CHARACTERIZATION OF PATHOLOGICAL VOICE SIGNALS BASED ON CLASSICAL ACOUSTIC ANALYSIS

Robert Rice Brandt, Benedito Guimarães Aguiar Neto, Raimundo Carlos Silvério Freire, Joseana Macedo Fechine, Silvana Luciene do Nascimento Cunha Costa
Abstract:
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.
Keywords:
voice characterization, pathological voice, acoustic analysis, noninvasive
Download:
IMEKO-TC4-2011-073.pdf
DOI:
-
Event details
IMEKO TC:
TC4
Event name:
TC4 Symposium 2011
Title:

XVIIIth IMEKO TC4 International Symposium on Measurement of Electrical Quantities (part of Metrologia2011, together with IX International Congress on Electrical Metrology - IX SEMETRO)

Place:
Natal, BRAZIL
Time:
27 September 2011 - 30 September 2011