Objective quality evaluation in blind source separation for speech recognition in a real room

Autores
Di Persia, Leandro Ezequiel; Yanagida, Masuzo; Rufiner, Hugo Leonardo; Milone, Diego Humberto
Año de publicación
2007
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The determination of quality of the signals obtained by blind source separation is a very important subject fordevelopment and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic speechrecognition, the quality measure of separation applied for assessment should be related to the recognition rates of thesystem. Many measures have been used for quality evaluation, but in general these have been applied without priorresearch of their capabilities as quality measures in the context of blind source separation, and often they requireexperimentation in unrealistic conditions. Moreover, these measures just try to evaluate the amount of separation, and thisvalue could not be directly related to recognition rates. Presented in this work is a study of several objective qualitymeasures evaluated as predictors of recognition rate of a continuous speech recognizer. Correlation between qualitymeasures and recognition rates is analyzed for a separation algorithm applied to signals recorded in a real room withdifferent reverberation times and different kinds and levels of noise. A very good correlation between weighted spectralslope measure and the recognition rate has been verified from the results of this analysis. Furthermore, a good performanceof total relative distortion and cepstral measures for rooms with relatively long reverberation time has been observed
Fil: Di Persia, Leandro Ezequiel. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Yanagida, Masuzo. Doshisha University; Japón
Fil: Rufiner, Hugo Leonardo. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Milone, Diego Humberto. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
Quality Measures
Blind Source Separation
Robust Speech Recognition
Reverberation
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/113586
Acceder
id CONICETDig_7f6f091d62b5b08ae7804f41eb3a73c7
oai_identifier_str oai:ri.conicet.gov.ar:11336/113586
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Objective quality evaluation in blind source separation for speech recognition in a real roomDi Persia, Leandro EzequielYanagida, MasuzoRufiner, Hugo LeonardoMilone, Diego HumbertoQuality MeasuresBlind Source SeparationRobust Speech RecognitionReverberationhttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2The determination of quality of the signals obtained by blind source separation is a very important subject fordevelopment and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic speechrecognition, the quality measure of separation applied for assessment should be related to the recognition rates of thesystem. Many measures have been used for quality evaluation, but in general these have been applied without priorresearch of their capabilities as quality measures in the context of blind source separation, and often they requireexperimentation in unrealistic conditions. Moreover, these measures just try to evaluate the amount of separation, and thisvalue could not be directly related to recognition rates. Presented in this work is a study of several objective qualitymeasures evaluated as predictors of recognition rate of a continuous speech recognizer. Correlation between qualitymeasures and recognition rates is analyzed for a separation algorithm applied to signals recorded in a real room withdifferent reverberation times and different kinds and levels of noise. A very good correlation between weighted spectralslope measure and the recognition rate has been verified from the results of this analysis. Furthermore, a good performanceof total relative distortion and cepstral measures for rooms with relatively long reverberation time has been observedFil: Di Persia, Leandro Ezequiel. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Yanagida, Masuzo. Doshisha University; JapónFil: Rufiner, Hugo Leonardo. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Milone, Diego Humberto. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaElsevier Science2007-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/113586Di Persia, Leandro Ezequiel; Yanagida, Masuzo; Rufiner, Hugo Leonardo; Milone, Diego Humberto; Objective quality evaluation in blind source separation for speech recognition in a real room; Elsevier Science; Signal Processing; 87; 8; 12-2007; 1951-19650165-1684CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.sigpro.2007.02.004info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T15:46:08Zoai:ri.conicet.gov.ar:11336/113586instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-10-15 15:46:08.324CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Objective quality evaluation in blind source separation for speech recognition in a real room
title Objective quality evaluation in blind source separation for speech recognition in a real room
spellingShingle Objective quality evaluation in blind source separation for speech recognition in a real room
Di Persia, Leandro Ezequiel
Quality Measures
Blind Source Separation
Robust Speech Recognition
Reverberation
title_short Objective quality evaluation in blind source separation for speech recognition in a real room
title_full Objective quality evaluation in blind source separation for speech recognition in a real room
title_fullStr Objective quality evaluation in blind source separation for speech recognition in a real room
title_full_unstemmed Objective quality evaluation in blind source separation for speech recognition in a real room
title_sort Objective quality evaluation in blind source separation for speech recognition in a real room
dc.creator.none.fl_str_mv Di Persia, Leandro Ezequiel
Yanagida, Masuzo
Rufiner, Hugo Leonardo
Milone, Diego Humberto
author Di Persia, Leandro Ezequiel
author_facet Di Persia, Leandro Ezequiel
Yanagida, Masuzo
Rufiner, Hugo Leonardo
Milone, Diego Humberto
author_role author
author2 Yanagida, Masuzo
Rufiner, Hugo Leonardo
Milone, Diego Humberto
author2_role author
author
author
dc.subject.none.fl_str_mv Quality Measures
Blind Source Separation
Robust Speech Recognition
Reverberation
topic Quality Measures
Blind Source Separation
Robust Speech Recognition
Reverberation
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv The determination of quality of the signals obtained by blind source separation is a very important subject fordevelopment and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic speechrecognition, the quality measure of separation applied for assessment should be related to the recognition rates of thesystem. Many measures have been used for quality evaluation, but in general these have been applied without priorresearch of their capabilities as quality measures in the context of blind source separation, and often they requireexperimentation in unrealistic conditions. Moreover, these measures just try to evaluate the amount of separation, and thisvalue could not be directly related to recognition rates. Presented in this work is a study of several objective qualitymeasures evaluated as predictors of recognition rate of a continuous speech recognizer. Correlation between qualitymeasures and recognition rates is analyzed for a separation algorithm applied to signals recorded in a real room withdifferent reverberation times and different kinds and levels of noise. A very good correlation between weighted spectralslope measure and the recognition rate has been verified from the results of this analysis. Furthermore, a good performanceof total relative distortion and cepstral measures for rooms with relatively long reverberation time has been observed
Fil: Di Persia, Leandro Ezequiel. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Yanagida, Masuzo. Doshisha University; Japón
Fil: Rufiner, Hugo Leonardo. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Milone, Diego Humberto. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description The determination of quality of the signals obtained by blind source separation is a very important subject fordevelopment and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic speechrecognition, the quality measure of separation applied for assessment should be related to the recognition rates of thesystem. Many measures have been used for quality evaluation, but in general these have been applied without priorresearch of their capabilities as quality measures in the context of blind source separation, and often they requireexperimentation in unrealistic conditions. Moreover, these measures just try to evaluate the amount of separation, and thisvalue could not be directly related to recognition rates. Presented in this work is a study of several objective qualitymeasures evaluated as predictors of recognition rate of a continuous speech recognizer. Correlation between qualitymeasures and recognition rates is analyzed for a separation algorithm applied to signals recorded in a real room withdifferent reverberation times and different kinds and levels of noise. A very good correlation between weighted spectralslope measure and the recognition rate has been verified from the results of this analysis. Furthermore, a good performanceof total relative distortion and cepstral measures for rooms with relatively long reverberation time has been observed
publishDate 2007
dc.date.none.fl_str_mv 2007-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/113586
Di Persia, Leandro Ezequiel; Yanagida, Masuzo; Rufiner, Hugo Leonardo; Milone, Diego Humberto; Objective quality evaluation in blind source separation for speech recognition in a real room; Elsevier Science; Signal Processing; 87; 8; 12-2007; 1951-1965
0165-1684
CONICET Digital
CONICET
url http://hdl.handle.net/11336/113586
identifier_str_mv Di Persia, Leandro Ezequiel; Yanagida, Masuzo; Rufiner, Hugo Leonardo; Milone, Diego Humberto; Objective quality evaluation in blind source separation for speech recognition in a real room; Elsevier Science; Signal Processing; 87; 8; 12-2007; 1951-1965
0165-1684
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/j.sigpro.2007.02.004
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier Science
publisher.none.fl_str_mv Elsevier Science
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1846083559443398656
score 13.22299

Publicaciones similares