A knowledge-driven vowel-based approach of depression classification from speech using data augmentation

TL;DR

This paper introduces an explainable, vowel-based deep learning approach for depression detection from speech, utilizing data augmentation and modeling temporal dependencies at multiple granularities, achieving competitive results.

Contribution

The study presents a novel vowel-level embedding method with data augmentation for depression classification, enhancing interpretability and temporal modeling in speech analysis.

Findings

Achieves comparable performance to state-of-the-art methods

Provides explainable insights into depression detection

Effective across various temporal granularities

Abstract

We propose a novel explainable machine learning (ML) model that identifies depression from speech, by modeling the temporal dependencies across utterances and utilizing the spectrotemporal information at the vowel level. Our method first models the variable-length utterances at the local-level into a fixed-size vowel-based embedding using a convolutional neural network with a spatial pyramid pooling layer ("vowel CNN"). Following that, the depression is classified at the global-level from a group of vowel CNN embeddings that serve as the input of another 1D CNN ("depression CNN"). Different data augmentation methods are designed for both the training of vowel CNN and depression CNN. We investigate the performance of the proposed system at various temporal granularities when modeling short, medium, and long analysis windows, corresponding to 10, 21, and 42 utterances, respectively. The proposed method reaches comparable performance with previous state-of-the-art approaches and depicts explainable properties with respect to the depression outcome. The findings from this work may benefit clinicians by providing additional intuitions during joint human-ML decision-making tasks.