ARTIFICIAL NEURAL NETWORK BASED PATHOLOGICAL VOICE CLASSIFICATION USING MFCC FEATURES

The analysis of pathological voice is a challenging and an important area of research in speech processing. Acoustic voice analysis can be used to characterize the pathological voices with the aid of the speech signals recorded from the patients. This paper presents a method for the identification and classification of pathological voice using Artificial Neural Network. Multilayer Perceptron Neural Network (MLPNN), Generalised Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) are used for classifying the pathological voices. Mel-Frequency Cepstral Coefficients (MFCC) features extracted from audio recordings are used for this purpose.