Audio Captioning on MusicCaps
23.33Captioning ScorePAR (Ours-UTS)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PAR (Ours-UTS)Label=Tag Sequence*, Evaluation Protocol=audio-language alignment2026.03 | 23.33 | — | |
| MTC (Ours-UTS)Label=Tag*, Evaluation Protocol=audio-language alignment2026.03 | 23.28 | — | |
| Multi-Task (Ours)Label=Tag*, Caption*, Evaluation Protocol=audio-language alignment2026.03 | 23.09 | — | |
| MTC (AudioSet)Label=Tag, Evaluation Protocol=audio-language alignment2026.03 | 22.91 | — | |
| Contrastive-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.03 | 22.83 | — | |
| Captioning-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.03 | 22.83 | — | |
| Captioning-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.03 | 22.62 | — | |
| Contrastive-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.03 | 22.07 | — | |
| Kimi-Audio-InstructDecoder Size=7B2025.08 | — | 35.43 | |
| MiDashengLMDecoder Size=7B2025.08 | — | 59.71 | |
| Qwen2.5-OmniDecoder Size=7B2025.08 | — | 43.71 |