Environmental Sound Deepfake Detection on EnvSDD Track 2 Progress-phase 1.0
0.3EEREnsemble
Evaluation results
| Method | Links | |
|---|---|---|
| EnsembleEnsemble components=0.4×BEATs-AASIST + 0.6×BEAT2AASIST (Freq., CNN-gate, k=4)2025.12 | 0.3 | |
| BEAT2AASISTFusion strategy=Frequency-based, Gate type=CNN-gate, k (number of layers)=42025.12 | 0.42 | |
| BEATs-AASISTFusion strategy=Concatenation, k (number of layers)=42025.12 | 0.61 |