跳到主要导航 跳到搜索 跳到主要内容

Dynamic visual features based on discriminative speech class projection for visual speech recognition

  • Lei Xie
  • , Xiu Li Cai
  • , Zhong Hua Fu
  • , Rong Chun Zhao
  • Northwestern Polytechnical University Xian

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

This paper presents a dynamic visual feature extraction scheme to capture important lip motion information for visual speech recognition. Discriminative projections based on a-priori chosen speech classes, phonemes and visemes, are applied to the concatenation of pre-extracted static visual features. First- and second-order temporal derivatives are subsequently extracted to further represent the dynamic differences. Experiments on a connected digits task demonstrate that the proposed high discriminative dynamic features, when augmented to the static, yields superior recognition performances. Compared to the commonly used delta and acceleration features, the proposed dynamic feature leads to an 8% absolute improvement in terms of word accuracy for the considered recognition task.

源语言英语
主期刊名2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2004
页687-690
页数4
出版状态已出版 - 2004
活动2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2004 - Hong Kong, China, 香港
期限: 20 10月 2004 → 22 10月 2004

丛书

姓名2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2004

会议

会议2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2004
国家/地区香港
市Hong Kong, China
时期20/10/04 → 22/10/04

学术指纹

探究 'Dynamic visual features based on discriminative speech class projection for visual speech recognition' 的科研主题。它们共同构成独一无二的学术指纹。

引用此