Audio Deepfake Detection On Asvspoof 2021
평가 지표
21DF EER
21LA EER
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | 21DF EER | 21LA EER | Paper Title | Repository |
|---|---|---|---|---|
| AASIST | 21.07 | 11.46 | AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks | - |
| BTS-E | / | 8.75 | Bts-e: Audio deepfake detection using breathing-talking-silence encoder | |
| XLSR-Mamba | 1.88 | 0.93 | XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection | - |
| XLSR+SLS | 1.96 | 2.86 | Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier | |
| TCM-Add | 2.14 | 2.99 | Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection | - |
| RawGAT-ST | 23.26 | 10.25 | End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection | - |
| RawNet-2 | 40.06 | 40.07 | End-to-end anti-spoofing with RawNet2 | - |
| XLSR+AASIST | 3.69 | 1.0 | Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation | - |
0 of 8 row(s) selected.