METHOD AND SYSTEM FOR ADAPTIVE AUTOMATIC DISCRETE UTTERANCE RECOGNITION

摘要

Adaptive training of a system for discrete utterance recognition during continuous speech permits single prototype utterances to be adapted to the needs of the talker, during operation, without tedious multiple recitation for training of prototypes. Initial training of the recognition system is by a single utterance (or simulation) of a prototype vocabulary. Operation proceeds, so long as utterances are recognized, until an unrecognized utterance is detected. The system then prompts a choice of prototype vocabulary keyword candidates, which the talker may then choose and utter. The system calculates three recognition distance values as follows: D1-unrecognized utterance vs. prototype vocabulary keyboard candidate D2-prototype vs. prototype vocabulary keyword candidate D3-prototype vs. unrecognized utterance. The system reviews the recognition distance values, and from this review determines whether to retry (when D1