Classification of ASR Word Hypotheses using prosodic information and resampling of training data

Autores
Albornoz, Enrique Marcelo; Milone, Diego Humberto; Rufiner, Hugo Leonardo; López-Cózar, R.
Año de publicación
2013
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In this work, we propose a novel re-sampling method based on word lattice information and we use prosodic cues with support vector machines for classification. The idea is to consider word recognition as a two-class classification problem, which considers the word hypotheses in the lattice of a standard recognizer either as True or False employing prosodic information. The technique developed in this paper was applied to set of words extracted from a continuous speech database. Our experimental results show that the method allows obtaining average word hypotheses recognition rate of 82%.
Fil: Albornoz, Enrique Marcelo. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; Argentina
Fil: Milone, Diego Humberto. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; Argentina
Fil: Rufiner, Hugo Leonardo. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; Argentina
Fil: López-Cózar, R.. Escuela Técnica Superior en Ingeniería Informática y de Telecomunicación. Universidad de Granada; España;
Materia
Resampling Corpus
Support Vector Machines
Hypotheses Classification
Automatic Speech Recognition
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:11336/1536
Acceder
id CONICETDig_b27625a58e40f46f7b5ae757dca30744
oai_identifier_str oai:ri.conicet.gov.ar:11336/1536
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Classification of ASR Word Hypotheses using prosodic information and resampling of training dataAlbornoz, Enrique MarceloMilone, Diego HumbertoRufiner, Hugo LeonardoLópez-Cózar, R.Resampling CorpusSupport Vector MachinesHypotheses ClassificationAutomatic Speech Recognitionhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1In this work, we propose a novel re-sampling method based on word lattice information and we use prosodic cues with support vector machines for classification. The idea is to consider word recognition as a two-class classification problem, which considers the word hypotheses in the lattice of a standard recognizer either as True or False employing prosodic information. The technique developed in this paper was applied to set of words extracted from a continuous speech database. Our experimental results show that the method allows obtaining average word hypotheses recognition rate of 82%.Fil: Albornoz, Enrique Marcelo. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; ArgentinaFil: Milone, Diego Humberto. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; ArgentinaFil: Rufiner, Hugo Leonardo. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; ArgentinaFil: López-Cózar, R.. Escuela Técnica Superior en Ingeniería Informática y de Telecomunicación. Universidad de Granada; España;Planta Piloto de Ingeniería Química2013-07info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/1536Albornoz, Enrique Marcelo; Milone, Diego Humberto; Rufiner, Hugo Leonardo; López-Cózar, R.; Classification of ASR Word Hypotheses using prosodic information and resampling of training data; Planta Piloto de Ingeniería Química; Latin American Applied Research; 43; 3; 7-2013; 1-50327-07931851-8796enginfo:eu-repo/semantics/altIdentifier/url/http://fich.unl.edu.ar/sinc/sinc-publications/2013/AMRL13/sinc_AMRL13.pdfinfo:eu-repo/semantics/altIdentifier/url/http://www.laar.uns.edu.ar/indexes/artic_v4303/Vol43_03_213.pdfinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:29:54Zoai:ri.conicet.gov.ar:11336/1536instacron: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:34982025-09-29 10:29:54.566CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Classification of ASR Word Hypotheses using prosodic information and resampling of training data
title Classification of ASR Word Hypotheses using prosodic information and resampling of training data
spellingShingle Classification of ASR Word Hypotheses using prosodic information and resampling of training data
Albornoz, Enrique Marcelo
Resampling Corpus
Support Vector Machines
Hypotheses Classification
Automatic Speech Recognition
title_short Classification of ASR Word Hypotheses using prosodic information and resampling of training data
title_full Classification of ASR Word Hypotheses using prosodic information and resampling of training data
title_fullStr Classification of ASR Word Hypotheses using prosodic information and resampling of training data
title_full_unstemmed Classification of ASR Word Hypotheses using prosodic information and resampling of training data
title_sort Classification of ASR Word Hypotheses using prosodic information and resampling of training data
dc.creator.none.fl_str_mv Albornoz, Enrique Marcelo
Milone, Diego Humberto
Rufiner, Hugo Leonardo
López-Cózar, R.
author Albornoz, Enrique Marcelo
author_facet Albornoz, Enrique Marcelo
Milone, Diego Humberto
Rufiner, Hugo Leonardo
López-Cózar, R.
author_role author
author2 Milone, Diego Humberto
Rufiner, Hugo Leonardo
López-Cózar, R.
author2_role author
author
author
dc.subject.none.fl_str_mv Resampling Corpus
Support Vector Machines
Hypotheses Classification
Automatic Speech Recognition
topic Resampling Corpus
Support Vector Machines
Hypotheses Classification
Automatic Speech Recognition
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv In this work, we propose a novel re-sampling method based on word lattice information and we use prosodic cues with support vector machines for classification. The idea is to consider word recognition as a two-class classification problem, which considers the word hypotheses in the lattice of a standard recognizer either as True or False employing prosodic information. The technique developed in this paper was applied to set of words extracted from a continuous speech database. Our experimental results show that the method allows obtaining average word hypotheses recognition rate of 82%.
Fil: Albornoz, Enrique Marcelo. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; Argentina
Fil: Milone, Diego Humberto. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; Argentina
Fil: Rufiner, Hugo Leonardo. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Departamento de Informática. Laboratorio de Investigaciones en Señales e Inteligencia Computacional; Argentina
Fil: López-Cózar, R.. Escuela Técnica Superior en Ingeniería Informática y de Telecomunicación. Universidad de Granada; España;
description In this work, we propose a novel re-sampling method based on word lattice information and we use prosodic cues with support vector machines for classification. The idea is to consider word recognition as a two-class classification problem, which considers the word hypotheses in the lattice of a standard recognizer either as True or False employing prosodic information. The technique developed in this paper was applied to set of words extracted from a continuous speech database. Our experimental results show that the method allows obtaining average word hypotheses recognition rate of 82%.
publishDate 2013
dc.date.none.fl_str_mv 2013-07
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/11336/1536
Albornoz, Enrique Marcelo; Milone, Diego Humberto; Rufiner, Hugo Leonardo; López-Cózar, R.; Classification of ASR Word Hypotheses using prosodic information and resampling of training data; Planta Piloto de Ingeniería Química; Latin American Applied Research; 43; 3; 7-2013; 1-5
0327-0793
1851-8796
url http://hdl.handle.net/11336/1536
identifier_str_mv Albornoz, Enrique Marcelo; Milone, Diego Humberto; Rufiner, Hugo Leonardo; López-Cózar, R.; Classification of ASR Word Hypotheses using prosodic information and resampling of training data; Planta Piloto de Ingeniería Química; Latin American Applied Research; 43; 3; 7-2013; 1-5
0327-0793
1851-8796
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://fich.unl.edu.ar/sinc/sinc-publications/2013/AMRL13/sinc_AMRL13.pdf
info:eu-repo/semantics/altIdentifier/url/http://www.laar.uns.edu.ar/indexes/artic_v4303/Vol43_03_213.pdf
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
dc.publisher.none.fl_str_mv Planta Piloto de Ingeniería Química
publisher.none.fl_str_mv Planta Piloto de Ingeniería Química
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_ 1844614306845425664
score 13.069144

Publicaciones similares