Audio Deepfake Detection on VITS
2.16FNRUnconditional Sampling
Evaluation results
| Method | Links | |
|---|---|---|
| Unconditional SamplingDetector Backbone=AST, Training Dataset=ASVspoof52026.06 | 2.16 | |
| FoeGlass (Cold Start)Detector Backbone=AST, Training Dataset=ASVspoof52026.06 | 8.44 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MelSpectrogram2026.06 | 9.04 | |
| FoeGlass (Warm Start)Detector Backbone=AST, Training Dataset=ASVspoof52026.06 | 9.92 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MelSpectrogram2026.06 | 10.72 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MelSpectrogram2026.06 | 11.6 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=ConstantQ2026.06 | 16.85 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MFCC2026.06 | 32.57 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=ConstantQ2026.06 | 42.02 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MelSpectrogram2026.06 | 48.78 | |
| Unconditional SamplingDetector Backbone=AST, Training Dataset=VoxCelebSpoof2026.06 | 51.18 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MFCC2026.06 | 64.24 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=ConstantQ2026.06 | 74.2 | |
| FoeGlass (Cold Start)Detector Backbone=AST, Training Dataset=VoxCelebSpoof2026.06 | 76.21 | |
| FoeGlass (Warm Start)Detector Backbone=AST, Training Dataset=VoxCelebSpoof2026.06 | 79.16 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=ConstantQ2026.06 | 81.34 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MFCC2026.06 | 90.76 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MFCC2026.06 | 93.03 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=ConstantQ2026.06 | 94.04 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MFCC2026.06 | 95.28 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=ConstantQ2026.06 | 96.15 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MelSpectrogram2026.06 | 96.22 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MelSpectrogram2026.06 | 96.96 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MFCC2026.06 | 98.08 |