Residual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorDhirubhai Ambani Institute of Information and Communication Technology (DA-IICT)-
Autor(es): dc.contributorArizona State University-
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.creatorGupta, Siddhant-
Autor(es): dc.creatorPatil, Ankur T.-
Autor(es): dc.creatorPurohit, Mirali-
Autor(es): dc.creatorParmar, Mihir-
Autor(es): dc.creatorPatel, Maitreya-
Autor(es): dc.creatorPatil, Hemant A.-
Autor(es): dc.creatorGuido, Rodrigo Capobianco [UNESP]-
Data de aceite: dc.date.accessioned2022-02-22T00:53:33Z-
Data de disponibilização: dc.date.available2022-02-22T00:53:33Z-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2021-07-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.neunet.2021.02.008-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/208481-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/208481-
Descrição: dc.descriptionRecently, we have witnessed Deep Learning methodologies gaining significant attention for severity-based classification of dysarthric speech. Detecting dysarthria, quantifying its severity, are of paramount importance in various real-life applications, such as the assessment of patients’ progression in treatments, which includes an adequate planning of their therapy and the improvement of speech-based interactive systems in order to handle pathologically-affected voices automatically. Notably, current speech-powered tools often deal with short-duration speech segments and, consequently, are less efficient in dealing with impaired speech, even by using Convolutional Neural Networks (CNNs). Thus, detecting dysarthria severity-level based on short speech segments might help in improving the performance and applicability of those systems. To achieve this goal, we propose a novel Residual Network (ResNet)-based technique which receives short-duration speech segments as input. Statistically meaningful objective analysis of our experiments, reported over standard Universal Access corpus, exhibits average values of 21.35% and 22.48% improvement, compared to the baseline CNN, in terms of classification accuracy and F1-score, respectively. For additional comparisons, tests with Gaussian Mixture Models and Light CNNs were also performed. Overall, the values of 98.90% and 98.00% for classification accuracy and F1-score, respectively, were obtained with the proposed ResNet approach, confirming its efficacy and reassuring its practical applicability.-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionSpeech Research Lab Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT)-
Descrição: dc.descriptionArizona State University-
Descrição: dc.descriptionInstituto de Biociências Letras e Ciências Exatas Unesp - Univ Estadual Paulista (São Paulo State University), Rua Cristóvão Colombo 2265, Jd Nazareth-
Descrição: dc.descriptionInstituto de Biociências Letras e Ciências Exatas Unesp - Univ Estadual Paulista (São Paulo State University), Rua Cristóvão Colombo 2265, Jd Nazareth-
Descrição: dc.descriptionFAPESP: 2019/04475-0-
Descrição: dc.descriptionCNPq: 306808/2018-8-
Formato: dc.format105-117-
Idioma: dc.languageen-
Relação: dc.relationNeural Networks-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectCNN-
Palavras-chave: dc.subjectDysarthria-
Palavras-chave: dc.subjectResNet-
Palavras-chave: dc.subjectSeverity-level-
Palavras-chave: dc.subjectShort-speech segments-
Título: dc.titleResidual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.