Voice recognizing method and apparatus

摘要

A voice recognizing method apparatus in which an input voice is recognized by obtaining a similar pattern by comparing the input voice and voice standard patterns. Voice standard patterns are stored into a memory. A voice is inputted. Voice duration lengths and distances are calculated by performing matching processes between the input voice and the standard patterns. The distance is corrected in accordance with the voice duration length so that the voice duration length having the best matching result is used as a reference, or such that the distance is small as the voice duration length is long. A recognition result is determined in accordance with the corrected distance. The matching is executed by a word spotting method. The input voice to be matched and the voice standard patterns are expressed by voice characteristic parameters.