Confidence based multiple classifier fusion in speaker verification

Author	dc.contributor.author	Huenupán, Fernando
Author	dc.contributor.author	Becerra Yoma, Néstor	es_CL
Author	dc.contributor.author	Molina, Carlos	es_CL
Author	dc.contributor.author	Garretón, Claudio	es_CL
Admission date	dc.date.accessioned	2010-01-26T19:02:49Z
Available date	dc.date.available	2010-01-26T19:02:49Z
Publication date	dc.date.issued	2008-05-01
Cita de ítem	dc.identifier.citation	PATTERN RECOGNITION LETTERS Volume: 29 Issue: 7 Pages: 957-966 Published: MAY 1 2008	en_US
Identifier	dc.identifier.issn	0167-8655
Identifier	dc.identifier.other	10.1016/j.patrec.2008.01.015
Identifier	dc.identifier.uri	https://repositorio.uchile.cl/handle/2250/125240
Abstract	dc.description.abstract	A novel framework that applies Bayes-based confidence measure for multiple classifier system fusion is proposed. Compared with ordinary Bayesian fusion, the presented approach can lead to reductions as high as 37% and 35% in EER and ROC curve area, respectively, in speaker verification.	en_US
Lenguage	dc.language.iso	en	en_US
Publisher	dc.publisher	ELSEVIER	en_US
Keywords	dc.subject	SPEECH RECOGNITION	en_US
Título	dc.title	Confidence based multiple classifier fusion in speaker verification	en_US
Document type	dc.type	Artículo de revista