@inproceedings{de2442619af24ee28efee784ad0e8754,
title = "Boosted audio-visual HMM for speech reading",
abstract = "We propose a new approach for combining acoustic and visual measurements to aid in recognizing lip shapes of a person speaking. Our method relies on computing the maximum likelihoods of (a) HMM used to model phonemes from the acoustic signal, and (b) HMM used to model visual features motions from video. One significant addition in this work is the dynamic analysis with features selected by AdaBoost, on the basis of their discriminant ability. This form of integration, leading to boosted HMM, permits AdaBoost to find the best features first, and then uses HMM to exploit dynamic information inherent in the signal.",
author = "Pei Yin and Irfan Essa and Rehg, {James M.}",
note = "Funding Information: We would like to thank Prof. Fred Huang for his guidance with some of the acoustic processing parts of this research. Matthew Mullin, Jianxin Wu for their guidance with boosting method. Zhenhao Zhou, Fabien Robert for the helpful discussions and our subjects for volunteering their time. This work is in part funded by the NSF ITR grant #IIS-0205507. Publisher Copyright: {\textcopyright} 2003 IEEE.; 2003 IEEE International Workshop on Analysis and Modeling of Faces and Gestures, AMFG 2003 ; Conference date: 17-10-2003",
year = "2003",
language = "English (US)",
series = "IEEE International Workshop on Analysis and Modeling of Faces and Gestures, AMFG 2003",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "68--73",
booktitle = "IEEE International Workshop on Analysis and Modeling of Faces and Gestures, AMFG 2003",
address = "United States",
}