IEEE SIGNAL PROCESSING LETTERS;
IEEE Signal Process. Lett.

dc.creatorBecerra-Yoma, Nestor
dc.creatorCarrasco-Romo, Jorge
dc.creatorMolina-Sánchez, Carlos
dc.creatorMolina-Sánchez, Carlos
dc.date2017-04-27T18:52:59Z
dc.date2022-07-07T02:25:23Z
dc.date2017-04-27T18:52:59Z
dc.date2022-07-07T02:25:23Z
dc.date2005
dc.date.accessioned2023-08-22T23:56:36Z
dc.date.available2023-08-22T23:56:36Z
dc.identifier1558-2361
dc.identifierD02I1089
dc.identifierD02I1089
dc.identifierWOS:000232841200004
dc.identifier1070-9908
dc.identifierhttps://hdl.handle.net/10533/197804
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8353169
dc.descriptionIn this letter, Bayes-based confidence measure (BBCM) in speech recognition is proposed. BBCM is applicable to any standard word feature and makes use of information about the speech recognition engine performance. In contrast to ordinary confidence measures, BBCM is a probability, which is interesting itself from the practical and theoretical point of view. If applied with word density confidence measure (WDCM), BBCM dramatically improves the discrimination ability of the false acceptance curve when compared to WDCM itself.
dc.description0
dc.description10
dc.descriptionFONDEF
dc.descriptionnbecerra@ing.uchile.cl
dc.description0
dc.description11
dc.descriptionFONDEF
dc.description12
dc.languageENG
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relationinstname: Conicyt
dc.relationreponame: Repositorio Digital RI2.0
dc.relationinstname: Conicyt
dc.relationreponame: Repositorio Digital RI2.0
dc.relationinfo:eu-repo/grantAgreement/Fondef/D02I1089
dc.relationinfo:eu-repo/semantics/dataset/hdl.handle.net/10533/93477
dc.rightsinfo:eu-repo/semantics/openAccess
dc.titleBayes-based confidence measure in speech recognition
dc.titleIEEE SIGNAL PROCESSING LETTERS
dc.titleIEEE Signal Process. Lett.
dc.typeArticulo
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.coveragePISCATAWAY


Este ítem pertenece a la siguiente institución