Title :
Automatic detection of laryngeal pathologies using cepstral analysis in Mel and Bark scales
Author :
Villa-Cañas, T. ; Belalcazar-Bolamos, E. ; Bedoya-Jaramillo, S. ; Garcés, J.F. ; Orozco-Arroyave, J.R. ; Arias-Londoño, J.D. ; Vargas-Bonilla, J.F.
Author_Institution :
Pertenecientes al Grupo de Investig. en Telecomun. Aplic. G.I.T.A. Medellin, Univ. de Antioquia, Medellin, Colombia
Abstract :
Problems in voice production can appear due to functional disorders and laryngeal pathologies. The presence of laryngeal pathologies can causes significant changes in the vibrational patterns of the vocal folds and it is demonstrated that the impact of such pathologies can be reduced through continuous speech therapy. We propose a methodology based on non-parametric cepstral coefficients in Mel and Bark scales. The most relevant features are automatically selected using two algorithms, one is based on Principal Components Analysis (PCA) and other is based on Sequential Floating Features Selection (SFFS). In order to decide whether a voice recording is healthy or pathological, four different classifiers are implemented: linear and quadratic Bayesian, K nearest neighbors and Parzen. The best result was 89.18%, it was obtained from the union between MFCC and BFCC.
Keywords :
Bayes methods; cepstral analysis; principal component analysis; signal detection; speech processing; Bark scales; K nearest neighbors; Mel scales; Parzen classifiers; SFFS; automatic detection; cepstral analysis; laryngeal pathologies; linear classifiers; nonparametric cepstral coefficients; principal components analysis; quadratic Bayesian classifiers; sequential floating features selection; speech therapy; vibrational patterns; vocal folds; voice production; voice recording; Cepstrum; Electronic mail; Media; Mel frequency cepstral coefficient; Pathology; Principal component analysis; Bark scale; Mel scale; cepstral coefficients; laryngeal pathologies; principal components analysis; sequential feature floating selection;
Conference_Titel :
Image, Signal Processing, and Artificial Vision (STSIVA), 2012 XVII Symposium of
Conference_Location :
Antioquia
Print_ISBN :
978-1-4673-2759-6
DOI :
10.1109/STSIVA.2012.6340567