The Implementation of the Forensic Method Using Voice Recognition Technique to Analyze Voice Resemblance Towards Mobile Phone’s Voice Recorder

Abstract

This thesis is intended to analyze the implementation of the forensic method using voice recognition technique to analyze voice resemblance towards mobile phone’s voice recorder, by using Forensic audio method In Audio forensics: Theory and Analysis, namely Pitch Statistical Analysis, Forman and Bandwidth Statistical Analysis, Graphical Distribution Analysis and Spectogram Analysis. However, in this study, researchers only focus on identifying pitch and formants in the data to be analyzed. The aims of this study is to provide an example scenario the application of digital forensic techniques for voice pain recognizes Greetings compare the sound in the evidence and the sound suspect on mobile phone media with a voice case study woman. So it is hoped that the output of this research can become a reference or enrichment material for law enforcement agencies law and academics who wish to continue their research related to digital forensics. In doing on In this study, a Praat application was used to help with the audio comparison process from Known Samples and Unknown Sample. The results of each sample of digital evidence of native speakers' voices and recorded comparisons on the two assessment factors, namely Pitch and Formant, the researcher can't distinguish between the original speaker's voice and the comparison voice.  The researcher can state that the accuracy of the pitch and formant analysis through Praat is very low and cannot be used as an indicator to distinguish that a date is correct as of the original voice, as evidenced by the results of the F0 value of the original voice data and the comparison obtained. Very flexible and inconsistent, some are the same, close to and even far from the F0 value of the subject data. This shows that everyone has a different pitch value because the intonation of each person's word pronunciation is different. It is possible that there are pitch values from several subjects that are almost the same.