Forensic Speaker Recognition: A Review

Abstract

In recent years, there has been an increase in both scientific and judicial interest in forensic  speaker recognition. Due to the diversity of speakers, speaker recognition is one of the most difficult  challenges in biometric authentication. A forensic expert must assess evidence material during a criminal  inquiry. This paper provides a brief overview of the topic of forensic speaker recognition, as well as  explanations of its approaches, many feature extraction and modelling modules, applications, underlying  techniques, and some performance evaluation indicators. In the overview, the limitations and application  areas of existing forensic speech recognition systems are also discussed. The study concludes with a  discussion of future trends and research prospects in this sector.