Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection
This work addresses the critical issue of spoof attack vulnerability in ASV systems, which is essential for security applications, though it appears incremental by building on existing modular approaches.
The study tackled the generalization problem in Automatic Speaker Verification (ASV) spoof detection by proposing an Efficient Attention Branch Network with a combined loss function, achieving improved robustness against unseen spoof attacks as evidenced by performance gains on the ASVspoof 2019 benchmark.
Many endeavors have sought to develop countermeasure techniques as enhancements on Automatic Speaker Verification (ASV) systems, in order to make them more robust against spoof attacks. As evidenced by the latest ASVspoof 2019 countermeasure challenge, models currently deployed for the task of ASV are, at their best, devoid of suitable degrees of generalization to unseen attacks. Upon further investigation of the proposed methods, it appears that a broader three-tiered view of the proposed systems. comprised of the classifier, feature extraction phase, and model loss function, may to some extent lessen the problem. Accordingly, the present study proposes the Efficient Attention Branch Network (EABN) modular architecture with a combined loss function to address the generalization problem...