People are poorly equipped to detect AI-powered voice clones
Human-Computer Interaction
2025-04-02 v2 Artificial Intelligence
Computers and Society
Sound
Audio and Speech Processing
Abstract
As generative artificial intelligence (AI) continues its ballistic trajectory, everything from text to audio, image, and video generation continues to improve at mimicking human-generated content. Through a series of perceptual studies, we report on the realism of AI-generated voices in terms of identity matching and naturalness. We find human participants cannot consistently identify recordings of AI-generated voices. Specifically, participants perceived the identity of an AI-voice to be the same as its real counterpart approximately 80% of the time, and correctly identified a voice as AI generated only about 60% of the time.
Keywords
Cite
@article{arxiv.2410.03791,
title = {People are poorly equipped to detect AI-powered voice clones},
author = {Sarah Barrington and Emily A. Cooper and Hany Farid},
journal= {arXiv preprint arXiv:2410.03791},
year = {2025}
}