This work is dedicated in the memory of Christian Benoit
who was a pioneer in audiovisual speech research.
The authors would like to thank
- Meredith and Dynasty Models
- Osamu Yoshimi, Shinsuke Sakai, Chao Wang, Ji-Wook Kim, and Dong-Juh Kim for help with audio annotation
- Craig Milanesi, Dave Konstine, and Jay Benoit from MIT Video Productions for video magic
- Volker Blanz, Thomas Vetter, Demetri Terzopoulos, Carl Livadas, and Ryan Rifkin for countless comments
- David Beymer, Mike Jones, Vinay Kumar, Steve Lines, Roberto Brunelli and Steve Librande for laying the groundwork.
- Casey Johnson and Mary Pat Fitzgerald for paper magic.
- Marney Smyth for web site comments
- Jenny Shapiro and BMG for help with music rights
This work was partially funded by the
- Association Christian Benoit
- NTT Japan
- Office of Naval Research
- DARPA
- National Science Foundation (Adaptive Man-Machine Interfaces).
Additional support was provided by:
- Central Research Institute of Electric Power Industry
- Eastman Kodak Company
- DaimlerChrysler AG
- Compaq
- Honda R&D Co.
- Komatsu Ltd.
- Toyota Motor Corporation
- The Whitaker Foundation.
Send any comments or questions to Tony Ezzat