While the technologies now exist to build voice and touch natural language editors, the question arises as to what performance they may be able to deliver.

Specifically, one can ask which allows users to solve problems with spoken English a) how might a natural language processor perform commands, has been constructed. The system utilizes a in conjunction with such input devices, and commercially available discrete speech recognizer which requires that each word be followed by approximately a 300 b) how habitable would the resulting voice-interactive millisecond pause. In a test of the system, subjects were able systems be for real users?