Your Voice Tells a Story — Explore One of the World’s Largest Pathological Voice Databases hosted by the University Hospital Essen and collected by the Saarland University
A clinically validated collection of pathological and non-pathological voice recordings — structured for research, AI development, and reproducibility.
One of the most comprehensive collections of pathological and non-pathological voice recordings — ideal for research in speech, neurology, and AI.
Each audio file includes metadata like emotion, speaker ID, and diagnosis — enabling powerful search and filtering for researchers and developers.
The dataset is organized and labeled for ML workflows — consistent filenames and structured labels make it easy to train supervised models.
All voice recordings are normalized, professionally captured WAV files, providing clean audio data for robust analysis and AI pipelines.
Validated annotations by clinical experts include ALS, Parkinson’s, and control groups — ensuring scientific reliability and reproducibility.
Created & Collected by Saarland University & hosted by University Hospital Essen — free to use for reproducible voice science.
Narrow down the speaker records using gender, pathology type, and diagnosis to focus your search.
| Speaker ID | Gender | Aufnahme Typ | Pathologien |
|---|---|---|---|
| No results match the current filters. | |||
