研究发现语音"克隆"实为风格迁移，而非忠实复制

View PDF HTML (experimental)

Abstract:Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity preservation is important, such as completing a recording, dubbing in a new language, or preserving the voices of individuals with speech loss. However, in our work, we find that despite the term, voice cloning does not faithfully ''clone'' an individual's voice. Instead, we find that widely-used voice cloning models systematically apply style transfer to source voices. As rated by human annotators, cloned voices are perceived as more authoritative, warm, customer-service-like, and human-like compared to their sources. Human annotators also report greater trust in cloned voices than source voices, and a greater willingness to disclose sensitive personal information to them. Our work furthermore shows that voice cloning leads to homogenization of speaker characteristics, as measured by reduced variance in accent, speaking rate, and the audio embedding space. Together, our results highlight a new set of limitations and risks of voice cloning technology and their potential impact on human behavior.

Comments:	NeurIPS 2026
Subjects:	Sound (cs.SD); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
Cite as:	arXiv:2605.16578 [cs.SD]
	(or arXiv:2605.16578v4 [cs.SD] for this version)
	https://doi.org/10.48550/arXiv.2605.16578 arXiv-issued DOI via DataCite

Submission history

From: Kaitlyn Zhou [view email]
[v1] Fri, 15 May 2026 19:32:28 UTC (3,515 KB)
[v2] Wed, 20 May 2026 16:52:07 UTC (3,515 KB)
[v3] Tue, 26 May 2026 19:32:15 UTC (3,515 KB)
[v4] Tue, 6 Oct 2026 01:15:52 UTC (3,518 KB)