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

2025-08-25

AI Summary

This study investigates the feasibility of detecting depressive symptoms in individuals with multiple sclerosis (MS) using speech-based AI, with emphasis on cross-corpus and cross-lingual generalizability. Addressing the unique challenges of affect recognition in MS comorbidity, we propose a supervised learning framework integrating conventional acoustic features, pretrained speech emotion representations, and exploratory vocal biomarkers, enhanced by feature selection to optimize performance. Evaluated on multilingual, multi-source datasets, the model achieves an unweighted average recall (UAR) of 66% for binary depression classification, improving to 74% after feature selection. Key contributions are: (1) the first application of speech-based depression detection to neurodegenerative disease populations with psychiatric comorbidity; (2) empirical validation of the cross-population transferability and clinical interpretability of depression-related vocal features in MS; and (3) a scalable, low-resource technical pipeline for cross-cohort clinical screening support.

Technology Category

• Natural Language Processing: Speech
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Detecting depression in Multiple Sclerosis patients using speech
• Cross-lingual speech analysis for depressive mood detection
• Evaluating emotional speech features for depression identification

Innovation

• Cross-corpus and cross-lingual analysis approach
• Combined conventional and emotional speech features
• Feature selection boosting detection performance