Voice Aging with Audio-Visual Style Transfer

Face aging techniques have used generative adversarial networks (GANs) and style transfer learning to transform one’s appearance to look younger/older. Identity is maintained by conditioning these generative networks on a learned vector representation of the source content.

Data and Resources

Cite this as

Justin Wilson, Sunyeong Park, Seunghye J. Wilson, Ming C. Lin (2024). Dataset: Voice Aging with Audio-Visual Style Transfer. https://doi.org/10.57702/6gllkvzy

DOI retrieved: December 17, 2024

Additional Info

Field Value
Created December 17, 2024
Last update December 17, 2024
Defined In https://doi.org/10.48550/arXiv.2110.02411
Author Justin Wilson
More Authors
Sunyeong Park
Seunghye J. Wilson
Ming C. Lin
Homepage https://arxiv.org/abs/1905.08233