Dataset for smartphone mismatch in computer aided diagnosis systems based on speech

Voice analysis-based systems offer low-cost, highly available automatic diagnostic aid for Parkinson’s disease (PD) detection anywhere a smartphone with a broadband connection is available. However, reliability depends on factors affecting the communication channel. The data presented here have been obtained to evaluate the effects of the recording device mismatch.

All the information on data collection and dataset building is presented in the following paper. This paper is encouraged to be cited in case of any scientific research publication is produced using this dataset:

Mario Madruga, Yolanda Campos-Roca, Carlos J. Pérez, Addressing smartphone mismatch in Parkinson’s disease detection aid systems based on speech, Biomedical Signal Processing and Control, Volume 80, Part 1, 2023, 104281, https://doi.org/10.1016/j.bspc.2022.104281

Data are in .csv and .xlms formats. A brief description of attributes can be found in the .pdf file.

This research is part of R&D&I projects PID2021-122209OB-C32 and MTM2017-86875-C3-2-R, funded by Ministerio de Ciencia e Innovación and Agencia Estatal de Investigación, Spain. It has also been funded by Junta de Extremadura, Spain (Projects GR21057 and GR21072), the European Union (European Regional Development Funds), and grant number FPU18/03274.