Text recognition from silent lip movement video
文献类型：会议论文
| 作者 | Wei, Youda1,2; Hu, Xiaodong1
|
| 出版日期 | 2019-01-02 |
| 会议日期 | 2018-07-13 |
| 会议地点 | Shenzhen, China |
| DOI | 10.1109/SIPROCESS.2018.8600535 |
| 页码 | 168-171 |
| 英文摘要 | 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. |
| 产权排序 | 1 |
| 会议录 | 2018 IEEE 3rd International Conference on Signal and Image Processing, ICSIP 2018
 |
| 会议录出版者 | Institute of Electrical and Electronics Engineers Inc. |
| 语种 | 英语 |
| ISBN号 | 9781538663943 |
| 源URL | [http://ir.opt.ac.cn/handle/181661/31280]  |
| 专题 | 西安光学精密机械研究所_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]. 见:. Shenzhen, China. 2018-07-13. |
入库方式： OAI收割
来源：西安光学精密机械研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。