| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Impact sound synthesis | Greatest Hits (test) | KL Div.2.04 | 10 | |
| Conditional Foley Generation | Greatest Hits perceptual study evaluation set (test) | Material Chosen Rate64.7 | 9 | |
| Action Classification | Greatest Hits (test) | Match Accuracy78.2 | 8 | |
| Material Classification | Greatest Hits (test) | Match Accuracy54.8 | 8 | |
| Onset Prediction | Greatest Hits (test) | Onset Acc26.5 | 7 | |
| Predicting Sounds from Video | Greatest Hits | Loudness Error0.21 | 5 | |
| Video-to-audio generation | Greatest Hits | Accuracy23.94 | 2 |