Ensemble and Multimodal Learning for Pathological Voice Classification

Abstract

Voice disorders are one of the most common medical diseases in modern society, especially for occupational voice demand. This letter investigates a stacked ensemble learning method to classify pathological voice disorders by combining acoustic signals and medical records. In the proposed ensemble learning framework, stacked support vector machines (SVMs) form a set of weak classifiers, and a deep neural network (DNN) acts as a metalearner. Acoustic features and medical records are combined to attain better classification performance based on the high complexity of metalearner. Results showed that the proposed approach significantly outperformed individual SVM and DNN classifiers and showed a performance improvement over the two-stage DNN-based fusion classifier. The proposed approach achieved 89.83 accuracy and 85.84% unweighted average recall in a three-disorder classification task, confirming the effectiveness of the ensemble learning for pathological voice classification.