Principal component analysis of spectral perturbation parameters for voice pathology detection

Author

Gómez, P. ; Díaz, F. ; Álvarez, A. ; Murphy, K. ; Lázaro, C. ; Martínez, R. ; Rodellar, V.

Author_Institution

Fac. de Informatica, Madrid, Spain

fYear

2005

fDate

23-24 June 2005

Firstpage

41

Lastpage

46

Abstract

In recent years emphasis has been placed upon the early detection of voice pathologies by using the signal processing of voice to evaluate certain time and spectrum domain parameters which may infer the presence of pathology. The present work is aimed at establishing the suitability of these voice spectral parameters in fixing a clear distinction between pathologic and normophonic voice, and to further classify the specific patient´s pathology. Principal component analysis is used in parameter selection. Results for normal and pathological samples will be presented and discussed.

Keywords

diseases; perturbation techniques; principal component analysis; speech; normophonic voice; principal component analysis; signal processing; spectral perturbation parameter; voice pathology detection; voice spectral parameter; Costs; Frequency; Inspection; Pathology; Power harmonic filters; Power system harmonics; Principal component analysis; Professional activities; Signal processing; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2005. Proceedings. 18th IEEE Symposium on

ISSN

1063-7125

Print_ISBN

0-7695-2355-2

Type

conf

DOI

10.1109/CBMS.2005.88

Filename

1467665