List your company

Music Classification on VocalSound

93.59AccuracyQwen2-Audio + CoAT
87.880489.362790.84592.3273Jun 5, 2026

Evaluation results

MethodLinks
Qwen2-Audio + CoATBackbone=Qwen2-Audio, Method=CoAT2026.0693.59
Audio Flamingo 3Backbone=Audio Flamingo 3, Method=Baseline2026.0693.06
Audio Flamingo 3 + CoATBackbone=Audio Flamingo 3, Method=CoAT2026.0692.39
Qwen2.5-Omni-7B + CoATBackbone=Qwen2.5-Omni-7B, Method=CoAT2026.0691.7
Qwen2.5-Omni-7BBackbone=Qwen2.5-Omni-7B, Method=Baseline2026.0691.36
Qwen2-AudioBackbone=Qwen2-Audio, Method=Baseline2026.0688.1