TianshunHan/3D-CAVFA
收藏官方服务：
资源简介：
3D-CAVFA数据集是一个多模态的集合，包含同步的音频和面部混合形状系数，这些数据是从20个测试对象中捕获的，总计15小时。其语言内容包括常用的现代汉语词汇和短语，以及来自日常生活的多种句子模式，确保了与现实生活场景的高度相关性。
The 3D-CAVFA dataset is a multimodal collection featuring synchronized audio and facial blendshape coefficients captured from 20 subjects, totaling 15 hours. Its linguistic content encompasses frequently used modern Chinese words and phrases, alongside a variety of sentence patterns drawn from daily life, thereby guaranteeing strong relevance to real-world scenarios.
提供机构：
TianshunHan
