Text recognition from silent lip movement video

doi:10.1109/SIPROCESS.2018.8600535

OPT OpenIR > 光学定向与测量技术研究室

	Text recognition from silent lip movement video
	Wei, Youda 1,2; Hu, Xiaodong1
	2019-01-02
会议名称	2018 IEEE 3rd International Conference on Signal and Image Processing, ICSIP 2018
会议录名称	2018 IEEE 3rd International Conference on Signal and Image Processing, ICSIP 2018
页码	168-171
会议日期	2018-07-13
会议地点	Shenzhen, China
出版者	Institute of Electrical and Electronics Engineers Inc.
产权排序	1
摘要	Lip reading, the ability to recognize text information from the movement of a speaker's mouth, is a difficult and challenging task. Recently, the end-to-end model that maps a variable-length sequence of video frames to text performs poorly in real life situation where people unintentionally move the lips instead of speaking. The goal of this work is to improve the performance of lip reading task in real life. The model proposed in this article consists of two networks that are visual to audio feature network and audio feature to text network. Our experiments showed that the model proposed in this article can achieve 92.76% accuracy in lip reading task on the dataset that the unintentional lips movement was added. ? 2018 IEEE.
作者部门	光学定向与测量技术研究室
DOI	10.1109/SIPROCESS.2018.8600535
收录类别	EI
ISBN号	9781538663943
语种	英语
EI入藏号	20190806535377
引用统计
文献类型	会议论文
条目标识符	http://ir.opt.ac.cn/handle/181661/31280
专题	光学定向与测量技术研究室
作者单位	1.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China; 2.University of Chinese Academy of Sciences, Beijing, China
推荐引用方式 GB/T 7714	Wei, Youda,Hu, Xiaodong. Text recognition from silent lip movement video[C]:Institute of Electrical and Electronics Engineers Inc.,2019:168-171.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Text recognition fro（2638KB）	会议论文		限制开放	CC BY-NC-SA	请求全文