%Aigaion2 BibTeX export from Idiap Publications %Monday 20 January 2025 03:43:58 PM @INPROCEEDINGS{Purohit_ICASSP_2025, author = {Purohit, Tilak and Ruvolo, Barbara and Orozco-Arroyave, Juan Rafael and Magimai-Doss, Mathew}, projects = {EMIL}, title = {Automatic Parkinson's disease detection from speech: Layer selection vs adaptation of foundation models}, booktitle = {Proceedings of IEEE International Conference Acoustics, Speech, and Signal Processing (ICASSP)}, year = {2025}, abstract = {In this work, we investigate Speech Foundation Models (SFMs) for Parkinson’s Disease (PD) detection. We explore two main approaches: using SFMs as frozen feature extractors and fine-tuning/adapting them for PD detection tasks. We propose a cross-validation based layer selection methodology to identify the layer effective for PD detection. Additionally, we compare the performance of the layer selection scheme with full fine- tuning and parameter-efficient fine-tuning (PEFT) using Low- Rank Adaptation (LoRA). Our results show that layer selection and LoRA based fine-tuning can perform on par with full fine- tuning, providing a more parameter-cost efficient alternative. The highest accuracy was achieved by fine-tuning Whisper with LoRA.}, pdf = {https://publications.idiap.ch/attachments/papers/2025/Purohit_ICASSP_2025.pdf} }