Cross-speaker viseme mapping using hidden Markov models

In this paper, a method of mapping visual speech between different speakers is proposed. This approach adopts Hidden Markov Model (HMM) to model the basic visual speech element – viseme. Some mapping terms are applied to associate the state chains decoded for the visemes produced by different spe...

Full description

Saved in:
Bibliographic Details
Main Authors: Dong, Liang, Foo, Say Wei, Yong, Lian
Other Authors: School of Electrical and Electronic Engineering
Format: Conference or Workshop Item
Language:English
Published: 2009
Subjects:
Online Access:https://hdl.handle.net/10356/91219
http://hdl.handle.net/10220/5953
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-91219
record_format dspace
spelling sg-ntu-dr.10356-912192020-03-07T13:24:46Z Cross-speaker viseme mapping using hidden Markov models Dong, Liang Foo, Say Wei Yong, Lian School of Electrical and Electronic Engineering International Conference on Information, Communications and Signal Processing (4th : 2003 : Singapore) IEEE Pacific Rim Conference on Multimedia (4th : 2003 : Singapore) DRNTU::Engineering::Electrical and electronic engineering::Electronic systems In this paper, a method of mapping visual speech between different speakers is proposed. This approach adopts Hidden Markov Model (HMM) to model the basic visual speech element – viseme. Some mapping terms are applied to associate the state chains decoded for the visemes produced by different speakers. The HMMs configured in this way are trained using the Baum-Welch estimation, and are used to generate new visemes. Experiments are conducted to map the visemes produced by several speakers to a destination speaker. The experimental results show that the proposed approach provides good accuracy and continuity for mapping the visemes. Accepted version 2009-07-31T06:30:55Z 2019-12-06T18:01:49Z 2009-07-31T06:30:55Z 2019-12-06T18:01:49Z 2003 2003 Conference Paper Dong, L., Foo, S. W., & Yong,L. (2003). Cross-speaker viseme mapping using hidden Markov models. Proceedings of the 4th International Conference on Information, Communications and Signal Processing and the 4th IEEE Pacific-Rim Conference on Multimedia (pp. 1384-1388). Vol.3. Singapore: IEEE. https://hdl.handle.net/10356/91219 http://hdl.handle.net/10220/5953 10.1109/ICICS.2003.1292692 en International Conference on Information, Communications and Signal Processing and the IEEE Pacific-Rim Conference Multimedia © 2003 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. http://www.ieee.org/portal/site. 5 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering::Electronic systems
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Electronic systems
Dong, Liang
Foo, Say Wei
Yong, Lian
Cross-speaker viseme mapping using hidden Markov models
description In this paper, a method of mapping visual speech between different speakers is proposed. This approach adopts Hidden Markov Model (HMM) to model the basic visual speech element – viseme. Some mapping terms are applied to associate the state chains decoded for the visemes produced by different speakers. The HMMs configured in this way are trained using the Baum-Welch estimation, and are used to generate new visemes. Experiments are conducted to map the visemes produced by several speakers to a destination speaker. The experimental results show that the proposed approach provides good accuracy and continuity for mapping the visemes.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Dong, Liang
Foo, Say Wei
Yong, Lian
format Conference or Workshop Item
author Dong, Liang
Foo, Say Wei
Yong, Lian
author_sort Dong, Liang
title Cross-speaker viseme mapping using hidden Markov models
title_short Cross-speaker viseme mapping using hidden Markov models
title_full Cross-speaker viseme mapping using hidden Markov models
title_fullStr Cross-speaker viseme mapping using hidden Markov models
title_full_unstemmed Cross-speaker viseme mapping using hidden Markov models
title_sort cross-speaker viseme mapping using hidden markov models
publishDate 2009
url https://hdl.handle.net/10356/91219
http://hdl.handle.net/10220/5953
_version_ 1681048021023850496