Dr. Ed Kaiser is a research scientist working with multimodal integration technology. His main research activity is focused on understanding how combinations of multimodal inputs can support real-time machine learning of new knowledge. The redundancy of speech and handwriting during lectures and meetings presents rich opportunities for machine learning in perceptual environments, which are the current focus of his research work. Ed has an M.S. in Speech Processing from Oregon Health & Science University and a  Ph.D. in Computer Science.

Publications include:

Barthelmess, Paulo, Edward C. Kaiser, Xiao Huang, David McGee, and Philip Cohen. "Collaborative Multimodal Photo Annotation over Digital Paper," Proceedings of the Eighth International Conference on Multimodal Interfaces (ICMI '06), Banff, Canada. 2006, to appear.

Edward C Kaiser, Paulo Barthelmess. "Edge-splitting in a Cumulative Multimodal System, for a No-Wait Temporal Threshold on Information Fusion, Combined with an Under-Specified Display," Proceedings of the International Conference on Spoken Language Processing (Interspeech2006 ICSLP), Pittsburgh, Sept. 17-21, 2006, to appear.

Barthelmess, Paulo, Edward C. Kaiser, Rebecca Lunsford, David McGee, Sharon Oviatt, and Philip Cohen. "Human Centered Collaborative Interaction," First International Workshop on Human-Centered Multimedia (HCM 2006) in Conjunction with ACM Multimedia, Santa Barbara, Oct. 23-27, 2006, to appear.

Barthelmess, Paulo, Edward C. Kaiser, Xiao Huang, David McGee, and Philip Cohen. "Demo: Collaborative Multimodal Photo Annotation over Digital Paper," Proceedings of the Eighth International Conference on Multimodal Interfaces (ICMI '06), Banff, Canada. 2006, to appear.