VOICE RESEMBLANCE ANALYSIS ON MOBILE PHONE’S VOICE RECORDER (AUDIO FORENSIC METHOD)

Abstract

Audio forensics is one of the sciences that juxtaposes science and scientific methods in sound 
recording analysis to assist and support the disclosure of a crime required in the trial process. This article is intended to analyze voice resemblance towards mobile phone’s voice recorder: an implementation of the forensic method using voice recognition technique, by using Forensic audio method In Audio forensics: Theory and analysis, namely pitch statistical analysis, formant and bandwidth statistical analysis, graphical distribution analysis and spectrogram analysis. However, in this study, researchers only focus on identifying pitch and  formants in the data to be analyzed. This study aims to provide an example scenario of the application of digital  forensic techniques for voice recognition. 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 this study, a PRAAT application was used to help with the  audio comparison process from Known Samples and Unknown Samples. The results showed that most of the F1-F4 values of the comparison voices showed higher results than the original voices. However, several voices  have F1-F4 results close to the original sound, namely PP2 on behalf of Dayu Inten and PP4 on behalf of  Chandra.