Designing robust multimodal systems for universal access

Multimodal interfaces are being developed that permit our highly skilled and coordinated communicative behavior to control system interactions in a more transparent and flexible interface experience than ever before. As applications become more complex, a single modality alone does not permit varied users to interact effectively across different tasks and usage environments [11]. However, a flexible multimodal interface offers people the choice to use a combination of modalities, or to switch to a better-suited modality, depending on the specifics of their abilities, the task, and the usage conditions. This paper will begin by summarizing some of the primary advantages of multimodal interfaces. In particular, it will discuss the inherent flexibility of multimodal interfaces, which is a key feature that makes them suitable for universal access and mobile computing. It also will discuss the role of multimodal architectures in improving the robustness and performance stability of recognition-based systems. Data will be reviewed from two recent studies in which a multimodal architecture suppressed errors and stabilized system performance for accented nonnative speakers and during mobile use. The paper will conclude by discussing the implications of this research for designing multimodal interfaces for the elderly, as well as the need for future work in this area.