Optimal Combination of Multivariate Filter Feature Selection and Classifier for Speech-Based Depression Detection

Abstract

In this paper, we have focused to improve the performance of a speech-based uni-modal depression detection system, which is non-invasive, involves low cost and computation time in comparison to multi-modal systems. The performance of a decision system mainly depends on the choice of feature selection method and the classifier. We have investigated the combination of four well-known multivariate filter methods (minimum Redundancy Maximum Relevance, Scatter Ratio, Mahalanobis Distance, Fast Correlation Based feature selection) and four well-known classifiers (k-Nearest Neighbour, Linear Discriminant classifier, Decision Tree, Support Vector Machine) to obtain a minimal set of relevant and non-redundant features to improve the performance. This will speed up the acquisition of features from speech and build the decision system with low cost and complexity. Experimental results on the high and low-level features of recent work on the DAICWOZ dataset demonstrate the superior performance of the combination of Scatter Ratio and LDC as well as that of Mahalanobis Distance and LDC, in comparison to other combinations and existing speech-based depression results, for both gender independent and gender-based studies. Further, these combinations have also outperformed a few multimodal systems. It was noted that low-level features are more discriminatory and provide a better f1 score.