Vocal Markers of Schizophrenia: Assessing the Generalizability of Machine Learning Models and Their Clinical Applicability
Overall, the cross-linguistic generalizability of vocal markers of schizophrenia is limited. We argue that more emphasis should be placed on collecting large open cross-linguistic datasets to systematically test the generalizability of voice-based ML models, and on identifying more precise mechanisms of how the clinical features of schizophrenia are expressed in language and voice, and how different languages vary in that expression.
Authors
- Arndis Simonsen (ORCID: https://orcid.org/0000-0002-5044-9936)
- Jessica Mary Lin
- Astrid Rybner
- Katja Koelkebeck (ORCID: https://orcid.org/0000-0002-0469-3997)
- Vibeke Bliksted (ORCID: https://orcid.org/0000-0003-4779-0700)
- Riccardo Fusaroli (ORCID: https://orcid.org/0000-0003-4775-5219)
- Yuan Zhou (ORCID: https://orcid.org/0000-0001-6378-1711)
- Alberto Parola (ORCID: https://orcid.org/0000-0002-6039-0907)
- Emil Trenckner Jessen
- Marie Damsgaard Mortensen
- Konstantinos Sechidis (ORCID: https://orcid.org/0000-0001-6582-7453)
- Stine Nyhus Larsen
- Huiling Wang
Institutions
- Novartis (Switzerland) (CH)
- Center for Applied Linguistics (US)
- University of Southern Denmark (DK)
- Aarhus University (DK)
- Odense University Hospital (DK)
- Aarhus University Hospital (DK)
- Wuhan University (CN)
- State and University Library (DK)
- Pennsylvania Academic Library Consortium (US)
- Renmin Hospital of Wuhan University (CN)
- Institute of Physics (CN)
- University of Chinese Academy of Sciences (CN)
- Bethel University (US)
Publication Details
- Journal
- Schizophrenia Bulletin
- Published
- 2025-08-18
- DOI
- https://doi.org/10.1093/schbul/sbaf124
- Citations
- 2
- Primary Topic
- Music and Audio Processing
- Type
- article
- Field-Weighted Citation Impact
- 2.97