Speech Deepfake Detection on ADD ASVspoof 2023
2.25EERXLS-R-1B
Evaluation results
| Method | Links | |
|---|---|---|
| XLS-R-1BTraining Strategy=DOSS-Weight, #Params=965M, #Hours=12k2025.12 | 2.25 | |
| XLS-R-300MTraining Strategy=DOSS-Weight, #Params=317M, #Hours=12k2025.12 | 3.63 | |
| SOTATraining Strategy=Existing Benchmarks2025.12 | 4.67 | |
| XLS-R-2BTraining Strategy=Naive Aggregation, #Params=2.2B, #Hours=74k2025.12 | 4.67 | |
| XLS-R-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 5.39 | |
| MMS-300MTraining Strategy=Naive Aggregation, #Params=317M, #Hours=74k2025.12 | 7.96 | |
| MMS-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 9.05 |