It's Time to Take Action: Acoustic Modeling of Motor Verbs to Detect Parkinson's Disease
Escobar-Grisales D, Ríos-Urrego CD, Baumann I, Riedhammer K, Nöth E, Bocklet T, Garcia AM, Orozco-Arroyave JR (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: International Speech Communication Association
Pages Range: 1965-1969
Conference Proceedings Title: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Event location: Kos Island, GRC
DOI: 10.21437/Interspeech.2024-2205
Abstract
Pre-trained models generate speech representations that are used in different tasks, including the automatic detection of Parkinson's disease (PD). Although these models can yield high accuracy, their interpretation is still challenging. This paper used a pre-trained Wav2vec 2.0 model to represent speech frames of 25ms length and perform a frame-by-frame discrimination between PD patients and healthy control (HC) subjects. This fine granularity prediction enabled us to identify specific linguistic segments with high discrimination capability. Speech representations of all produced verbs were compared w.r.t. nouns and the first ones yielded higher accuracies. To gain a deeper understanding of this pattern, representations of motor and non-motor verbs were compared and the first ones yielded better results, with accuracies of around 83% in an independent test set. These findings support well-established neurocognitive models about action-related language highlighted as key drivers of PD.
Authors with CRIS profile
Involved external institutions
Universidad de Antioquía (UDEA)
Colombia (CO)
Technische Hochschule Nürnberg "Georg Simon Ohm"
Germany (DE)
Universidad de San Andrés
Argentina (AR)
Colombia (CO)
Technische Hochschule Nürnberg "Georg Simon Ohm"
Germany (DE)
Universidad de San Andrés
Argentina (AR)
How to cite
APA:
Escobar-Grisales, D., Ríos-Urrego, C.D., Baumann, I., Riedhammer, K., Nöth, E., Bocklet, T.,... Orozco-Arroyave, J.R. (2024). It's Time to Take Action: Acoustic Modeling of Motor Verbs to Detect Parkinson's Disease. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 1965-1969). Kos Island, GRC: International Speech Communication Association.
MLA:
Escobar-Grisales, Daniel, et al. "It's Time to Take Action: Acoustic Modeling of Motor Verbs to Detect Parkinson's Disease." Proceedings of the 25th Interspeech Conferece 2024, Kos Island, GRC International Speech Communication Association, 2024. 1965-1969.
BibTeX: Download