@inproceedings{e366a53677474f4992150317128760ce,
title = "Multi-stream articulator model with adaptive reliability measure for audio visual speech recognition",
abstract = "We propose a multi-stream articulator model (MSAM) for audio visual speech recognition (AVSR). This model extends the articulator modelling technique recently used in audio-only speech recognition to audio-visual domain. A multiple-stream structure with a shared articulator layer is used in the model to mimic the speech production process. We also present an adaptive reliability measure (ARM) based on two local dispersion indicators, integrating audio and visual streams with local, temporal reliability. Experiments on the AVCONDIG database shows that our model can achieve comparable recognition performance with the multi-stream hidden Markov model (MSHMM) under various noisy conditions. With the help of the ARM, our model even performs the best at some testing SNRs.",
author = "Lei Xie and Liu, \{Zhi Qiang\}",
year = "2006",
doi = "10.1007/11739685\_104",
language = "英语",
isbn = "3540335846",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "994--1004",
booktitle = "Advances in Machine Learning and Cybernetics - 4th International Conference, ICMLC 2005, Revised Selected Papers",
note = "4th International Conference on Machine Learning and Cybernetics, ICMLC 2005 ; Conference date: 18-08-2005 Through 21-08-2005",
}