Symmetric Multimodal Interaction in a Dynamic Dialogue

Two important themes in current work on interfaces are multimodal interaction and the use of dialogue. Human multimodal dialogues are symmetric, i.e., both participants communicate multimodally. We describe a proof of concept system that supports symmetric multimodal communication for speech and sketching in the domain of simple mechanical device design. We discuss three major aspects of the communication: multimodal input processing, multimodal output generation, and creating a dynamic dialogue. While previous systems have had some of these capabilities individually, their combination appears to be unique. We provide examples from our system that illustrate a variety of user inputs and system outputs. Author Keywords multimodal, dynamic dialogue, sketch recognition, sketch generation, speech