Towards evidence based diagnosis of voice disorders using phonovibrograms

Abstract

Clinical diagnosis of voice disorders is based on examination of the oscillating vocal folds during phonation with state-of-the-art endoscopic high-speed cameras. Commonly, the offline analysis is performed in a subjective and time-consuming manner via slow-motion playback. In this study an objective method for overcoming this drawback is presented being based on phonovibrogram (PVG) images. For a set of normal voices and subjects suffering from vocal fold paralysis or functional dysphonia the laryngeal dynamics were captured by specialized phonovibrogram features and classified using a support vector machine (SVM). In case of functional voice disorders a mean classification accuracy of 78.5% was obtained while in vocal fold paralysis a classification accuracy of up to 93% could be obtained. The classification results show that the PVG features hold a lot of promise in supporting diagnosis of voice pathologies even in case of muscle tension dysphonia.