Voice "Cloning" is Style Transfer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911722474831872 |
|---|---|
| author | Zhou, Kaitlyn Bianchi, Federico Bartelds, Martijn Pot, Anna Kwon, Yongchan Zou, James |
| author_facet | Zhou, Kaitlyn Bianchi, Federico Bartelds, Martijn Pot, Anna Kwon, Yongchan Zou, James |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16578 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Voice "Cloning" is Style Transfer Zhou, Kaitlyn Bianchi, Federico Bartelds, Martijn Pot, Anna Kwon, Yongchan Zou, James Sound Artificial Intelligence Human-Computer Interaction Machine Learning 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. |
| title | Voice "Cloning" is Style Transfer |
| topic | Sound Artificial Intelligence Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2605.16578 |