Automated Audio Captioning on Clotho 2.1 (evaluation)
33.4SPIDErLAMB
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| LAMBPT Dataset=AC+CL+WC2026.01 | 33.4 | 19.8 | 52.3 | 14.7 | 33.1 | 53.4 | |
| SLAM-AACPre-training Data=AC+CLp+WC+MA2024.10 | 33.2 | 19.7 | 51.5 | 14.8 | 33 | 54 | |
| SLAM-AACPT Dataset=AC+CLP +WC +MA2026.01 | 33.2 | 19.7 | 51.5 | 14.8 | 33 | 54 | |
| LOAEPT Dataset=AC+CL+WC2026.01 | 33 | 19.7 | 51.3 | 14.7 | 33 | 53.8 | |
| Wu et al.Pre-training Data=AC+CLC2024.10 | 32.6 | 19.3 | 50.6 | 14.6 | 32.6 | 53.6 | |
| MQ-CapPT Dataset=AC+CL+WC+AA2026.01 | 31.9 | — | 49.6 | 14.3 | — | — | |
| Tang et al.Pre-training Data=AC+CL+WC+LS+GS2024.10 | 31.8 | — | — | — | — | — | |
| WavCapsPre-training Data=AC+CL+WC2024.10 | 31 | 18.5 | 48.8 | 13.3 | 29.6 | 50.1 | |
| HTSAT-BARTPT Dataset=AC+CL+WC2026.01 | 31 | 18.5 | 48.8 | 13.3 | 29.6 | 50.1 | |
| CLAP-ARTPT Dataset=- / AC2026.01 | 30.4 | 18.7 | 47.5 | 13.3 | — | 51.1 | |
| EnCLAP-largePre-training Data=AC+CL2024.10 | 29.9 | 18.6 | 46.4 | 13.3 | 28.9 | 50.7 | |
| EnCLAP-largePT Dataset=AC+CL2026.01 | 29.9 | 18.6 | 46.4 | 13.3 | 28.9 | 50.7 |