Natural interaction with a virtual guide in a virtual environment: A multimodal dialogue system

摘要: This paper describes the Virtual Guide, a multimodal dialogue system represented by an embodied conversational agent that can help users to find their way in virtual environment, while adapting its affective linguistic style of user. We discuss modular architecture system, and describe entire loop from input analysis output generation. also how Guide detects level politeness user’s utterances real-time during aligns own language user, using different strategies. Finally we report on our first user tests, some potential extensions improve system.