Speech-Based Depressive Mood Detection in the Presence of Multiple Sclerosis: A Cross-Corpus and Cross-Lingual Study

TL;DR

This study explores the feasibility of speech-based AI methods for detecting depression in people with Multiple Sclerosis across different languages and datasets, showing moderate success and highlighting emotional features as key indicators.

Contribution

It introduces a cross-corpus and cross-lingual approach for speech-based depression detection specifically in pwMS, with feature selection improving detection accuracy.

Findings

Achieved 66% UAR in depression detection among pwMS

Feature selection increased UAR to 74%

Emotional features are significant indicators of depression

Abstract

Depression commonly co-occurs with neurodegenerative disorders like Multiple Sclerosis (MS), yet the potential of speech-based Artificial Intelligence for detecting depression in such contexts remains unexplored. This study examines the transferability of speech-based depression detection methods to people with MS (pwMS) through cross-corpus and cross-lingual analysis using English data from the general population and German data from pwMS. Our approach implements supervised machine learning models using: 1) conventional speech and language features commonly used in the field, 2) emotional dimensions derived from a Speech Emotion Recognition (SER) model, and 3) exploratory speech feature analysis. Despite limited data, our models detect depressive mood in pwMS with moderate generalisability, achieving a 66% Unweighted Average Recall (UAR) on a binary task. Feature selection further improved performance, boosting UAR to 74%. Our findings also highlight the relevant role emotional changes have as an indicator of depressive mood in both the general population and within PwMS. This study provides an initial exploration into generalising speech-based depression detection, even in the presence of co-occurring conditions, such as neurodegenerative diseases.