Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

A new manifold representation for visual speech recognition

Yu, Dahai and Ghita, Ovidiu and Sutherland, Alistair and Whelan, Paul F. (2007) A new manifold representation for visual speech recognition. In: CAIP 2007 - 12th International Conference on Computer Analysis of Images and Patterns, 27-29 August 2007, Vienna, Austria. ISBN 978-3-540-74271-5

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


In this paper, we propose a new manifold representation capable of being applied for visual speech recognition. In this regard, the real time input video data is compressed using Principal Component Analysis (PCA) and the low-dimensional points calculated for each frame define the manifolds. Since the number of frames that from the video sequence is dependent on the word complexity, in order to use these manifolds for visual speech classification it is required to re-sample them into a fixed number of keypoints that are used as input for classification. In this paper two classification schemes, namely the k Nearest Neighbour (kNN) algorithm that is used in conjunction with the two-stage PCA and Hidden-Markov-Model (HMM) classifier are evaluated. The classification results for a group of English words indicate that the proposed approach is able to produce accurate classification results.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Uncontrolled Keywords:visual speech recognition; PCA manifolds; spline interpolation; k-Nearest Neighbour; Hidden Markov model;
Subjects:Computer Science > Digital video
Computer Science > Information retrieval
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > Research Institute for Networks and Communications Engineering (RINCE)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in:Computer Analysis of Images and Patterns. Lecture Notes in Computer Science 4673. Springer Berlin / Heidelberg. ISBN 978-3-540-74271-5
Publisher:Springer Berlin / Heidelberg
Official URL:
Copyright Information:The original publication is available at
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:4666
Deposited On:03 Jul 2009 11:52 by DORAS Administrator. Last Modified 03 Jul 2009 11:52

Download statistics

Archive Staff Only: edit this record