Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis

Detalhes bibliográficos
Autor(a) principal: Teixeira, João Paulo
Data de Publicação: 2020
Outros Autores: Alves, Nuno Filipe Ribeiro, Fernandes, Paula Odete
Tipo de documento: Artigo
Idioma: spa
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10198/21790
Resumo: Vocal acoustic analysis is becoming a useful tool for the classification and recognition of laryngological pathologies. This technique enables a non-invasive and low-cost assessment of voice disorders, allowing a more efficient, fast, and objective diagnosis. In this work, ANN and SVM were experimented on to classify between dysphonic/control and vocal cord paralysis/control. A vector was made up of 4 jitter parameters, 4 shimmer parameters, and a harmonic to noise ratio (HNR), determined from 3 different vowels at 3 different tones, with a total of 81 features. Variable selection and dimension reduction techniques such as hierarchical clustering, multilinear regression analysis and principal component analysis (PCA) was applied. The classification between dysphonic and control was made with an accuracy of 100% for female and male groups with ANN and SVM. For the classification between vocal cords paralysis and control an accuracy of 78,9% was achieved for female group with SVM, and 81,8% for the male group with ANN.
id RCAP_67c8eea6c21f26da99627593934ea88a
oai_identifier_str oai:bibliotecadigital.ipb.pt:10198/21790
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysisANNClassificationFeature selectionHierarchical clusteringHNRJitterMultilinear regression analysisPCAShimmerSVMVocal acoustic analysisVoice pathologiesVocal acoustic analysis is becoming a useful tool for the classification and recognition of laryngological pathologies. This technique enables a non-invasive and low-cost assessment of voice disorders, allowing a more efficient, fast, and objective diagnosis. In this work, ANN and SVM were experimented on to classify between dysphonic/control and vocal cord paralysis/control. A vector was made up of 4 jitter parameters, 4 shimmer parameters, and a harmonic to noise ratio (HNR), determined from 3 different vowels at 3 different tones, with a total of 81 features. Variable selection and dimension reduction techniques such as hierarchical clustering, multilinear regression analysis and principal component analysis (PCA) was applied. The classification between dysphonic and control was made with an accuracy of 100% for female and male groups with ANN and SVM. For the classification between vocal cords paralysis and control an accuracy of 78,9% was achieved for female group with SVM, and 81,8% for the male group with ANN.IGI GlobalBiblioteca Digital do IPBTeixeira, João PauloAlves, Nuno Filipe RibeiroFernandes, Paula Odete2020-04-23T08:54:43Z20202020-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10198/21790spaTeixeira, João Paulo; Alves, Nuno; Fernandes, Paula O. (2020). Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis. International Journal of E-Health and Medical Communications (IJEHMC). ISSN 1947-315X. 11:1, p. 37-511947-315X10.4018/IJEHMC.20200101031947-3168info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-21T10:49:07Zoai:bibliotecadigital.ipb.pt:10198/21790Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T23:13:11.314078Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
title Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
spellingShingle Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
Teixeira, João Paulo
ANN
Classification
Feature selection
Hierarchical clustering
HNR
Jitter
Multilinear regression analysis
PCA
Shimmer
SVM
Vocal acoustic analysis
Voice pathologies
title_short Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
title_full Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
title_fullStr Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
title_full_unstemmed Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
title_sort Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis
author Teixeira, João Paulo
author_facet Teixeira, João Paulo
Alves, Nuno Filipe Ribeiro
Fernandes, Paula Odete
author_role author
author2 Alves, Nuno Filipe Ribeiro
Fernandes, Paula Odete
author2_role author
author
dc.contributor.none.fl_str_mv Biblioteca Digital do IPB
dc.contributor.author.fl_str_mv Teixeira, João Paulo
Alves, Nuno Filipe Ribeiro
Fernandes, Paula Odete
dc.subject.por.fl_str_mv ANN
Classification
Feature selection
Hierarchical clustering
HNR
Jitter
Multilinear regression analysis
PCA
Shimmer
SVM
Vocal acoustic analysis
Voice pathologies
topic ANN
Classification
Feature selection
Hierarchical clustering
HNR
Jitter
Multilinear regression analysis
PCA
Shimmer
SVM
Vocal acoustic analysis
Voice pathologies
description Vocal acoustic analysis is becoming a useful tool for the classification and recognition of laryngological pathologies. This technique enables a non-invasive and low-cost assessment of voice disorders, allowing a more efficient, fast, and objective diagnosis. In this work, ANN and SVM were experimented on to classify between dysphonic/control and vocal cord paralysis/control. A vector was made up of 4 jitter parameters, 4 shimmer parameters, and a harmonic to noise ratio (HNR), determined from 3 different vowels at 3 different tones, with a total of 81 features. Variable selection and dimension reduction techniques such as hierarchical clustering, multilinear regression analysis and principal component analysis (PCA) was applied. The classification between dysphonic and control was made with an accuracy of 100% for female and male groups with ANN and SVM. For the classification between vocal cords paralysis and control an accuracy of 78,9% was achieved for female group with SVM, and 81,8% for the male group with ANN.
publishDate 2020
dc.date.none.fl_str_mv 2020-04-23T08:54:43Z
2020
2020-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10198/21790
url http://hdl.handle.net/10198/21790
dc.language.iso.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv Teixeira, João Paulo; Alves, Nuno; Fernandes, Paula O. (2020). Vocal acoustic analysis: ANN versos SVM in classification of dysphonic voices and vocal cords paralysis. International Journal of E-Health and Medical Communications (IJEHMC). ISSN 1947-315X. 11:1, p. 37-51
1947-315X
10.4018/IJEHMC.2020010103
1947-3168
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.publisher.none.fl_str_mv IGI Global
publisher.none.fl_str_mv IGI Global
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799135407449833472