List your company

Audio Classification on AIR-Bench Speech

47.16Emotion Acc (MELD)MTC (AudioSet)
16.729624.629832.5340.4302Mar 26, 2026

Evaluation results

MethodLinks
MTC (AudioSet)Training Data=AudioSet2026.0347.1625.947.2745.0637.24
Contrastive-scratch (Ours)Training Data=Caption*2026.0344.0841.3473.1177.8240.48
Multi-Task (Ours)Training Data=Caption*, Tag*2026.0341.732.8653.385765.47
MTC (Ours-UTS)Training Data=UTS2026.0339.1948.7974.4592.6486.59
Contrastive-scratch [78]Training Data=Original Captions2026.0329.6148.7955.2584.8586.59
Captioning-scratch (Ours)Training Data=Caption*2026.0323.4729.946.428.0218.82
Captioning-scratch [78]Training Data=Original Captions2026.0322.9337.470.278.9340.14
PAR (Ours-UTS)Training Data=UTS2026.0317.938.6447.8237.457.16