Dr. Iain Matthews

Systems scientist in Robotics Institute

• Email: iainm@cs.cmu.edu
• Lab: Smith Hall 101
  (412) 268-3127
• Office: Smith Hall 215
  (412) 268-5594

I obtained my degree in electronic engineering (1994) and PhD (1998) on computer lipreading and audio-visual speech recognition at the University of East Anglia, Norwich, UK. I currently have a systems scientist position in the Robotics Institute at Carnegie Mellon University. A PDF version of my CV is available for those who need to know more.

My official Robotics page has more CMU related information.

Current Demos

Flexible Appearance Models for Face Tracking

See the offical robotics project page for more information.

	Mpeg tracking movie (1.0M). Top left: Orignal image. Top right: Tracking result. Bottom right: Model reconstruction. Bottom left: Overlayed reconstruction.
	Mpeg tracking movie (1.0M). Example of fitting under varying rotation and scale.

Projects

Robotics Institute projects are listed on my official page.

Other Projects

• Audio-visual speech recognition. In collaboration with IBM Research.
• Audio-visual speech synthesis (aka talking head). In collaboration with the University of East Anglia.

Publications

All Robotics Institute publications are available on my official page.

Other Publications

• Towards Video Realistic Synthetic Visual Speech. B. Theobald, J. A. Bangham, I. Matthews and G. Cawley. Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2002. (Accepted)

• Extraction of Visual Features for Lipreading. I. Matthews, T. F. Cootes, J. A. Bangham, S. Cox, R. Harvey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(2):198-213, February 2002.

• Visual Speech Synthesis Using Statistical Models of Shape and Appearance. B. Theobald, J. A. Bangham, I. Matthews and G. Cawley. Proc. Auditory-Visual Speech Processing (AVSP), Scheelsminde, 2001. (582k ps.gz)

• Large-Vocabulary Audio-Visual Speech Recognition: A Summary of the John Hopkins Summer 2000 Workshop. C. Neti, G. Potaminos, J. Luettin, I. Matthews, H. Glotin and D. Vergyri. Workshop on Multimedia Signal Processing (MMSP), Cannes, 2001. (141k pdf)

• A Comparison of Model and Transform-Based Visual Features for Audio-Visual LVCSR. I. Matthews, G. Potamianos, C. Neti and J. Luettin. Proc. International Conference on Multimedia and Expo (ICME), Tokyo, 2001. (477k pdf)

• Audio-Visual Speech Recognition. C. Neti, G. Potamianos, J. Luettin, I. Matthews, H. Glotin, D. Vergyri, J. Sison, A. Mashari and J. Zhou. Technical Report, Workshop 2000, CLSP, Johns Hopkins University, July-August 2000. (2.1M pdf)

• Features for Audio-Visual Speech Recognition. I. Matthews. PhD thesis, School of Information Systems, University of East Anglia, Norwich, UK, 1998. (4.2M ps.gz)

• Lipreading from shape shading and scale. I. Matthews, J. A. Bangham, R. Harvey and S. Cox. Proc. Auditory-Visual Speech Processing (AVSP), pp 73-78. Terrigal, 1998. (170k ps.gz)

• A comparison of active shape models and scale decomposition based features for visual speech recognition. I. Matthews, J. A. Bangham, R. Harvey and S. Cox. Proc. European Conference on Computer Vision (ECCV), pp 514-528. Freiburg, 1998. (872k ps.gz)

• Combining noise compensation with visual information in speech recognition. S. Cox, I. Matthews and J. A. Bangham. Proc. ESCA Workshop on Audio-Visual Speech Processing (AVSP),  pp 53-56. Rhodes, 1997. (32k ps.gz)

• Lipreading from scale space measurements. R. Harvey, I. Matthews, J. A. Bangham and S. Cox. Proc. Computer Vision and Pattern Recognition (CVPR), pp 582-587. Puerto Rico, 1997. (473k ps.gz)

• Scale based features for audio-visual speech recognition. I. Matthews, J. A. Bangham and S. Cox. IEE Colloquium on Integrated Audio-Visual Processing for Recognition, Synthesis and Communication, pp 8/1-8/7. London, 1996. (427k ps.gz)

Last updated 22/7/2002, Iain Matthews (iainm@cs.cmu.edu).