Innovative spoken dialogue interfaces are one area in which research developments can contribute to increased efficiency, robustness and safety. An important part of creating performance enhancing systems is to have interfaces that do not in themselves create additional work or cognitive burden. Imagine how much easier it would be to use a computer system that you could simply converse with in the same way you would when delegating to a human assistant or as you would when collaborating with a colleague using speech and other modalities. Especially good payoffs for using spoken interfaces are:

At the heart of the work is the question of understanding and modeling how people communicate, of exploring what representations can facilitate that communication either with other humans or with computer and robotic systems. Our approach is based on empirical study of what people say to each other, what people say to actual systems and what they say to simulations of possible future systems. We believe that one of the benefits of a spoken dialogue interface is that the closer it is to handling the types of conversations that people would have with each other, the more the interface provides a reduction in required training and in cognitive load.
Future NASA missions require these improved methods of human-computer interaction based on spoken natural language dialogues. Astronauts building the International Space Station or on planetary surfaces will need to be able to carry out many tasks without using their hands to interact with computers and robotic systems. Spoken dialogue systems are the natural way to provide this much needed interface to external devices.