Context Adaptive Interaction with an Automatically Created Spoken Interface for Intelligent Environments

In this paper we present the interpretation and generation processes of a spoken dialogue interface for intelligent environments. The interface is automatically created for each specific environment and the interpretation and generation vary depending on the environment and its context. These processes rely on a dialogue tree structure. Several modules process the tree structure and the environment context information to produce specific dialogues for the current environment state. Dialogues are provided with clarification, error recovering, anaphora resolution and other capabilities. The interface is implemented in a real intelligent environment laboratory.