Speech Deepfake Detection on DV
0.86EERXLS-R-1B
Evaluation results
| Method | Links | |
|---|---|---|
| XLS-R-1BTraining Strategy=DOSS-Weight, #Params=965M, #Hours=12k2025.12 | 0.86 | |
| XLS-R-300MTraining Strategy=DOSS-Weight, #Params=317M, #Hours=12k2025.12 | 0.97 | |
| SOTATraining Strategy=Existing Benchmarks2025.12 | 2.27 | |
| MMS-300MTraining Strategy=Naive Aggregation, #Params=317M, #Hours=74k2025.12 | 2.27 | |
| XLS-R-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 2.35 | |
| XLS-R-2BTraining Strategy=Naive Aggregation, #Params=2.2B, #Hours=74k2025.12 | 2.35 | |
| MMS-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 2.47 |