Visual and auditory analysis methods for speaker recognition in digital forensic

摘要

In the first part of this study, the basic concepts of forensic phonetics such as voice, speech, and voice track are explained. In the second part; visual and auditory montage detection methods used in forensic phonetics, one of the lower branches of digital forensics, were examined. The most frequently used visual and auditory analysis methods have been determined by examining the literature. Then detailed information was given about them. Sound is a wave movement that creates a feeling of hearing in the ear by vibrating the molecules with a certain frequency and intensity with the movement of an object. The human voice has many unique features that called voice-print. Voice-print is frequently used in forensic phonetics to illuminate the crime. Voice is a reliable evidence used to detect guilt or detect a criminal. There are software that can do autonomous audio analysis. In addition, statistical and mathematical methods, artificial intelligence methods can be used. Visual and auditory analysis are performed on the sound and then evaluation is made according to different criteria. The success rate in speaker recognition methods is 85%-99%. Generally, the rate of misrecognition is 3% and the rate of non-recognition is 10%.