Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models

Detalhes bibliográficos
Autor(a) principal: Thomé, Antonio Carlos Gay
Data de Publicação: 1999
Outros Autores: Santos, Sidney B. dos, Diniz, Suelaine S
Tipo de documento: Relatório
Idioma: eng
Título da fonte: Repositório Institucional da UFRJ
Texto Completo: http://hdl.handle.net/11422/2652
Resumo: The main goal in this research is to find out possible ways to built hybrid systems, based on neural network (NN) and hidden M;arkov (HMM) models, for the task of automatic speech recognition. The investigation that has been conducted covers different types of neural network and hidden Markov models, and the combination of them into some hybrid models. The neural networks used were basically MLP and Radial Basis models. The hidden Markov models were basically different combinations of states and mixtures of the Continuous Density type of the Bakis model. A reduced set with ten words spoken in the Portuguese idiom, from Brazil, was carefully chosen to provide some pronounce and phonetic confusion. The results already obtained showed very positive, pointing toward to a high potentiality of such hybrid models.
id UFRJ_80605d0a0a5f5c73aabccfcd0d5b6242
oai_identifier_str oai:pantheon.ufrj.br:11422/2652
network_acronym_str UFRJ
network_name_str Repositório Institucional da UFRJ
repository_id_str
spelling Thomé, Antonio Carlos GaySantos, Sidney B. dosDiniz, Suelaine S2017-08-15T13:44:49Z2023-11-30T03:00:27Z1999-12-31THOMÉ, A. G.; SANTOS, S. B. dos; DINIZ, S. S. Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models. Rio de Janeiro: NCE, UFRJ, 1999. 6 p. (Relatório Técnico, 19/99)http://hdl.handle.net/11422/2652The main goal in this research is to find out possible ways to built hybrid systems, based on neural network (NN) and hidden M;arkov (HMM) models, for the task of automatic speech recognition. The investigation that has been conducted covers different types of neural network and hidden Markov models, and the combination of them into some hybrid models. The neural networks used were basically MLP and Radial Basis models. The hidden Markov models were basically different combinations of states and mixtures of the Continuous Density type of the Bakis model. A reduced set with ten words spoken in the Portuguese idiom, from Brazil, was carefully chosen to provide some pronounce and phonetic confusion. The results already obtained showed very positive, pointing toward to a high potentiality of such hybrid models.Submitted by Elaine Almeida (elaine.almeida@nce.ufrj.br) on 2017-08-15T13:44:49Z No. of bitstreams: 1 15_99_000611274.pdf: 729618 bytes, checksum: 9df4cc7b98f678cc21c117a8d4a427e3 (MD5)Made available in DSpace on 2017-08-15T13:44:49Z (GMT). No. of bitstreams: 1 15_99_000611274.pdf: 729618 bytes, checksum: 9df4cc7b98f678cc21c117a8d4a427e3 (MD5) Previous issue date: 1999-12-31engRelatório Técnico NCECNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOReconhecimento de vozRedes neurais (Ciência da computação)Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov modelsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/report1599abertoBrasilInstituto Tércio Pacitti de Aplicações e Pesquisas Computacionaisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRJinstname:Universidade Federal do Rio de Janeiro (UFRJ)instacron:UFRJORIGINAL15_99_000611274.pdf15_99_000611274.pdfapplication/pdf729618http://pantheon.ufrj.br:80/bitstream/11422/2652/1/15_99_000611274.pdf9df4cc7b98f678cc21c117a8d4a427e3MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81853http://pantheon.ufrj.br:80/bitstream/11422/2652/2/license.txtdd32849f2bfb22da963c3aac6e26e255MD52TEXT15_99_000611274.pdf.txt15_99_000611274.pdf.txtExtracted texttext/plain23693http://pantheon.ufrj.br:80/bitstream/11422/2652/3/15_99_000611274.pdf.txt3ec6e894899635ab8b43431245c3365dMD5311422/26522023-11-30 00:00:27.064oai:pantheon.ufrj.br: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Repositório de PublicaçõesPUBhttp://www.pantheon.ufrj.br/oai/requestopendoar:2023-11-30T03:00:27Repositório Institucional da UFRJ - Universidade Federal do Rio de Janeiro (UFRJ)false
dc.title.pt_BR.fl_str_mv Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
title Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
spellingShingle Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
Thomé, Antonio Carlos Gay
CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
Reconhecimento de voz
Redes neurais (Ciência da computação)
title_short Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
title_full Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
title_fullStr Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
title_full_unstemmed Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
title_sort Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models
author Thomé, Antonio Carlos Gay
author_facet Thomé, Antonio Carlos Gay
Santos, Sidney B. dos
Diniz, Suelaine S
author_role author
author2 Santos, Sidney B. dos
Diniz, Suelaine S
author2_role author
author
dc.contributor.author.fl_str_mv Thomé, Antonio Carlos Gay
Santos, Sidney B. dos
Diniz, Suelaine S
dc.subject.cnpq.fl_str_mv CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
topic CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
Reconhecimento de voz
Redes neurais (Ciência da computação)
dc.subject.por.fl_str_mv Reconhecimento de voz
Redes neurais (Ciência da computação)
description The main goal in this research is to find out possible ways to built hybrid systems, based on neural network (NN) and hidden M;arkov (HMM) models, for the task of automatic speech recognition. The investigation that has been conducted covers different types of neural network and hidden Markov models, and the combination of them into some hybrid models. The neural networks used were basically MLP and Radial Basis models. The hidden Markov models were basically different combinations of states and mixtures of the Continuous Density type of the Bakis model. A reduced set with ten words spoken in the Portuguese idiom, from Brazil, was carefully chosen to provide some pronounce and phonetic confusion. The results already obtained showed very positive, pointing toward to a high potentiality of such hybrid models.
publishDate 1999
dc.date.issued.fl_str_mv 1999-12-31
dc.date.accessioned.fl_str_mv 2017-08-15T13:44:49Z
dc.date.available.fl_str_mv 2023-11-30T03:00:27Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/report
format report
status_str publishedVersion
dc.identifier.citation.fl_str_mv THOMÉ, A. G.; SANTOS, S. B. dos; DINIZ, S. S. Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models. Rio de Janeiro: NCE, UFRJ, 1999. 6 p. (Relatório Técnico, 19/99)
dc.identifier.uri.fl_str_mv http://hdl.handle.net/11422/2652
identifier_str_mv THOMÉ, A. G.; SANTOS, S. B. dos; DINIZ, S. S. Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models. Rio de Janeiro: NCE, UFRJ, 1999. 6 p. (Relatório Técnico, 19/99)
url http://hdl.handle.net/11422/2652
dc.language.iso.fl_str_mv eng
language eng
dc.relation.ispartof.pt_BR.fl_str_mv Relatório Técnico NCE
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.country.fl_str_mv Brasil
dc.publisher.department.fl_str_mv Instituto Tércio Pacitti de Aplicações e Pesquisas Computacionais
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFRJ
instname:Universidade Federal do Rio de Janeiro (UFRJ)
instacron:UFRJ
instname_str Universidade Federal do Rio de Janeiro (UFRJ)
instacron_str UFRJ
institution UFRJ
reponame_str Repositório Institucional da UFRJ
collection Repositório Institucional da UFRJ
bitstream.url.fl_str_mv http://pantheon.ufrj.br:80/bitstream/11422/2652/1/15_99_000611274.pdf
http://pantheon.ufrj.br:80/bitstream/11422/2652/2/license.txt
http://pantheon.ufrj.br:80/bitstream/11422/2652/3/15_99_000611274.pdf.txt
bitstream.checksum.fl_str_mv 9df4cc7b98f678cc21c117a8d4a427e3
dd32849f2bfb22da963c3aac6e26e255
3ec6e894899635ab8b43431245c3365d
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFRJ - Universidade Federal do Rio de Janeiro (UFRJ)
repository.mail.fl_str_mv
_version_ 1784097091212017664