Emotional adaptive training for speaker verification

Biblos-e Archivo/Manakin Repository

Show simple item record

dc.contributor.author Bie, Fanhu
dc.contributor.author Wang, Dong
dc.contributor.author Zheng, Thomas Fang
dc.contributor.author Tejedor Noguerales, Javier
dc.contributor.author Chen, Ruxin
dc.contributor.other UAM. Departamento de Tecnología Electrónica y de las Comunicaciones es_ES
dc.date.accessioned 2015-05-27T15:27:33Z
dc.date.available 2015-05-27T15:27:33Z
dc.date.issued 2013-12
dc.identifier.citation Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. APSIPA 2013, IEEE, 2013. 1-4 en_US
dc.identifier.uri http://hdl.handle.net/10486/666433
dc.description Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Bie, F., Wang, D., Zheng, T.F., Tejedor, J., Chen, R. "Emotional adaptive training for speaker verification", in Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific, 2013, pp. 1-4 en_US
dc.description.abstract Speaker verification suffers from significant performance degradation with emotion variation. In a previous study, we have demonstrated that an adaptation approach based on MLLR/CMLLR can provide a significant performance improvement for verification on emotional speech. This paper follows this direction and presents an emotional adaptive training (EAT) approach. This approach iteratively estimates the emotion-dependent CMLLR transformations and re-trains the speaker models with the transformed speech, which therefore can make use of emotional enrollment speech to train a stronger speaker model. This is similar to the speaker adaptive training (SAT) in speech recognition. The experiments are conducted on an emotional speech database which involves speech recordings of 30 speakers in 5 emotions. The results demonstrate that the EAT approach provides significant performance improvements over the baseline system where the neutral enrollment data are used to train the speaker models and the emotional test utterances are verified directly. The EAT also outperforms another two emotionadaptation approaches in a significant way: (1) the CMLLR-based approach where the speaker models are trained with the neutral enrollment speech and the emotional test utterances are transformed by CMLLR in verification; (2) the MAP-based approach where the emotional enrollment data are used to train emotion-dependent speaker models and the emotional utterances are verified based on the emotion-matched models. en_US
dc.description.sponsorship This work was supported by the National Natural Science Foundation of China under Grant No. 61271389 and the National Basic Research Program (973 Program) of China under Grant No. 2013CB329302. en_US
dc.format.extent 5 pág. es_ES
dc.format.mimetype application/pdf en
dc.language.iso eng en
dc.publisher Institute of Electrical and Electronics Engineers en_US
dc.rights © 2013 IEEE en_US
dc.subject.other Adaptation models en_US
dc.subject.other Computers en_US
dc.subject.other Data models en_US
dc.subject.other Hidden Markov models en_US
dc.subject.other Spectrogram en_US
dc.title Emotional adaptive training for speaker verification en_US
dc.type conferenceObject en
dc.subject.eciencia Informática es_ES
dc.subject.eciencia Telecomunicaciones es_ES
dc.relation.publisherversion http://dx.doi.org/10.1109/APSIPA.2013.6694123
dc.identifier.doi 10.1109/APSIPA.2013.6694123
dc.identifier.publicationfirstpage 1
dc.identifier.publicationlastpage 4
dc.relation.eventdate October 29- November 1, 2013 en_US
dc.relation.eventplace Kaohsiung (Taiwan) en_US
dc.relation.eventtitle Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 en_US
dc.type.version info:eu-repo/semantics/acceptedVersion en
dc.contributor.group Laboratorio de Tecnología Hombre-Computador (ING EPS-010) es_ES
dc.rights.accessRights openAccess en
dc.authorUAM Tejedor Noguerales, Javier (261273)


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record