Using jitter and shimmer in speaker verification

Jitter and shimmer are measures of the fundamental frequency and amplitude cycle-to-cycle variations, respectively. Both features have been largely used for the description of pathological voices, and since they characterise some aspects concerning particular voices, they are expected to have a cert...

Descripción completa

Detalles Bibliográficos
Autores: Farrús, Mireia, Hernando, Javier
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2009
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/32737
Acceso en línea:http://hdl.handle.net/10230/32737
http://dx.doi.org/10.1049/iet-spr.2008.0147
Access Level:acceso abierto
Palabra clave:Support vector machines
Jitter
Speaker recognition
id ES_7bc9dde29ccfc1aae3e060abf65ffce0
oai_identifier_str oai:recercat.cat:10230/32737
network_acronym_str ES
network_name_str España
repository_id_str
spelling Using jitter and shimmer in speaker verificationFarrús, MireiaHernando, JavierSupport vector machinesJitterSpeaker recognitionJitter and shimmer are measures of the fundamental frequency and amplitude cycle-to-cycle variations, respectively. Both features have been largely used for the description of pathological voices, and since they characterise some aspects concerning particular voices, they are expected to have a certain degree of speaker specificity. In the current work, jitter and shimmer are successfully used in a speaker verification experiment. Moreover, both measures are combined with spectral and prosodic features using several types of normalisation and fusion techniques in order to obtain better verification results. The overall speaker verification system is also improved by using histogram equalisation as a normalisation technique previous to fusing the features by SVM.This work has been supported by the Spanish Government under Grant AP2003-3598. The authors would like to thank Pascual Ejarque and Andrey Temko for his help in the fusion techniques used in this work.Institution of Engineering and Technology (IET)201720172009info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/32737http://dx.doi.org/10.1049/iet-spr.2008.0147reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésIET Signal Process. 2009;3(4):247-57.© The Institution of Engineering and Technologyinfo:eu-repo/semantics/openAccessoai:recercat.cat:10230/327372026-05-29T05:05:01Z
dc.title.none.fl_str_mv Using jitter and shimmer in speaker verification
title Using jitter and shimmer in speaker verification
spellingShingle Using jitter and shimmer in speaker verification
Farrús, Mireia
Support vector machines
Jitter
Speaker recognition
title_short Using jitter and shimmer in speaker verification
title_full Using jitter and shimmer in speaker verification
title_fullStr Using jitter and shimmer in speaker verification
title_full_unstemmed Using jitter and shimmer in speaker verification
title_sort Using jitter and shimmer in speaker verification
dc.creator.none.fl_str_mv Farrús, Mireia
Hernando, Javier
author Farrús, Mireia
author_facet Farrús, Mireia
Hernando, Javier
author_role author
author2 Hernando, Javier
author2_role author
dc.subject.none.fl_str_mv Support vector machines
Jitter
Speaker recognition
topic Support vector machines
Jitter
Speaker recognition
description Jitter and shimmer are measures of the fundamental frequency and amplitude cycle-to-cycle variations, respectively. Both features have been largely used for the description of pathological voices, and since they characterise some aspects concerning particular voices, they are expected to have a certain degree of speaker specificity. In the current work, jitter and shimmer are successfully used in a speaker verification experiment. Moreover, both measures are combined with spectral and prosodic features using several types of normalisation and fusion techniques in order to obtain better verification results. The overall speaker verification system is also improved by using histogram equalisation as a normalisation technique previous to fusing the features by SVM.
publishDate 2009
dc.date.none.fl_str_mv 2009
2017
2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/32737
http://dx.doi.org/10.1049/iet-spr.2008.0147
url http://hdl.handle.net/10230/32737
http://dx.doi.org/10.1049/iet-spr.2008.0147
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IET Signal Process. 2009;3(4):247-57.
dc.rights.none.fl_str_mv © The Institution of Engineering and Technology
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © The Institution of Engineering and Technology
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institution of Engineering and Technology (IET)
publisher.none.fl_str_mv Institution of Engineering and Technology (IET)
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411541286125568
score 15,81155

Similares en LA Referencia