A simplified viterbi matching algorithm for word partition in visual speech processing

In this paper, a novel simplified Viterbi matching algorithm for sequence partition is presented. This method connects the states of different HMMs to model the observed sequence. The method is applied to visual speech processing to partition the word into visual speech elements. Experimental result...

Full description

Saved in:
Bibliographic Details
Main Authors: Foo, Say Wei, Yong, Lian, Liang, Dong
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2009
Subjects:
Online Access:https://hdl.handle.net/10356/79871
http://hdl.handle.net/10220/6039
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-79871
record_format dspace
spelling sg-ntu-dr.10356-798712020-03-07T13:24:43Z A simplified viterbi matching algorithm for word partition in visual speech processing Foo, Say Wei Yong, Lian Liang, Dong School of Electrical and Electronic Engineering European Workshop on Image Analysis for Multimedia Interactive Services (4th : 2003 : London) DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems In this paper, a novel simplified Viterbi matching algorithm for sequence partition is presented. This method connects the states of different HMMs to model the observed sequence. The method is applied to visual speech processing to partition the word into visual speech elements. Experimental result shows that good accuracy is achieved with the proposed method. Accepted version 2009-08-11T07:12:27Z 2019-12-06T13:35:47Z 2009-08-11T07:12:27Z 2019-12-06T13:35:47Z 2009 2009 Conference Paper Foo, S. W., Yong, L., & Liang, D. (2009). A simplified viterbi matching algorithm for word partition in visual speech processing. Proceedings of 4th European Workshop on Image Analysis for Multimedia Interactive Services, 355-358. https://hdl.handle.net/10356/79871 http://hdl.handle.net/10220/6039 10.1142/9789812704337_0065 en A simplified viterbi matching algorithm for word partition in visual speech processing © copyright 2009 World Scientific Publishing Co. This conference's website is located at http://eproceedings.worldscinet.com/9789812704337/9789812704337_0065.html. 4 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Foo, Say Wei
Yong, Lian
Liang, Dong
A simplified viterbi matching algorithm for word partition in visual speech processing
description In this paper, a novel simplified Viterbi matching algorithm for sequence partition is presented. This method connects the states of different HMMs to model the observed sequence. The method is applied to visual speech processing to partition the word into visual speech elements. Experimental result shows that good accuracy is achieved with the proposed method.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Foo, Say Wei
Yong, Lian
Liang, Dong
format Conference or Workshop Item
author Foo, Say Wei
Yong, Lian
Liang, Dong
author_sort Foo, Say Wei
title A simplified viterbi matching algorithm for word partition in visual speech processing
title_short A simplified viterbi matching algorithm for word partition in visual speech processing
title_full A simplified viterbi matching algorithm for word partition in visual speech processing
title_fullStr A simplified viterbi matching algorithm for word partition in visual speech processing
title_full_unstemmed A simplified viterbi matching algorithm for word partition in visual speech processing
title_sort simplified viterbi matching algorithm for word partition in visual speech processing
publishDate 2009
url https://hdl.handle.net/10356/79871
http://hdl.handle.net/10220/6039
_version_ 1681046178918039552