A boosted multi-HMM classifier for recognition of visual speech elements
A boosted multi-HMM classifier for recognition of visual speech elements
复制标题
用于识别视觉语音元素的增强型多 HMM 分类器
DOI：
10.1109/icassp.2003.1202350
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Liang Dong
中科院分区：
文献类型：
--
作者：
S. Foo;Liang Dong
提出了一种新的基于多隐马尔可夫模型的提升分类器。复合障碍物经过特殊训练，以突出某些组的训练样本，并应用自适应增强技术。实验进行了识别英语中的基本视觉语音元素使用建议的提升分类。比较使用所提出的分类器获得的结果和使用传统的单个HMM分类器获得的结果，可以说所提出的系统在准确性和鲁棒性方面明显更好。
A novel boosted classifier using multiple hidden Markov models (HMMs) is reported. The composite HMMs are specially trained to highlight certain group of training samples with the application of adaptive boosting technique. Experiments were carried out to identify the basic visual speech elements in English using the proposed boosted classifier. Comparing the results obtained using the proposed classifier and those obtained using the traditional single HMM classifier, it may be said that the proposed system is significantly better in terms of accuracy and robustness.