About AMP Lab        Projects        Downloads        Publications        People        Links

Group Member

	Todd Stephenson Post Doctoral Fellow Personal Homepage:  http://www.andrew.cmu.edu/user/toddstep/ Email: toddstep@andrew.cmu.edu
	Office: B21 Porter Hall Phone: 412-268-2528 Fax: 412-268-1679	Mailing Address: Department of ECE, Carnegie Mellon University, 5000 Forbes Avenue Pittsburgh, PA 15213-3890

[Research Interests]        [Project]      [Publications] 

• 3-D Face Modeling, Enhancement, and Synthesis 

Build a hi-resolution 3D face model from a single low-resolution (2D) face image.  Using a portable computer (e.g., PDA), synthesize possible changes (facial hair, hair style, expressions, etc.) in the face's appearance.

• Dynamic Bayesian Networks (DBNs)
  

Utilize the flexibility of DBNs in having hidden data and various conditional independencies so as to model additional information more easily than with traditional hidden Markov models (HMMs).

• Robust Speech Recognition
  

Incorporate auxiliary information (energy, rate-of-speech, pitch, articulators) into speech recognition to make it more robust in noisy conditions.

  Top of this page

• Portable 3D Faces for Field Identification of Suspects
  

• Construct a 3D face model based on 2D images or video captured by surveillance cameras.
• Display a 3D face model to render face images at different poses, under various illumination conditions, and with different surroundings so as to ease suspect identification.
• Manipulate the 3D face model to create different facial expressions, to simulate the aging process, to add or remove facial hairs, and to change hairstyles or other decorations.
  

Top of this page

Theses: 

• T. A. Stephenson, Speech Recognition with Auxiliary Information. Ph.D. thesis, Swiss Federal Institute of Technology Lausanne (EPFL), 2003.  Unpublished.  
• T. A. Stephenson, Speech Recognition using Phonetically Featured Syllables. M.Sc. thesis, University of Edinburgh, 1998.  Unpublished.  

• T. A. Stephenson and T. Chen, "Adaptive Markov random fields for example-based super-resolution of faces," EURASIP Journal on Applied Signal Processing 2006, (2006), Article ID 31062, 11 pages.
• T. A. Stephenson, M. Magimai-Doss, and H. Bourlard, "Speech recognition with auxiliary information," IEEE Transactions on Speech and Audio Processing, volume 12, number 3, pages 189-203, May 2004.  

• M. Magimai.-Doss, T. A. Stephenson, S. Ikbal, and H. Bourlard, "Modelling auxiliary features in tandem systems," 8th International Conference on Spoken Language Processing (ICSLP '04), Jeju, Korea, October 2004.  
• M. Magimai.-Doss, T. A. Stephenson, H. Bourlard, and S. Bengio, "Phoneme-grapheme based speech recognition system," 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU '03), pages 94-98, St. Thomas, U.S. Virgin Islands, November 2003.  
• M. Magimai.-Doss, T. A. Stephenson, and H. Bourlard, "Using pitch frequency information in speech recognition," 8th European Conference on Speech Communication and Technology (Eurospeech '03), volume 4, pages 2525-2528, Geneva, Switzerland, September 2003.  
• T. A. Stephenson, M. Magimai-Doss, and H. Bourlard, "Speech recognition of spontaneous, noisy speech using auxiliary information in Bayesian networks," Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-03), volume 1, pages 20-23, Hong Kong, April 2003.  
• T. A. Stephenson, M. Magimai-Doss, and H. Bourlard, "Auxiliary variables in conditional Gaussian mixtures for automatic speech recognition," 7th International Conference on Spoken Language Processing (ICSLP '02), volume 4, pages 2665-2668, Denver, September 2002.  
• T. A. Stephenson, J. Escofet, M. Magimai-Doss, and H. Bourlard, "Dynamic Bayesian network based speech recognition with pitch and energy as auxiliary variables," Neural Networks for Signal Processing XII--Proceedings of the 2002 IEEE Signal Processing Society Workshop (NNSP 2002), pages 637-646, Martigny, Switzerland, September 2002.  
• T. A. Stephenson, M. Magimai-Doss, and H. Bourlard, "Mixed Bayesian networks with auxiliary variables for automatic speech recognition," International Conference on Pattern Recognition (ICPR 2002), volume 4, pages 293-296, Quebec City, PQ, Canada, August 2002.  
• T. A. Stephenson, M. Mathew, and H. Bourlard, "Modeling auxiliary information in Bayesian network based ASR," 7th European Conference on Speech Communication and Technology (Eurospeech '01), volume 4, pages 2765-2768, Aalborg, Denmark, September 2001.  
• T. A. Stephenson, H. Bourlard, S. Bengio, and A. C. Morris, "Automatic speech recognition using dynamic Bayesian networks with both acoustic and articulatory variables," 6th International Conference on Spoken Language Processing (ICSLP '00), volume 2, pages 951-954, Beijing, October 2000.  
• S. King, T. Stephenson, S. Isard, P. Taylor, and A. Strachan, "Speech recognition via phonetically featured syllables," 5th International Conference on Spoken Language Processing (ICSLP '98), volume 3, pages 1031-1034, Sydney, November 1998.  

Top of this page