Voice clones sound realistic but not (yet) hyperrealistic
PLOS One · 24.09.2025 · 20 (9) · e0332692
DOI: 10.1371/journal.pone.0332692 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 24.09.2025. Verfasst von Nadine Lavan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Brain and Behaviour, School of Biological and Behavioural Sciences, Queen Mary University of London, London, United Kingdom. Hauptthemen laut MEDLINE: Voice, Artificial Intelligence. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, British Academy, Leverhulme Trust.
Abstract (Originalsprache)
AI-generated voices are increasingly prevalent in our lives, via virtual assistants, automated customer service, and voice-overs. With increased availability and affordability of AI-generated voices, we need to examine how humans perceive them. Recently, an intriguing effect was reported in AI-generated faces, where such face images were perceived as more human than images of real humans – a “hyperrealism effect.” Here, we tested whether a “hyperrealism effect” also exists for AI-generated voices. We investigated the extent to which AI-generated voices sound real to human listeners, and whether listeners can accurately distinguish between human and AI-generated voices. We also examined perceived social trait characteristics (trustworthiness and dominance) of human and AI-generated voices. We tested these questions using AI-generated voices generated with and without a specific human counterpart (i.e., voice clones, and voices generated from the latent space of a large voice model). We find that voice clones can sound as real as human voices, making it difficult for listeners to distinguish between them. However, we did not observe a hyperrealism effect. Both types of AI-generated voices were evaluated as more dominant than human voices, with some AI-generated voices also being perceived as more trustworthy. These findings raise questions for future research: Can hyperrealistic voices be created with more advanced technology, or is the lack of a hyperrealism effect due to differences between voice and face (image) perception? Our findings also highlight the potential for AI-generated voices to misinform and defraud, alongside opportunities to use realistic AI-generated voices for beneficial purposes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Centre for Brain and Behaviour, School of Biological and Behavioural Sciences, Queen Mary University of London, London, United Kingdom.
- UCL Speech, Hearing and Phonetic Sciences, Division of Psychology and Language Sciences, London, United Kingdom.
ORCID-Profile: Nadine Lavan, Mairi Irvine, Victor Rosi
Förderung
- Wellcome Trust
- British Academy
- Leverhulme Trust
Zitieren
APA
Lavan, N., Irvine, M., Rosi, V., & McGettigan, C. (2025). Voice clones sound realistic but not (yet) hyperrealistic. PLOS One, 20(9), e0332692. https://doi.org/10.1371/journal.pone.0332692
Vancouver
Lavan N, Irvine M, Rosi V, McGettigan C. Voice clones sound realistic but not (yet) hyperrealistic. PLOS One. 2025;20(9):e0332692. doi:10.1371/journal.pone.0332692
BibTeX
@article{Lavan2025,
author = {Lavan, Nadine and Irvine, Mairi and Rosi, Victor and McGettigan, Carolyn},
title = {Voice clones sound realistic but not (yet) hyperrealistic},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {9},
pages = {e0332692},
doi = {10.1371/journal.pone.0332692}
}
EUVIMED