Adaptive stream reliability modeling based on local dispersion measures for audio visual speech recognition

Lei Xie, Rong Chun Zhao, Zhi Qiang Liu

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

This paper proposes an adaptive stream reliability modeling technique for audio visual speech recognition (AVSR). As recognition conditions vary locally, we present two local measures - frame and window dispersions to depict the temporal discriminative powers and noise levels of both audio and visual streams. The dispersions are subsequently mapped to stream exponents according to the minimum classification error (MCE) criterion. Experiments on a connected-digits task show that our method consistently outperforms the popular Discriminative Training (DT) and Grid Search (GS) methods at various signal noise ratios (SNRs), improving for example word accuracy rate (WAR) from 94.7% to 96.4% at 28dB SNR.

源语言英语
主期刊名2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005
4852-4857
页数6
出版状态已出版 - 2005
活动International Conference on Machine Learning and Cybernetics, ICMLC 2005 - Guangzhou, 中国
期限: 18 8月 200521 8月 2005

出版系列

姓名2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005

会议

会议International Conference on Machine Learning and Cybernetics, ICMLC 2005
国家/地区中国
Guangzhou
时期18/08/0521/08/05

指纹

探究 'Adaptive stream reliability modeling based on local dispersion measures for audio visual speech recognition' 的科研主题。它们共同构成独一无二的指纹。

引用此