A supervised two-channel learning method for hidden Markov model and application on lip reading
In this paper, a novel two-channel learning method for hidden Markov model (HMM) is proposed. This method is specially designed to train HMMs for fine recognition from similar observations. The prominent features of this method are 1.) the criterion function is based on the difference between trai...
Saved in:
Main Authors: | Foo, Say Wei, Dong, Liang |
---|---|
其他作者: | IEEE International Conference on Advanced Learning Technologies (2nd : 2002 : Kazan, Russia) |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2009
|
在線閱讀: | https://hdl.handle.net/10356/90829 http://hdl.handle.net/10220/4617 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
A two-channel training algorithm for hidden markov model and its application to lip reading
由: Dong, L., et al.
出版: (2014) -
A two-channel training algorithm for hidden Markov model to identify visual speech elements
由: Foo, Say Wei, et al.
出版: (2009) -
Cross-speaker viseme mapping using hidden Markov models
由: Dong, Liang, et al.
出版: (2009) -
A two-channel training algorithm for hidden Markov model to identify visual speech elements
由: Foo, S.W., et al.
出版: (2014) -
Recognition of visual speech elements using adaptively boosted hidden Markov models
由: Foo, Say Wei, et al.
出版: (2009)