We have obtained permission from the dataset providers to release these research-only datasets for use in this special session. Papers that incorporate these datasets will be considered under the Focused Track, and their authors may be invited to serve as panelists during the special session. Please note that the datasets are available for OneVoice-MSD-2026 ONLY, and the datasets must be deleted after the paper submission. Further usage of each dataset requires obtaining permission from the owner of each dataset.
Further details about each dataset are provided in the list below. When using the datasets provided through this session, please cite the following paper https://arxiv.org/abs/2603.22225. Respective original datasets:
e-PC-GITA [paper]
Pérez-Toro, P. A., Vasquez-Correa, J. C., Arias-Vergara, T., Klumpp, P., Schuster, M., Nöth, E., & Orozco-Arroyave, J. R. (2021, August). Emotional state modeling for the assessment of depression in Parkinson’s disease. In International Conference on Text, Speech, and Dialogue (pp. 457-468).
GermanPD [paper]
Bocklet, T., Nöth, E., Stemmer, G., Ruzickova, H., & Rusz, J. (2011, December). Detection of persons with Parkinson's disease by acoustic, vocal, and prosodic analysis. In 2011 IEEE workshop on automatic speech recognition & understanding (pp. 478-483).
CzechPD [paper]
Rios-Urrego, C. D., Rusz, J., & Orozco-Arroyave, J. R. (2024). Automatic speech-based assessment to discriminate Parkinson’s disease from essential tremor with a cross-language approach. Digital Medicine, 7(1), 37.
If you want to request access to our collaborative datasets, please fill out this Google Form https://forms.gle/58vskDQBY8xdBNd39.
If you experience any issues accessing the form, please do not hesitate to contact us at onevoice_msd@googlegroups.com
Participants are also encouraged to use their own public or private corpora relevant to MSD research. For those who may need guidance on selecting appropriate datasets for this special session, we have provided the following recommendations.
Potential open-source datasets include, but are not limited to, the following: