Audio-guided self-supervised learning for disentangled visual speech representations  

作　　者：Dalu FENG Shuang YANG Shiguang SHAN Xilin CHEN 

机构地区：[1]Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China [2]University of Chinese Academy of Sciences,Beijing 100049,China

出　　处：《Frontiers of Computer Science》2024年第6期277-279,共3页计算机科学前沿（英文版）

基　　金：the National Natural Science Foundation of China(Grant Nos.62276247,62076250)。

摘　　要：1 Introduction.Learning visual speech representations from talking face videos is an important problem for several speech-related tasks,such as lip reading,talking face generation,and audiovisual speech separation[1,2].The key difficulty lies in tackling speech-irrelevant factors presented in the videos,such as lighting,resolution,viewpoints,and head motion.

关 键 词：SUCH DIS VISUAL 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN912.3[自动化与计算机技术—计算机科学与技术]