Audio Classification on D-SUPERB
67.5LID AccuracyPEAV S
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=30 FPS2025.12 | 67.5 | 72.5 | 52.1 | 81.4 | |
| PEAV BA-Enc Params.=0.2B, Data (M)=124, Sampling=30 FPS2025.12 | 66.5 | 82 | 44.2 | 85.6 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=30 FPS2025.12 | 64.5 | 72 | 43.8 | 86.1 | |
| PEAV BA-Enc Params.=.2B, Data (M)=124, Sampling=16 Frames2025.12 | 64 | 75.5 | 51.3 | 84.2 | |
| PEAV SA-Enc Params.=.09B, Data (M)=124, Sampling=16 Frames2025.12 | 62 | 69.5 | 52.1 | 81.7 | |
| PEAV LA-Enc Params.=1.1B, Data (M)=124, Sampling=16 Frames2025.12 | 62 | 80 | 47.9 | 85.4 | |
| PEAV L-OODA-Enc Params.=1.1B, Data (M)=114, Sampling=30 FPS, OOD=true2025.12 | 59.5 | 89.5 | 46.3 | 82.5 | |
| PEAV L (PT)A-Enc Params.=1.1B, Data (M)=92, Sampling=30 FPS, PT=true2025.12 | 47 | 88 | 35.8 | 78.5 | |
| ImageBindA-Enc Params.=.09B, Data (M)=32025.12 | 39 | 66.5 | 29.6 | 29.9 | |
| MS-CLAP23’A-Enc Params.=.08B, Data (M)=0.12025.12 | 36 | 74.5 | 25 | 82.4 | |
| CLAPA-Enc Params.=.03B, Data (M)=32025.12 | 23 | 72.5 | 22.5 | 77.4 | |
| LangBindA-Enc Params.=0.3B, Data (M)=102025.12 | 20.5 | 89 | 14.6 | 50.8 | |
| AFlamingo2A-Enc Params.=0.3B, Data (M)=82025.12 | 20 | 67.5 | 21.3 | 38.1 | |
| CLAP-FusionA-Enc Params.=.03B, Data (M)=32025.12 | 17.5 | 62.5 | 22.5 | 76.9 | |
| M2D-CLAPA-Enc Params.=.09B, Data (M)=22025.12 | 16.5 | 57.5 | 12.9 | 61.7 |