The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices

Detalhes bibliográficos
Autor(a) principal: Crovato, César David Paredes
Data de Publicação: 2007
Outros Autores: Schuck Junior, Adalberto
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFRGS
Texto Completo: http://hdl.handle.net/10183/27585
Resumo: This paper presents a dysphonic voice classification system using the wavelet packet transform and the best basis algorithm (BBA) as dimensionality reductor and 06 artificial neural networks (ANN) acting as specialist systems. Each ANN was a 03-layer multilayer perceptron with 64 input nodes, 01 output node and in the intermediary layer the number of neurons depends on the related training pathology group. The dysphonic voice database was separated in five pathology groups and one healthy control group. Each ANN was trained and associated with one of the 06 groups, and fed by the best base tree (BBT) nodes’ entropy values, using the multiple cross validation (MCV) method and the leave-one-out (LOO) variation technique and success rates obtained were 87.5%, 95.31%, 87.5%, 100%, 96.87% and 89.06% for the groups 01 to 06, respectively.
id UFRGS-2_203579488c8142551c79f5c90f599422
oai_identifier_str oai:www.lume.ufrgs.br:10183/27585
network_acronym_str UFRGS-2
network_name_str Repositório Institucional da UFRGS
repository_id_str
spelling Crovato, César David ParedesSchuck Junior, Adalberto2011-01-28T05:59:12Z20070018-9294http://hdl.handle.net/10183/27585000608313This paper presents a dysphonic voice classification system using the wavelet packet transform and the best basis algorithm (BBA) as dimensionality reductor and 06 artificial neural networks (ANN) acting as specialist systems. Each ANN was a 03-layer multilayer perceptron with 64 input nodes, 01 output node and in the intermediary layer the number of neurons depends on the related training pathology group. The dysphonic voice database was separated in five pathology groups and one healthy control group. Each ANN was trained and associated with one of the 06 groups, and fed by the best base tree (BBT) nodes’ entropy values, using the multiple cross validation (MCV) method and the leave-one-out (LOO) variation technique and success rates obtained were 87.5%, 95.31%, 87.5%, 100%, 96.87% and 89.06% for the groups 01 to 06, respectively.application/pdfengIEEE transactions on biomedical engineering. New York, NY. vol. 54, no. 10 (oct. 2007), p. 1898-1900.Redes neurais artificiaisProcessamento de sinais de vozTransformadas waveletVozAcoustical analysis of voicesArtificial neural networkDysphonic voice classificationWavelet packet transformThe use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voicesEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSORIGINAL000608313.pdf000608313.pdfTexto completo (inglês)application/pdf111468http://www.lume.ufrgs.br/bitstream/10183/27585/1/000608313.pdfeef170e252580b3346639e99d8c7f2e6MD51TEXT000608313.pdf.txt000608313.pdf.txtExtracted Texttext/plain20926http://www.lume.ufrgs.br/bitstream/10183/27585/2/000608313.pdf.txtc8e774488e5672bd45943d44910c0c65MD52THUMBNAIL000608313.pdf.jpg000608313.pdf.jpgGenerated Thumbnailimage/jpeg2296http://www.lume.ufrgs.br/bitstream/10183/27585/3/000608313.pdf.jpg30cf0b3f1f1c6b56e4fde6d365609c75MD5310183/275852021-06-13 04:29:09.856272oai:www.lume.ufrgs.br:10183/27585Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-06-13T07:29:09Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false
dc.title.pt_BR.fl_str_mv The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
title The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
spellingShingle The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
Crovato, César David Paredes
Redes neurais artificiais
Processamento de sinais de voz
Transformadas wavelet
Voz
Acoustical analysis of voices
Artificial neural network
Dysphonic voice classification
Wavelet packet transform
title_short The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
title_full The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
title_fullStr The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
title_full_unstemmed The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
title_sort The use of Wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices
author Crovato, César David Paredes
author_facet Crovato, César David Paredes
Schuck Junior, Adalberto
author_role author
author2 Schuck Junior, Adalberto
author2_role author
dc.contributor.author.fl_str_mv Crovato, César David Paredes
Schuck Junior, Adalberto
dc.subject.por.fl_str_mv Redes neurais artificiais
Processamento de sinais de voz
Transformadas wavelet
Voz
topic Redes neurais artificiais
Processamento de sinais de voz
Transformadas wavelet
Voz
Acoustical analysis of voices
Artificial neural network
Dysphonic voice classification
Wavelet packet transform
dc.subject.eng.fl_str_mv Acoustical analysis of voices
Artificial neural network
Dysphonic voice classification
Wavelet packet transform
description This paper presents a dysphonic voice classification system using the wavelet packet transform and the best basis algorithm (BBA) as dimensionality reductor and 06 artificial neural networks (ANN) acting as specialist systems. Each ANN was a 03-layer multilayer perceptron with 64 input nodes, 01 output node and in the intermediary layer the number of neurons depends on the related training pathology group. The dysphonic voice database was separated in five pathology groups and one healthy control group. Each ANN was trained and associated with one of the 06 groups, and fed by the best base tree (BBT) nodes’ entropy values, using the multiple cross validation (MCV) method and the leave-one-out (LOO) variation technique and success rates obtained were 87.5%, 95.31%, 87.5%, 100%, 96.87% and 89.06% for the groups 01 to 06, respectively.
publishDate 2007
dc.date.issued.fl_str_mv 2007
dc.date.accessioned.fl_str_mv 2011-01-28T05:59:12Z
dc.type.driver.fl_str_mv Estrangeiro
info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10183/27585
dc.identifier.issn.pt_BR.fl_str_mv 0018-9294
dc.identifier.nrb.pt_BR.fl_str_mv 000608313
identifier_str_mv 0018-9294
000608313
url http://hdl.handle.net/10183/27585
dc.language.iso.fl_str_mv eng
language eng
dc.relation.ispartof.pt_BR.fl_str_mv IEEE transactions on biomedical engineering. New York, NY. vol. 54, no. 10 (oct. 2007), p. 1898-1900.
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFRGS
instname:Universidade Federal do Rio Grande do Sul (UFRGS)
instacron:UFRGS
instname_str Universidade Federal do Rio Grande do Sul (UFRGS)
instacron_str UFRGS
institution UFRGS
reponame_str Repositório Institucional da UFRGS
collection Repositório Institucional da UFRGS
bitstream.url.fl_str_mv http://www.lume.ufrgs.br/bitstream/10183/27585/1/000608313.pdf
http://www.lume.ufrgs.br/bitstream/10183/27585/2/000608313.pdf.txt
http://www.lume.ufrgs.br/bitstream/10183/27585/3/000608313.pdf.jpg
bitstream.checksum.fl_str_mv eef170e252580b3346639e99d8c7f2e6
c8e774488e5672bd45943d44910c0c65
30cf0b3f1f1c6b56e4fde6d365609c75
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)
repository.mail.fl_str_mv
_version_ 1815447422085627904