Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches
It addresses the problem of explainable and robust depression diagnosis for clinicians, though it appears incremental by building on existing evidence and methods.
This study tackled depression identification from speech by using vowel-based embeddings and ensemble learning to predict depression symptoms and severity, achieving performance comparable to state-of-the-art baselines with robustness against dataset biases.
This study investigates explainable machine learning algorithms for identifying depression from speech. Grounded in evidence from speech production that depression affects motor control and vowel generation, pre-trained vowel-based embeddings, that integrate semantically meaningful linguistic units, are used. Following that, an ensemble learning approach decomposes the problem into constituent parts characterized by specific depression symptoms and severity levels. Two methods are explored: a "bottom-up" approach with 8 models predicting individual Patient Health Questionnaire-8 (PHQ-8) item scores, and a "top-down" approach using a Mixture of Experts (MoE) with a router module for assessing depression severity. Both methods depict performance comparable to state-of-the-art baselines, demonstrating robustness and reduced susceptibility to dataset mean/median values. System explainability benefits are discussed highlighting their potential to assist clinicians in depression diagnosis and screening.