YEFERENCE PATTERN TRAINING SYSTEM AND SPEECH RECOGNITION SYSTEM USING THE SAME

A training unit selector takes out and compares phoneme data about recognition units stored in a recognition word dictionary and a training word dictionary, and selects a recognition unit from the recognition unit training words stored in the training word dictionary, the selected recognition unit resembling each selected recognition unit in a subject recognition word stored in the recognition word dictionary in phoneme context, the selected recognition unit being sent to a recognition unit reference pattern generator. The recognition unit reference pattern generator utilizes a recognition unit, which is best in accord in phoneme context among training data stored in a training data memory, concerning a recognition unit selected by the training unit selector.