People are poorly equipped to detect AI-powered voice clones

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Barrington, Sarah, Cooper, Emily A., Farid, Hany
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912302049001472
author Barrington, Sarah
Cooper, Emily A.
Farid, Hany
author_facet Barrington, Sarah
Cooper, Emily A.
Farid, Hany
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03791
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle People are poorly equipped to detect AI-powered voice clones
Barrington, Sarah
Cooper, Emily A.
Farid, Hany
Human-Computer Interaction
Artificial Intelligence
Computers and Society
Sound
Audio and Speech Processing
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.
title People are poorly equipped to detect AI-powered voice clones
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2410.03791