Classification of Control/Pathologic Subjects with Support Vector Machines

The diagnosis of pathologies using vocal acoustic analysis has the advantage of been noninvasive and inexpensive technique compared to traditional technique in use. In this work the SVM were experimentally tested to diagnose dysphonia, chronic laryngitis or vocal cords paralysis. Three groups of par...

Full description

Saved in:
Bibliographic Details
Published inProcedia computer science Vol. 138; pp. 272 - 279
Main Authors Teixeira, Felipe, Fernandes, Joana, Guedes, Vitor, Junior, Arnaldo, Teixeira, João Paulo
Format Journal Article
LanguageEnglish
Published Elsevier B.V 2018
Subjects
HNR
Jitter
MFCCs
Shimmer
SVM functions
SVM methods
Vocal Acoustic Analysis
Vocal Acoustic Analysis
MFCCs
Jitter
Shimmer
SVM functions
HNR
SVM methods
Online AccessGet full text

Cover

More Information
Summary:The diagnosis of pathologies using vocal acoustic analysis has the advantage of been noninvasive and inexpensive technique compared to traditional technique in use. In this work the SVM were experimentally tested to diagnose dysphonia, chronic laryngitis or vocal cords paralysis. Three groups of parameters were experimented. Jitter, shimmer and HNR, MFCCs extracted from a sustained vowels and MFCC extracted from a short sentence. The first group showed their importance in this type of diagnose and the second group showed low discriminative power. The SVM functions and methods were also experimented using the dataset with and without gender separation. The best accuracy was 71% using the jitter, shimmer and HNR parameters without gender separation.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2018.10.039