Cross-Corpus Depression Detection in Semi-Structured Clinical Interviews

(2026)


Publication Type: Conference contribution

Publication year: 2026

Original Authors: Misha Sadeghi, Phuc Truong Loc Nguyen, Andreas Triantafyllopoulos, Mahdis Habibpour, Robert Richer, Lydia Helene Rupp, Lena Schindler-Gmelch, Marie Keinert, Malin Hager, Björn Schuller, Bernhard Egger, Matthias Berking, Bjoern Eskofier

Pages Range: 60628-60646

DOI: 10.18653/2026.emnlp-main.2663

Abstract

Previous work links Major Depressive Disorder (MDD) to linguistic and paralinguistic speech patterns, highlighting speech analysis as a potential diagnostic tool for remote monitoring or clinical decision support (CDS) systems. Recent attempts to build MDD diagnostic models primarily rely on the English (E-)DAIC corpus. Despite promising results, these works rarely evaluate cross-corpus generalization and rely on self-reported questionnaires, limiting their clinical utility. We introduce a new, clinically validated German corpus, EmpkinS-EKSpression, of semi-structured diagnostic interviews to test the reliability of spoken language-based measures of MDD. Our model achieves an F1-score of 0.86 on the EmpkinS-EKSpression dataset and 0.74 on E-DAIC via zero-shot cross-corpus transfer, suggesting that MDD detection models can generalize across corpora and languages despite differences in interview format and ground truth definition, supporting further development of CDS systems.

Authors with CRIS profile

Involved external institutions