Abstract: A speech recognition LSI system comprises a speech segment detector for detecting a speech segment from a speech segment detected, a reference pattern memory for storing reference patterns, and a speech recognition section for comparing the speech segment detected by the detector with the reference patterns stored in the reference pattern memory and selecting the reference pattern most similar to that of the speech segment. The system further comprises a recording/reproduction device for recording the speech signal and for reproducing only the speech segment the speech segment detector has detected, so that an operator can hear the speech segment.