Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{165285,
        author = {G KRISHNA and Kajal Bansal},
        title = {Forensic Analysis of AI-Modulated Threatening Voices A PRAAT-based Study},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {11},
        number = {1},
        pages = {795-802},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=165285},
        abstract = {Audio analysis is defined as the systematic investigation of recorded audio evidence to determine its origin, content, and authenticity. It plays a vital role in forensic investigations, especially in analysing audio recordings to determine the identity of speakers through comparison of known and unknown samples. Audio comparison involves examining a variety of auditory parameters such as pitch, intensity, jitter, pulse, duration, and spectral characteristics. This investigation seeks to determine the likelihood of a link between recognized and questioned voices. This study examines audio forensics involving AI-altered threatening voices, addressing concerns regarding the potential harm posed by AI's use of voice-altering software to create threatening messages. This study explores a technique called PRAAT analysis to determine if it can effectively identify AI-manipulated voices used for malicious intent. Using a careful methodology, audio samples will be collected from participants acting out threatening scenarios based on prepared prompts. Then, these samples will be altered using software called VOICEMOD CLIPS. The PRAAT software will be used to analyse the original human voice and robotic voices which is modulated using AI, focusing on factors such as pitch, formant frequencies, jitter, pulse and spectrographic representations. By looking at these aspects along with ways to identify speakers and conducting a thorough analysis, the study aims to give useful insights for law enforcement and security agencies dealing with technology-based threat detection.},
        keywords = {AI-modulated voices, voice forensics, PRAAT analysis, threat detection, voice analysis, speaker identification, voice manipulation.},
        month = {},
        }