Time-Domain Features And Probabilistic Neural Network For The Detection Of Vocal Fold Pathology

Abstract

Due to the nature of job, unhealthy social habits and voice abuse, people are subjected to the risk of voice problems. It is well known that most of vocal fold pathologies cause changes in the acoustic voice signal. Therefore, the voice signal can be a useful tool to diagnose them. Acoustic voice analysis can be used to characterize the pathological voices. This paper presents the detection of vocal fold pathology with the aid of the speech signal recorded from the patients. The speech samples from Massachusetts Eye and Ear Infirmary (MEEI) database are used to evaluate the scheme. Time-domain features based on energy variation are proposed and extracted from the speech to form a feature vector. In order to test the effectiveness and reliability of the proposed time-domain features, a Probabilistic Neural Network (PNN) is employed. The experimental results show that the proposed features gives very promising classification accuracy and can be effectively used to detect the vocal fold pathology clinically.