Dialogues with a Talking Face for Web-Based Services and Transactions

摘要

In this paper we discuss our research on interactions in a virtual theatre that has been built using VRML and therefore can be accessed through Web pages. In the virtual environment we employ several agents. The virtual theatre allows navigation input through keyboard and mouse, but there is also a navigation agent which listens to typed input and spoken commands. Feedback of the system is given using speech synthesis. We also have an information agent which allows a natural language dialogue with the system where the input is keyboard-driven and the output is both with tables as with template driven natural language generation. In development are several talking faces for the different agents in the virtual world. At this moment an avatar with a cartoon-like talking face driven by a text-to-speech synthesizer can provide users with information about performances in the theatre.