Audio Deepfake Detection on Kokoro-82M
0FNRUnconditional Sampling
Evaluation results
| Method | Links | |
|---|---|---|
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=ConstantQ2026.06 | 0 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MelSpectrogram2026.06 | 0 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MFCC2026.06 | 0 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=ConstantQ2026.06 | 0.1 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=ConstantQ2026.06 | 1.89 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MelSpectrogram2026.06 | 7.52 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MFCC2026.06 | 8.62 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MFCC2026.06 | 16.8 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=VoxCelebSpoof, Visualization=MelSpectrogram2026.06 | 39.72 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=ConstantQ2026.06 | 59.44 | |
| Unconditional SamplingDetector Backbone=AST, Training Dataset=ASVspoof52026.06 | 95.64 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MFCC2026.06 | 99.68 | |
| Unconditional SamplingDetector Backbone=AST, Training Dataset=VoxCelebSpoof2026.06 | 99.72 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=ConstantQ2026.06 | 99.8 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=ConstantQ2026.06 | 99.8 | |
| FoeGlass (Cold Start)Detector Backbone=AST, Training Dataset=ASVspoof52026.06 | 99.93 | |
| Unconditional SamplingDetector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MelSpectrogram2026.06 | 100 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MelSpectrogram2026.06 | 100 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MelSpectrogram2026.06 | 100 | |
| FoeGlass (Cold Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MFCC2026.06 | 100 | |
| FoeGlass (Warm Start)Detector Backbone=VIT, Training Dataset=ASVspoof5, Visualization=MFCC2026.06 | 100 | |
| FoeGlass (Warm Start)Detector Backbone=AST, Training Dataset=ASVspoof52026.06 | 100 | |
| FoeGlass (Cold Start)Detector Backbone=AST, Training Dataset=VoxCelebSpoof2026.06 | 100 | |
| FoeGlass (Warm Start)Detector Backbone=AST, Training Dataset=VoxCelebSpoof2026.06 | 100 |