Sadeghi M, Loc Nguyen PT, Triantafyllopoulos A, Habibpourfatideh M, Richer R, Rupp L, Schindler-Gmelch L, Keinert M, Hager M, Schuller BW, Egger B, Berking M, Eskofier B (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
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.
APA:
Sadeghi, M., Loc Nguyen, P.T., Triantafyllopoulos, A., Habibpourfatideh, M., Richer, R., Rupp, L.,... Eskofier, B. (2026). Cross-Corpus Depression Detection in Semi-Structured Clinical Interviews. In Proceedings of the Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (pp. 60628-60646).
MLA:
Sadeghi, Misha, et al. "Cross-Corpus Depression Detection in Semi-Structured Clinical Interviews." Proceedings of the Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing 2026. 60628-60646.
BibTeX: Download