Sound Event Recognition on AudioSet dynamic single-source moving clips
62.8mAPST-Audio Encoder
Evaluation results
| Method | Links | |
|---|---|---|
| ST-Audio EncoderInput=FOA2026.06 | 62.8 | |
| Spatial-AST-FOA (temporal crop)Input=FOA2026.06 | 45.2 | |
| PSELDNets-mACCDOA + sem./dist. headsInput=FOA2026.06 | 29.7 |