Audio Understanding on Dynamic-Superb (test)
88.95CON AccuracyDeSTA2.5-Audio
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| DeSTA2.5-Audio2025.07 | 88.95 | — | — | — | — | 66 | 63.71 | 65.08 | 56.1 | 69.53 | |
| ASR+AAC+LLM2025.07 | 82.77 | — | — | — | — | 68.58 | 45.93 | 54.87 | 48.1 | 60.97 | |
| DeSTA22025.07 | 79.41 | — | — | — | — | 59.42 | 43.14 | 51.63 | 42.5 | 56.78 | |
| Qwen2-Audio-Instruct2025.07 | 77.64 | — | — | — | — | 59.17 | 29.21 | 43.58 | 47.9 | 51.69 | |
| ASR+LLM2025.07 | 73.05 | — | — | — | — | 59.67 | 40.5 | 43.13 | 43.5 | 51.71 | |
| Qwen-Audio2025.07 | 61.77 | — | — | — | — | 47.17 | 28.64 | 30.95 | 41.4 | 40.79 | |
| SALMONN2025.07 | 52 | — | — | — | — | 50.75 | 24.5 | 28.16 | 33.2 | 36.44 | |
| LTU-AS2025.07 | 43.95 | — | — | — | — | 36 | 17.14 | 37.53 | 40.2 | 36.11 | |
| ASR-ChatGPT2024.06 | — | 7 | 15 | 3 | 96 | — | — | — | — | — | |
| ImageBind-LLM2024.06 | — | 19 | 28 | 44 | 26 | — | — | — | — | — | |
| UniAudio 1.52024.06 | — | 24 | 50 | 55 | 25 | — | — | — | — | — | |
| Whisper-LLM2024.06 | — | 4 | 14 | 58 | 13 | — | — | — | — | — |