T01 - Digital biomarkers for speech changes in Parkinson‘s disease
The project aims to transfer foundational knowledge about phonetic-prosodic changes in the speech system of neurotypical and pathological speakers into a clinical context. Together with our industry partner ki:elements GmbH, we are developing an algorithm that reliably detects clinically relevant speech changes in Parkinson’s disease using digital biomarkers. The algorithm is intended for long-term use in clinical practice to help preserve the communication abilities of Parkinson's patients through timely speech therapy.
Team
Prof. Dr. Michael T. Barbe
Project Leader T01
Office: Neurology, Kerpener Str. 62E-Mail: michael.barbe(at)uk-koeln.dePhone: (+49) 221 478-7494
Dr. Tabea Thies
Postdoc T01
Office: Neurology, Kerpener Str. 62E-Mail: tabea.thies(at)uk-koeln.dePhone: (+49) 221 478-98578
Dr. Ilona Rubi-Fessen
Associated Researcher T01
Office: Chair in Speech Language Pathology, Klosterstr. 1E-Mail: ilona.rubi-fessen(at)uni-koeln.dePhone: (+49) 221 470-5508
Dr. Joshua Strelow
Postdoc T01
Office: Neurology, Kerpener Str. 62E-Mail: joshua.strelow2(at)uk-koeln.dePhone: (+49) 221 478-4013
Dr. Johannes Tröger
Project partner T01
Office: Bleichstr. 27, SaarbrückenE-Mail: info(at)ki-elements.dePhone: (+49) 681372009200
ki:elements GmbH
Project Partner T01
Office: Bleichstr. 27, SaarbrückenE-Mail: info(at)ki-elements.dePhone: (+49) 681372009200
Student Assistants
Helene Becker | helene.becker(at)uni-koeln.de
Felix Kopner | felix.kopner(at)uni-koeln.de
Ursel Unkelbach | ursel.unkelbach(at)uni-koeln.de
Publications
2025
- Herbig, Elisa, Doris Mücke, Michael T. Barbe & Tabea Thies. 2025. Executive dysfunctions impair and levodopa improves articulatory timing in Parkinson’s disease. Frontiers in Human Neuroscience 19.
- Thies, Tabea, Elisa Mallick, Johannes Tröger, Ebru Baykara, Doris Mücke & Michael T. Barbe. 2025. Automatic speech analysis combined with machine learning reliably predicts the motor state in people with Parkinson’s disease. npj Parkinsons Disease 11(105). pdf
