Speech Deepfake Detection on ODSS
1.13EER (%)SOTA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SOTATraining Strategy=Existing Benchmarks2025.12 | 1.13 | — | |
| XLS-R-2BTraining Strategy=Naive Aggregation, #Params=2.2B, #Hours=74k2025.12 | 1.13 | — | |
| XLS-R-1BTraining Strategy=DOSS-Weight, #Params=965M, #Hours=12k2025.12 | 1.23 | — | |
| XLS-R-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 1.53 | — | |
| XLS-R-300MTraining Strategy=DOSS-Weight, #Params=317M, #Hours=12k2025.12 | 1.65 | — | |
| MMS-1BTraining Strategy=Naive Aggregation, #Params=965M, #Hours=74k2025.12 | 5.49 | — | |
| MMS-300MTraining Strategy=Naive Aggregation, #Params=317M, #Hours=74k2025.12 | 13.34 | — | |
| MMS-1B#Params=965M, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | — | 95.01 | |
| MMS-300M#Params=317M, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | — | 86.59 | |
| XLS-R-1B#Params=965M, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | — | 98.46 | |
| XLS-R-1B#Params=965M, #Hours=12k, Training Protocol=DOSS-Weight2025.12 | — | 96.34 | |
| XLS-R-2B#Params=2.2B, #Hours=74k, Training Protocol=Naive Aggregation2025.12 | — | 98.92 | |
| XLS-R-300M#Params=317M, #Hours=12k, Training Protocol=DOSS-Weight2025.12 | — | 97.01 |