Speech Deepfake Detection on FSW (ACC%)
92.77ACCXLS-R-1B
Evaluation results
| Method | Links | |
|---|---|---|
| XLS-R-1B#Params=965M, #Hours=12k, Training Protocol=DOSS-Weight2025.12 | 92.77 | |
| XLS-R-300M#Params=317M, #Hours=12k, Training Protocol=DOSS-Weight2025.12 | 89.31 | |
| XLS-R-1B#Params=965M, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | 76.92 | |
| XLS-R-2B#Params=2.2B, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | 75.83 | |
| MMS-300M#Params=317M, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | 73.13 | |
| MMS-1B#Params=965M, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | 70.21 |