The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article traite de la vérification du locuteur (SV) à l'aide de modèles de mélange gaussien (GMM), où seuls les énoncés des locuteurs inscrits sont requis. Un tel système SV peut être réalisé en utilisant des cohortes générées artificiellement au lieu de cohortes réelles provenant de bases de données de locuteurs. Cet article présente une approche rationnelle pour définir les paramètres GMM pour les cohortes artificielles, basée sur les statistiques des paramètres GMM pour les cohortes réelles. Les taux d'erreur égaux pour la méthode proposée sont environ 10 % inférieurs à ceux de la méthode précédente, dans laquelle les paramètres GMM pour les cohortes artificielles étaient définis de manière ad hoc.
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.
Copier
Yuuji MUKAI, Hideki NODA, Takashi OSANAI, "Artificial Cohort Generation Based on Statistics of Real Cohorts for GMM-Based Speaker Verification" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 1, pp. 162-166, January 2011, doi: 10.1587/transinf.E94.D.162.
Abstract: This paper discusses speaker verification (SV) using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Such an SV system can be realized using artificially generated cohorts instead of real cohorts from speaker databases. This paper presents a rational approach to set GMM parameters for artificial cohorts based on statistics of GMM parameters for real cohorts. Equal error rates for the proposed method are about 10% less than those for the previous method, where GMM parameters for artificial cohorts were set in an ad hoc manner.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.162/_p
Copier
@ARTICLE{e94-d_1_162,
author={Yuuji MUKAI, Hideki NODA, Takashi OSANAI, },
journal={IEICE TRANSACTIONS on Information},
title={Artificial Cohort Generation Based on Statistics of Real Cohorts for GMM-Based Speaker Verification},
year={2011},
volume={E94-D},
number={1},
pages={162-166},
abstract={This paper discusses speaker verification (SV) using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Such an SV system can be realized using artificially generated cohorts instead of real cohorts from speaker databases. This paper presents a rational approach to set GMM parameters for artificial cohorts based on statistics of GMM parameters for real cohorts. Equal error rates for the proposed method are about 10% less than those for the previous method, where GMM parameters for artificial cohorts were set in an ad hoc manner.},
keywords={},
doi={10.1587/transinf.E94.D.162},
ISSN={1745-1361},
month={January},}
Copier
TY - JOUR
TI - Artificial Cohort Generation Based on Statistics of Real Cohorts for GMM-Based Speaker Verification
T2 - IEICE TRANSACTIONS on Information
SP - 162
EP - 166
AU - Yuuji MUKAI
AU - Hideki NODA
AU - Takashi OSANAI
PY - 2011
DO - 10.1587/transinf.E94.D.162
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2011
AB - This paper discusses speaker verification (SV) using Gaussian mixture models (GMMs), where only utterances of enrolled speakers are required. Such an SV system can be realized using artificially generated cohorts instead of real cohorts from speaker databases. This paper presents a rational approach to set GMM parameters for artificial cohorts based on statistics of GMM parameters for real cohorts. Equal error rates for the proposed method are about 10% less than those for the previous method, where GMM parameters for artificial cohorts were set in an ad hoc manner.
ER -