Rostami Amir Mohammad ; Homayounpour Mohammad Mehdi ; Nickabadi Ahmad

Abstract

Many endeavors have sought to develop countermeasure techniques asenhancements on Automatic Speaker Verification (ASV) systems, in order to makethem more robust against spoof attacks. As evidenced by the latest ASVspoof2019 countermeasure challenge, models currently deployed for the task of ASVare, at their best, devoid of suitable degrees of generalization to unseenattacks. Upon further investigation of the proposed methods, it appears that abroader three-tiered view of the proposed systems. comprised of the classifier,feature extraction phase, and model loss function, may to some extent lessenthe problem. Accordingly, the present study proposes the Efficient AttentionBranch Network (EABN) modular architecture with a combined loss function toaddress the generalization problem...