2 datasets found

Groups: Multimodal Learning

Filter Results
  • 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...
  • VoxCeleb

    Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature...