Jun, 2024
MultiTalk: 多语种视频数据集增强跨语言的三维说话头生成
MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset
Kim Sung-Bin, Lee Chae-Yeon, Gihun Son, Oh Hyun-Bin, Janghoon Ju...
TL;DR通过多语种 2D 视频数据集,引入多语种增强模型,利用语言特定的样式嵌入,提高了 3D 说话人模型的多语种性能,并提出了度量多语种环境下的唇同步准确性指标。