Detection of AI-Generated (Cloned) Voices Using Audio Forensics: A Review

DOI

10.2991/978-94-6239-610-4_22How to use a DOI?

Keywords

Artificial Intelligence; Audio; Voice cloning; Audio Forensics; AI-generated Voices; Forensic tools; Forensic Voice Analysis; Deepfake Audio

Abstract

Artificial intelligence is a domain which is constantly evolving in various fields. The recent advances in AI have given rise to voice cloning technologies which produce voices that sound exactly like human speech. These are highly realistic and common man cannot easily distinguish between the generated(cloned) voice and a genuine voice. This technology has useful applications but can be dangerously misused in criminal activities like fraud, impersonation and generating fake audio evidence. This review paper focuses on the detection of AI-generated (cloned) voices using audio forensic tools and also addresses the challenges that the forensic investigators face while detecting fake voice and a genuine voice sample. The paper also understands the forensic tools and techniques being used currently such as audio forensic methods like acoustic analysis and spectrographic analysis and identifies the gaps and limitations and addresses the need for more robust and improved forensic tools. Additionally, it discusses the upcoming machine learning oriented detection methods which are more efficient for detecting AI generated audio like deepfake audio. This paper also includes a comparative study of the traditional forensic methods and the emerging methods. Furthermore, this review focuses on the other implications of cloned voices for criminal investigations, legal and judiciary systems with respect to admissibility and reliability in the courtroom. The aim of this paper is to understand how these AI generated voices are detected and addressing the need for better and upgraded tools to combat the challenges faced by the forensic investigators.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Hasmita Kaur
PY  - 2026
DA  - 2026/05/05
TI  - Detection of AI-Generated (Cloned) Voices Using Audio Forensics: A Review
BT  - Proceedings of the First International Conference on Advances in Forensics and Cyber Technologies (ICFACT 2025)
PB  - Atlantis Press
SP  - 223
EP  - 232
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-610-4_22
DO  - 10.2991/978-94-6239-610-4_22
ID  - Kaur2026
ER  -