Characterization of pathological voice signals based on classical acoustic analysis
Tipo
Artigo de evento
Data de publicação
2011
Periódico
18th IMEKO TC4 Symposium on Measurement of Electrical Quantities 2011, Part of Metrologia 2011
Citações (Scopus)
0
Autores
Brandt R.R.
Neto B.G.A.
Freire R.C.S.
Fechine J.M.
Do Nascimento Cunha Costa S.L.
Neto B.G.A.
Freire R.C.S.
Fechine J.M.
Do Nascimento Cunha Costa S.L.
Orientador
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
Copyright © 2011 by the International Measurement Confederation (IMEKO) All rights reserved.This work describes a method used to classify voice signals as normal or pathological. Voices were chosen from the KAY ELEMETRICS CORP Voice Disorders Database. The process of characterization of the voices as normal or pathological was done using classical acoustic analysis characteristics. Individual features gave false positive and false negative rates ranging from 15% up. By using three features simultaneously false positive and false negative rates of 13% and 15%, respectively, were obtained.
Descrição
Palavras-chave
Assuntos Scopus
Acoustic analysis , False positive and false negatives , Individual features , Noninvasive , Pathological voice , Voice disorders , Voice signals