RealDESED Benchmark
Explore score history ↗RealDESED is a real-world domestic sound event detection benchmark with 5,710 recordings from 652 participants, 15 classes, and temporally precise annotations. Includes multi-annotator labeling and rich metadata.
- Released
- 2026-07-18
- Institutions
- Johannes Kepler University of Linz
- Evaluates
- General AI, Vision & 3D, eess.AS
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
RealDESED paper, code and dataset
No reported scores are on record for this benchmark yet.