Acoustic Analysis for Detection of Voice Disorders Using Adaptive Features and Classifiers

Voice diseases are increasing dramatically, due mainly to unhealthy social habits and voice abuse. In this paper, we investigate the methods of acoustic voice analysis (AVA) with adaptive features to develop a system for voice pathologies detection, where the models correspond to classes of patients who share the same diagnostic. One essential part in this topic is the database (described later), the samples voices (healthy and pathological) are chosen from a German database which contains many diseases, nonneurological pathologies (such as chronical laryngitis and Vocal fold nodules), is proposed for this study. A supervised algorithm is used to accomplish this task, Mel frequency cepstral coefficients (MFCCs with variation of Jitter & shimmer), and modeled by weighted Gaussian mixture model (GMM) as it is used in AVA. The work is simulated using MATLAB, for features extraction, for training and testing steps. The results are encouraging for further improvement of combining classifiers and investigation multi-pathologies classifier. KeywordsVoice disorders, Acoustic voice analysis, classifiction techniques, Jitter and Shimmer, laryngeal deseases.