Speech Deepfake Detection on ADD ASVspoof 2022
0.82EERXLS-R-300M
Evaluation results
| Method | Links | |
|---|---|---|
| XLS-R-300MTraining Strategy=DOSS-Weight, #Params=317M, #Hours=12k2025.12 | 0.82 | |
| SOTATraining Strategy=Existing Benchmarks2025.12 | 1.05 | |
| XLS-R-2BTraining Strategy=Naive Aggregation, #Params=2.2B, #Hours=74k2025.12 | 1.05 | |
| XLS-R-1BTraining Strategy=DOSS-Weight, #Params=965M, #Hours=12k2025.12 | 1.4 | |
| XLS-R-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 1.68 | |
| MMS-300MTraining Strategy=Naive Aggregation, #Params=317M, #Hours=74k2025.12 | 2.64 | |
| MMS-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 2.76 |