2008
AB - This paper presents a text-independent speaker verification method using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Artificial cohorts are used instead of those from speaker databases, and GMMs for artificial cohorts are generated by changing model parameters of the GMM for a claimed speaker. Equal error rates by the proposed method are about 60% less than those by a conventional method which also uses only utterances of enrolled speakers.
ER -
English
