Comparative analysis between wavelets for the identification of pathological voices

dc.contributor.authorSoares, Heliana Bezerra
dc.contributor.authorCavalcanti, Náthalee
dc.contributor.authorSilva, Sandro
dc.contributor.authorBresolin, Adriano
dc.contributor.authorGuerreiro, Ana Maria Guimarães
dc.date.accessioned2021-12-01T17:42:01Z
dc.date.issued2010
dc.description.embargo2030
dc.description.resumoThis study presents a comparative analysis of wavelets, in order to find a descriptor that provides a better classification of voice pathologies. Different types of Wavelet Packet Transform were used as a tool for feature extraction and Support Vector Machine (SVM) to classify vocal disorders. Tests were conducted with 23 wavelets types in two SVMs, the first using the strategy “one vs. all” to classify normal and pathological voices and the second, using the strategy “one vs. one” to classify pathologies: edema and nodules. The best results were obtained using Daubechies family, especially Daubechies 5 (db5) waveletpt_BR
dc.identifier.citationCAVALCANTE, Nathalee; SOARES, Heliana Bezerra ; BRESOLIN, Adriano A.; Silva, Sandro; Guerreiro, Ana Maria Guimarães. Comparative Analysis between Wavelets for the Identification of Phatological Voices. Lecture Notes in Computer Science, v. 6419, p. 236-243, 2010. Disponível em: https://link.springer.com/chapter/10.1007%2F978-3-642-16687-7_34. Acesso em: 16 jul. 2020. https://doi.org/10.1007/978-3-642-16687-7_34.pt_BR
dc.identifier.doihttps://doi.org/10.1007/978-3-642-16687-7_34
dc.identifier.isbn978-3-642-16686-0
dc.identifier.isbn978-3-642-16687-7
dc.identifier.issn0302-9743 (print)
dc.identifier.urihttps://repositorio.ufrn.br/handle/123456789/45116
dc.languageenpt_BR
dc.publisherSpringer Naturept_BR
dc.rightsAttribution 3.0 Brazil*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/br/*
dc.subjectVocal disorderpt_BR
dc.subjectSupport Vector Machine (SVM)pt_BR
dc.subjectWavelet Packet Transformpt_BR
dc.titleComparative analysis between wavelets for the identification of pathological voicespt_BR
dc.typearticlept_BR

Arquivos

Licença do Pacote

Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
license.txt
Tamanho:
1.45 KB
Formato:
Item-specific license agreed upon to submission
Nenhuma Miniatura disponível
Baixar