Review of Spoof Detection in Automatic Speaker Verification System

A system that utilizes biometry technology is employed for the automated identification of individuals by leveraging unique biological characteristics. Over the past ten years, the use of biometry for human identification and verification has rapidly increased. Numerous biometric traits are used for verification and identification. Generally, biometric authentication can be susceptible to spoofing attacks, which involve presenting synthetic artifacts to deceive the biometric sensor. To combat this, an anti-spoofing method is needed to distinguish between real biometric traits and fake ones. A software-based anti-spoofing detection method is highly sought after to accurately classify these traits. This research work focuses on investigating spoofing detection techniques for Automatic Speaker Verification (ASV) and conducts a literature review of related research. The review shows a significant increase in research on the theory and practice of spoof detection in ASV, identifying key topics, articles, and author groups. These findings are expected to expand the scope of research into various subfields of ASV in the future.