On a study of decreasing the processing time in the speech recognition system using the HMM(hidden Markov model) algorithm

The study of isolated-word speech recognition is now progressing and the recognizer have been also reached to the commercialization. Speech recognition is now applied to communication systems in our environment. However, speech recognition performance on large vocabulary is insufficient for commercial use, since there are many problems which are the difficulty of speech database setup on large vocabulary and the increase of processing time. Therefore the various researches for those problems have been progressed. In this paper we proposed an improvement method of processing time on the recognition process. The variation of speech signal may be predicted through short time analysis. Especially, in the case of the voiced speech, the waveform is repeated with the some period. In this paper we discuss the reduction of both processing time for speech database setup and speech recognition time if we use this characteristic of the speech signal.