A Comparison of SSL-Based Feature Extractors and Back-End Classifiers for Spoofing Detection: A Multi-Corpus Training and Cross-Linguistic Analysis
About
Voice biometric systems face growing threats from spoofing attacks, yet the evaluation of detection models remains inconsistent across datasets. To investigate these unpredictable fluctuations, we conduct a comprehensive benchmark of four self-supervised learning feature extractors paired with four back-end classifiers. We compare the hierarchical local feature extraction of ResNet with the global sequence and relational modeling of attention and graph-based back-ends. Through multi-corpus training across three scenarios and six evaluation datasets, our empirical analysis yields two critical findings. First, we expose a domain bias within the ASVspoof 5 dataset, showing that naive data scaling actively degrades performance. Second, our cross-linguistic analysis reveals that fine-tuning with just 8 hours of target-language data enhances detection robustness. Together, these findings emphasize the critical need for domain-aware and language-specific adaptation in spoofing detection.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Audio anti-spoofing | ASVspoof DF 2021 (hidden) | EER3.03 | 19 | |
| Audio anti-spoofing | ASVspoof LA 2021 (hidden) | EER5.21 | 19 | |
| Audio anti-spoofing | ASVspoof 5 (evaluation) | EER4.73 | 17 | |
| Audio anti-spoofing | Wild | EER0.0121 | 12 | |
| Audio anti-spoofing | Fake-Or-Real | EER0.13 | 12 | |
| Audio anti-spoofing | Average across evaluation datasets | Average EER4.2 | 12 |