@inproceedings{e9b709b61adb48cbab1138fe2e40bc39,
title = "Adaptive stream reliability modeling based on local dispersion measures for audio visual speech recognition",
abstract = "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.",
keywords = "Audio visual speech recognition, Dispersion, Lipreading, MCE-GPD, Stream exponents",
author = "Lei Xie and Zhao, {Rong Chun} and Liu, {Zhi Qiang}",
year = "2005",
language = "英语",
isbn = "078039092X",
series = "2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005",
pages = "4852--4857",
booktitle = "2005 International Conference on Machine Learning and Cybernetics, ICMLC 2005",
note = "International Conference on Machine Learning and Cybernetics, ICMLC 2005 ; Conference date: 18-08-2005 Through 21-08-2005",
}