Discriminative Word-Spotting Using Ordered Spectro-Temporal Patch Features
Tony Ezzat, Tomaso Poggio, to appear, SAPA workshop, Interspeech, Brisbane, Australia, 2008(pdf)
Speech Analysis
Localized Spectro-Temporal Cepstral Analysis of Speech
Jake Bouvrie, Tony Ezzat, Tomaso Poggio, ICASSP, Las Vegas, Nevada, 2008(pdf)
Spectro-Temporal Analysis of Speech Using 2-D Gabor Filters
Tony Ezzat, Jake Bouvrie, Tomaso Poggio, Interspeech, Antwerp, Belgium 2007(pdf)
AM-FM Demodulation of Spectrograms using 2-D Max-Gabor Analysis
Tony Ezzat, Jake Bouvrie, Tomaso Poggio, ICASSP, Hawaii, USA, April 2007 (pdf)(demos)
Max-Gabor Analysis and Synthesis of Spectrograms
Tony Ezzat, Jake Bouvrie, Tomaso Poggio, ICSLP, Pittsburgh, PA, USA, September 2006 (ps.gz)(pdf)(demos)
An Incremental Algorithm for Signal Reconstruction from STFT Magnitude
Jake Bouvrie, Tony Ezzat ICSLP, Pittsburgh, PA, USA, September 2006 (pdf)(demos)
Morphing Spectral Envelopes Using Audio Flow
Tony Ezzat, Ethan Meyers, Jim Glass, and Tomaso Poggio, Interspeech/Eurospeech,
Lisbon, Portugal, September 2005 (ps.gz)(pdf)(demos)
Face Animation
Transferable Videorealistic Speech Animation,
Yao-Jen Chang and Tony Ezzat, ACM Siggraph/Eurographics Symposium on Computer Animation,
Los Angeles, CA 2005(ps.gz)(pdf)(AVI demo)(demos)
Perceptual Evaluation of Video-realistic Speech
Gadi Geiger, Tony Ezzat, and Tomaso Poggio, CBCL Paper #224/ AI Memo #2003-003,
Massachusetts Institute of Technology, Cambridge, MA, February 2003(ps.gz)(pdf)
Trainable Videorealistic Speech Animation
Tony Ezzat, Gadi Geiger, and Tomaso Poggio, Proceedings of
ACM SIGGRAPH 2002, San Antonio, Texas, July 2002. [Also appeared as
my Phd Thesis, MIT EECS, June 2002]
(ps.gz)(pdf)(demos)
Visual Speech Synthesis by Morphing Visemes
Tony Ezzat and Tomaso Poggio,
MIT AI Memo No 1658/CBCL Memo No 173. May 1999. [This paper also
appeared as T. Ezzat and T. Poggio. Visual speech synthesis by morphing visemes.
In K. A. Publishers, editor, International Journal of Computer Vision, volume 38,
pages 45--57, 2000.]
(ps.gz)(pdf)(demos)
MikeTalk: A Talking Facial Display Based on Morphing Visemes
Tony Ezzat and Tomaso Poggio,
Proceedings of the Computer Animation Conference Philadelphia, PA, June 1998.
(ps.gz)(pdf)(demos)
Videorealistic Talking Faces: A Morphing Approach, Tony Ezzat and Tomaso Poggio,
Proceedings of the Audiovisual Speech Processing Workshop, Rhodes, Greece, September 1997.
(ps.gz)(pdf)(demos)
Face Tracking
Facial Analysis and Synthesis Using Image-based Models,
Tony Ezzat and Tomaso Poggio,
Proceedings of the Second International Conference on Automatic Face and Gesture Recognition,
Killington, Vermont, October 1996.
(ps.gz)(pdf)(demos)
A longer version of the above paper with more results appeared as:
Facial Analysis and Synthesis Using Image-based Models,
Tony Ezzat and Tomaso Poggio,
Proceedings of the Workshop on the Algorithmic Foundations of Robotics,
Toulouse, France, August 1996.
(ps.gz)(pdf)(demos)
Example-Based Analysis and Synthesis for Images of Human
Faces, Tony Ezzat, MIT EECS Masters Thesis, February 1996.
(ps.gz)(pdf)(demos)
