List your company

Automated Audio Captioning on Clotho (evaluation)

33.2SPIDErSLAM-LLM
4.91212.25619.626.944Jan 14, 2026Jan 16, 2026Jan 19, 2026Jan 21, 2026Jan 24, 2026Jan 26, 2026Jan 29, 2026

Evaluation results

MethodLinks
SLAM-LLMPre-training Data=AC+CL_P+WC+MA2026.0133.219.751.514.83354
LOAEPre-training Data=AC+CL+WC2026.0133.119.751.414.732.853.2
CAT2026.0132.819.850.714.932.653.1
Wu et al.Pre-training Data=AC+CL_C2026.0132.619.350.614.632.653.6
Tang et al.Pre-training Data=AC+CL+WC+LS+GS2026.0131.8—————
WavCapsPre-training Data=AC+CL+WC2026.013118.548.813.329.650.1
BEATs2026.013118.548.813.329.650.1
EnCLAP-largePre-training Data=AC+CL2026.0129.918.646.413.328.950.7
Audio-MAE2026.0120.815.631.210.520.841.8
AST2026.0168.98.14621.4