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...

Full description

Saved in:
Bibliographic Details
Main Authors: Foo, Say Wei, Dong, Liang
Other Authors: IEEE International Conference on Advanced Learning Technologies (2nd : 2002 : Kazan, Russia)
Format: Conference or Workshop Item
Language:English
Published: 2009
Online Access:https://hdl.handle.net/10356/90829
http://hdl.handle.net/10220/4617
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-90829
record_format dspace
spelling sg-ntu-dr.10356-908292019-12-06T17:54:47Z A supervised two-channel learning method for hidden Markov model and application on lip reading Foo, Say Wei Dong, Liang IEEE International Conference on Advanced Learning Technologies (2nd : 2002 : Kazan, Russia) 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 training sequences, and 2.) a twochannel structure is adopted to maintain the validity of the HMM. This learning method has been applied on a viseme-level lip reading system. The result shows that the performance of the two channel approach is better than that of the maximum likelihood (ML) estimation. Accepted version 2009-05-25T04:19:55Z 2019-12-06T17:54:47Z 2009-05-25T04:19:55Z 2019-12-06T17:54:47Z 2002 2002 Conference Paper Foo, S. W., & Dong, L. (2002). A supervised two-channel learning method for hidden Markov model and application on lip reading. IEEE International Conference on Advanced Learning Technologies. https://hdl.handle.net/10356/90829 http://hdl.handle.net/10220/4617 en © IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. 5 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
description 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 training sequences, and 2.) a twochannel structure is adopted to maintain the validity of the HMM. This learning method has been applied on a viseme-level lip reading system. The result shows that the performance of the two channel approach is better than that of the maximum likelihood (ML) estimation.
author2 IEEE International Conference on Advanced Learning Technologies (2nd : 2002 : Kazan, Russia)
author_facet IEEE International Conference on Advanced Learning Technologies (2nd : 2002 : Kazan, Russia)
Foo, Say Wei
Dong, Liang
format Conference or Workshop Item
author Foo, Say Wei
Dong, Liang
spellingShingle Foo, Say Wei
Dong, Liang
A supervised two-channel learning method for hidden Markov model and application on lip reading
author_sort Foo, Say Wei
title A supervised two-channel learning method for hidden Markov model and application on lip reading
title_short A supervised two-channel learning method for hidden Markov model and application on lip reading
title_full A supervised two-channel learning method for hidden Markov model and application on lip reading
title_fullStr A supervised two-channel learning method for hidden Markov model and application on lip reading
title_full_unstemmed A supervised two-channel learning method for hidden Markov model and application on lip reading
title_sort supervised two-channel learning method for hidden markov model and application on lip reading
publishDate 2009
url https://hdl.handle.net/10356/90829
http://hdl.handle.net/10220/4617
_version_ 1681047593453355008