An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/s23115196 http://hdl.handle.net/11449/250048 |
Resumo: | Biometrics-based authentication has become the most well-established form of user recognition in systems that demand a certain level of security. For example, the most commonplace social activities stand out, such as access to the work environment or to one’s own bank account. Among all biometrics, voice receives special attention due to factors such as ease of collection, the low cost of reading devices, and the high quantity of literature and software packages available for use. However, these biometrics may have the ability to represent the individual impaired by the phenomenon known as dysphonia, which consists of a change in the sound signal due to some disease that acts on the vocal apparatus. As a consequence, for example, a user with the flu may not be properly authenticated by the recognition system. Therefore, it is important that automatic voice dysphonia detection techniques be developed. In this work, we propose a new framework based on the representation of the voice signal by the multiple projection of cepstral coefficients to promote the detection of dysphonic alterations in the voice through machine learning techniques. Most of the best-known cepstral coefficient extraction techniques in the literature are mapped and analyzed separately and together with measures related to the fundamental frequency of the voice signal, and its representation capacity is evaluated on three classifiers. Finally, the experiments on a subset of the Saarbruecken Voice Database prove the effectiveness of the proposed material in detecting the presence of dysphonia in the voice. |
id |
UNSP_2ce9f55e86403f8d9c0515a19f84a739 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/250048 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detectioncepstral analysisdysphonia detectionmachine learningpattern recognitionvoice disorder detectionBiometrics-based authentication has become the most well-established form of user recognition in systems that demand a certain level of security. For example, the most commonplace social activities stand out, such as access to the work environment or to one’s own bank account. Among all biometrics, voice receives special attention due to factors such as ease of collection, the low cost of reading devices, and the high quantity of literature and software packages available for use. However, these biometrics may have the ability to represent the individual impaired by the phenomenon known as dysphonia, which consists of a change in the sound signal due to some disease that acts on the vocal apparatus. As a consequence, for example, a user with the flu may not be properly authenticated by the recognition system. Therefore, it is important that automatic voice dysphonia detection techniques be developed. In this work, we propose a new framework based on the representation of the voice signal by the multiple projection of cepstral coefficients to promote the detection of dysphonic alterations in the voice through machine learning techniques. Most of the best-known cepstral coefficient extraction techniques in the literature are mapped and analyzed separately and together with measures related to the fundamental frequency of the voice signal, and its representation capacity is evaluated on three classifiers. Finally, the experiments on a subset of the Saarbruecken Voice Database prove the effectiveness of the proposed material in detecting the presence of dysphonia in the voice.Department of Computer Science and Statistics Institute of Biosciences Letters and Exact Sciences São Paulo State University, SPFederal Institute of São Paulo, SPFaculty of Architecture and Engineering Mato Grosso State University, MTDepartment of Computer Science and Statistics Institute of Biosciences Letters and Exact Sciences São Paulo State University, SPUniversidade Estadual Paulista (UNESP)Federal Institute of São PauloMato Grosso State UniversityContreras, Rodrigo Colnago [UNESP]Viana, Monique SimplicioFonseca, Everthon Silvados Santos, Francisco LledoZanin, Rodrigo BrunoGuido, Rodrigo Capobianco [UNESP]2023-07-29T16:16:17Z2023-07-29T16:16:17Z2023-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/s23115196Sensors, v. 23, n. 11, 2023.1424-8220http://hdl.handle.net/11449/25004810.3390/s231151962-s2.0-85161510694Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengSensorsinfo:eu-repo/semantics/openAccess2023-07-29T16:16:17Zoai:repositorio.unesp.br:11449/250048Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-07-29T16:16:17Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
title |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
spellingShingle |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection Contreras, Rodrigo Colnago [UNESP] cepstral analysis dysphonia detection machine learning pattern recognition voice disorder detection |
title_short |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
title_full |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
title_fullStr |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
title_full_unstemmed |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
title_sort |
An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection |
author |
Contreras, Rodrigo Colnago [UNESP] |
author_facet |
Contreras, Rodrigo Colnago [UNESP] Viana, Monique Simplicio Fonseca, Everthon Silva dos Santos, Francisco Lledo Zanin, Rodrigo Bruno Guido, Rodrigo Capobianco [UNESP] |
author_role |
author |
author2 |
Viana, Monique Simplicio Fonseca, Everthon Silva dos Santos, Francisco Lledo Zanin, Rodrigo Bruno Guido, Rodrigo Capobianco [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Federal Institute of São Paulo Mato Grosso State University |
dc.contributor.author.fl_str_mv |
Contreras, Rodrigo Colnago [UNESP] Viana, Monique Simplicio Fonseca, Everthon Silva dos Santos, Francisco Lledo Zanin, Rodrigo Bruno Guido, Rodrigo Capobianco [UNESP] |
dc.subject.por.fl_str_mv |
cepstral analysis dysphonia detection machine learning pattern recognition voice disorder detection |
topic |
cepstral analysis dysphonia detection machine learning pattern recognition voice disorder detection |
description |
Biometrics-based authentication has become the most well-established form of user recognition in systems that demand a certain level of security. For example, the most commonplace social activities stand out, such as access to the work environment or to one’s own bank account. Among all biometrics, voice receives special attention due to factors such as ease of collection, the low cost of reading devices, and the high quantity of literature and software packages available for use. However, these biometrics may have the ability to represent the individual impaired by the phenomenon known as dysphonia, which consists of a change in the sound signal due to some disease that acts on the vocal apparatus. As a consequence, for example, a user with the flu may not be properly authenticated by the recognition system. Therefore, it is important that automatic voice dysphonia detection techniques be developed. In this work, we propose a new framework based on the representation of the voice signal by the multiple projection of cepstral coefficients to promote the detection of dysphonic alterations in the voice through machine learning techniques. Most of the best-known cepstral coefficient extraction techniques in the literature are mapped and analyzed separately and together with measures related to the fundamental frequency of the voice signal, and its representation capacity is evaluated on three classifiers. Finally, the experiments on a subset of the Saarbruecken Voice Database prove the effectiveness of the proposed material in detecting the presence of dysphonia in the voice. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T16:16:17Z 2023-07-29T16:16:17Z 2023-06-01 |
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://dx.doi.org/10.3390/s23115196 Sensors, v. 23, n. 11, 2023. 1424-8220 http://hdl.handle.net/11449/250048 10.3390/s23115196 2-s2.0-85161510694 |
url |
http://dx.doi.org/10.3390/s23115196 http://hdl.handle.net/11449/250048 |
identifier_str_mv |
Sensors, v. 23, n. 11, 2023. 1424-8220 10.3390/s23115196 2-s2.0-85161510694 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Sensors |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799965478692585472 |