Open-formed Audio Question Answering on AIR-Bench Music
6.16ScoreMTC (Ours-UTS)
Evaluation Results
| Method | Links | |
|---|---|---|
| MTC (Ours-UTS)Training Data=UTS2026.03 | 6.16 | |
| Multi-Task (Ours)Training Data=Caption*, Tag*2026.03 | 6.15 | |
| PAR (Ours-UTS)Training Data=UTS2026.03 | 6.03 | |
| Contrastive-scratch (Ours)Training Data=Caption*2026.03 | 6.02 | |
| Contrastive-scratch [78]Training Data=Original Captions2026.03 | 5.99 | |
| Captioning-scratch (Ours)Training Data=Caption*2026.03 | 5.93 | |
| Captioning-scratch [78]Training Data=Original Captions2026.03 | 5.73 | |
| MTC (AudioSet)Training Data=AudioSet2026.03 | 5.61 |