USING NATURAL-LANGUAGE CONVENTIONS IN THE USER-INTERFACE DESIGN OF AUTOMATIC SPEECH RECOGNITION SYSTEMS

Four experiments were performed to examine how natural language conven tions might be used to improve the user interface for systems using au tomatic speech recognition (ASR). Two new technological developments o ffered us this opportunity: word spotting permits recognition of key w ords embedded in extraneous speech; barge in permits the user to speak to the system while it plays instructional prompts. Our goal was to t ake advantage of natural language conventions to design an optimal pro mpting arrangement that would accommodate both novice and expert users . The conversational conventions we focused on included people's readi ness to speak in response to a direct question and during an appropria tely timed conversational pause. We studied these conventions in the c ontext of an automated operator service. Our results indicated that a prompt-arranged as a leading question, followed by a brief pause and t hen a list of key words-met our goals for both the initial prompt and, if ASR failed, a subsequent reprompt. This approach resulted in fast, accurate responding, a user interface that received high user accepta nce ratings, and an interface that was usable by both novice and exper t users.