A Shared, Modular Architecture for Developing Virtual Humans
Abstract
Our research is focused on understanding the relationship between individual capabilities, how they strengthen each other within larger systems and which sets of minimum and desired permutations can be defined for different types of systems and domains. This research is often conducted within the context of a common, modular framework that contains a mix of research and commercial technologies to offer full coverage of subareas including speech recognition, audio-visual sensing, natural language processing, dialogue management, nonverbal behavior generation and realization, text-to-speech and rendering.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2014
- Accession Number
- AD1157727
Entities
People
- Ari Shapiro
- Arno Hartholt
- David R Traum
- Jonathan Gratch
- Louis-phillipe Morency
- Stacy C. Marsella
Organizations
- Northeastern University
- University of Southern California