Automated Audio Captioning on Clotho (evaluation)
33.2SPIDErSLAM-LLM
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| SLAM-LLMPre-training Data=AC+CL_P+WC+MA2026.01 | 33.2 | 19.7 | 51.5 | 14.8 | 33 | 54 | |
| LOAEPre-training Data=AC+CL+WC2026.01 | 33.1 | 19.7 | 51.4 | 14.7 | 32.8 | 53.2 | |
| CAT2026.01 | 32.8 | 19.8 | 50.7 | 14.9 | 32.6 | 53.1 | |
| Wu et al.Pre-training Data=AC+CL_C2026.01 | 32.6 | 19.3 | 50.6 | 14.6 | 32.6 | 53.6 | |
| Tang et al.Pre-training Data=AC+CL+WC+LS+GS2026.01 | 31.8 | — | — | — | — | — | |
| WavCapsPre-training Data=AC+CL+WC2026.01 | 31 | 18.5 | 48.8 | 13.3 | 29.6 | 50.1 | |
| BEATs2026.01 | 31 | 18.5 | 48.8 | 13.3 | 29.6 | 50.1 | |
| EnCLAP-largePre-training Data=AC+CL2026.01 | 29.9 | 18.6 | 46.4 | 13.3 | 28.9 | 50.7 | |
| Audio-MAE2026.01 | 20.8 | 15.6 | 31.2 | 10.5 | 20.8 | 41.8 | |
| AST2026.01 | 6 | 8.9 | 8.1 | 4 | 6 | 21.4 |