Abstract. We describe an architecture for building speech-enabled conversational agents, deployed as self-contained Web services, with ability to provide inference processing on ve...
Surface representation is needed for almost all modeling and visualization applications, but unfortunately, 3D data from a passive vision system are often insufficient for a tradi...
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative prede...
This paper presents techniques in clustering the sametopic news stories according to event themes. We model the relationship of stories with textual and visual concepts under the ...
Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interes...