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.

人脸老化技术已借助生成对抗网络（Generative Adversarial Networks，GANs）与风格迁移学习方法，将人物外观调整至更年轻或更年长的状态。此类生成网络通过以源内容的学习向量表征作为条件进行约束，得以保留目标人物的身份特征。