Abstract
•Incremental DBSCAN and SVM methods have been combined to classify pathological voice from normal voice.•DBSCAN algorithm with an incremental learning has been used to detect noises.•For each voices group (normal/pathological), we use a feature technique based on MFCC features.•Incremental DBSCAN-SVM method has been built to incrementally detect noises, analyze and classify pathological voices.
[Display omitted]
Machine learning techniques are a valuable tool for discriminative classification. They have been applied to a diverse range of applications in speech processing, such as the analysis of pathological voices. We propose, in this paper, a novel policy, called Incremental DBSCAN-SVM in order to detect noises, to analyze and to classify pathological voice from normal voice. We use a modified density-based clustering algorithm named DBSCAN with an incremental learning in order to detect noisy samples. Then, the output model is submitted to Support Vector Machines (SVM) classifier with a Radial Basis Function (RBF) kernel to discriminate between normal and pathological voices. Our method has the ability to handle incremental and dynamic voices database which evolve over time. We support our approach with empirical evaluation using voices data set from the Massachusetts Eye and Ear Infirmary Voice and Speech Laboratory (MEEI) database to show the effectiveness of our method in terms of detection voice disorders.