Table 5 Comparison with a base model
From: DeepDet: YAMNet with BottleNeck Attention Module (BAM) for TTS synthesis detection
Model | Accuracy(%) | Precision(%) | Recall(%) | EER(%) |
|---|---|---|---|---|
Base network | 90.1 | 93.4 | 91.1 | 2.3 |
YAMNet with BN and BAN | 95.4 | 97.3 | 95.4 | 1.30 |
DeepDet | 99.92 | 99.2 | 99.76 | 0.042 |