Abstract

This study focuses on a robust, rapid and accurate system for automatic detection of normal voice and speech pathologies. This system employs non-invasive, non-expensive and fully automated measures of vocal tract characteristics and excitation information. Mel-frequency filterbank cepstral coefficients and measures of pitch dynamics were modeled by Gaussian mixtures in a Hidden Markov Model (HMM) classifier. The method was evaluated using the sustained phoneme/a/data obtained from over 700 subjects of normal and different pathological cases from the Massachusetts Eye and Ear Infirmary (MEEI) database. This method attained 99.44% correct classification rates for discrimination of normal and pathological speech for sustained/a/. This represents 8% detection error rate improvement over the best performing classifier using carefully measured features prevalent in the state-of-the-art in pathological speech analysis. The result of this method also shows significant improvement in detection of different AP-Squeezing pathology with respect to the other methods.

Date

January 1, 1970

Authors

Alireza Afshordi Dibazar, Shikanth Narayanan

Journal

Conference Signals, Systems, and Computers, Asilomar, CA