Cooperative Spoken Language Understanding for Robust Speech Translation

This paper argues that the time is now right to field practical and robust Spoken Language Understanding (SLU) systems. It argues that, at the present state of the art, robustness can best be achieved through user cooperation and compromise with the system. If this insight guides design, several sorts of reliable SLU systems can be deployed over the next few years. Further, SLU systems can be arranged on a scale, in terms of the degree of cooperation or compromise they require from users. In general, the broader the intended linguistic or topical coverage of a system, the more user cooperation or compromise it will presently require. The authors focus on Spoken Language Translation as a specific example application.