High-quality voice recordings captured at CD quality from a Motorola Moto G4 smartphone in a clinical setting at King's College London Hospital. The dataset includes participants with early and advanced Parkinson's disease and healthy controls, labeled with Hoehn & Yahr and UPDRS clinical scores. Recordings were made in September 2017 using a custom app that triggered on phone call signals.
Use Cases
- Train models for Parkinson's disease detection based on voice recordings from a mobile device.
- Analyze correlations between voice features and clinical severity scores like Hoehn & Yahr and UPDRS.
- Develop methods for audio-based health monitoring using realistic phone call scenarios.
- Benchmark audio preprocessing techniques for clinical recordings captured in a room with specific reverberation.
Strengths
- Recordings are high quality with a sample rate of 44.1 kHz and 16-bit depth.
- Data includes clinical labels for Hoehn & Yahr and UPDRS scales for each participant.
- Recordings were performed in a controlled, realistic phone call scenario to ensure clean audio.
Limitations
- Row count and total dataset size are unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
- Last update date is unknown; freshness unverified.
Provenance
- Source
- Recorded at King's College London Hospital by Hagen Jaeger of the Fraunhofer Institute for Intelligent Analysis and Information Systems.
- Collection Method
- Voice recordings were captured using a custom Android app on a Motorola Moto G4 during simulated phone calls where participants read texts and engaged in spontaneous dialog.
- Time Range
- Recorded from 26 to 29 September 2017.
- Geography
- London, United Kingdom (King's College London Hospital, Denmark Hill, Brixton).