The existence of highly developed and fully automated telephone networks in industrialized countries and the pervasiveness of speech communication technology have resulted in the ever-increasing use of the human voice as an instrument in the commission of crimes. In malicious activities, the former safeguards a perpetrator’s anonymity, while the latter eases the commission of certain criminal offences such as hoax calling, drug dealing, extortion, and sexual harassment. As a result, forensic automatic speaker recognition (FASR) has become an important tool in forensic sciences, which are defined as the body of scientific principles and technical methods applied to criminal investigations to demonstrate the existence of a crime and help authorities identify the authors and their modus operandi. This article discusses the approaches, potential, and limitations of FASR (which is an exploratory application of digital speech signal processing and pattern recognition for judicial purposes, particularly for law enforcement).