Abstract: A sound processor (12) calculates first through third parameters according to an LPC cepstrum, a primary delta cepstrum and a secondary delta cepstrum. The first parameter catches a static characteristic, the second parameter catches a dynamic characteristic with time, and the third parameter catches a locally dynamic characteristic with time. A word dictionary (14) stores first through third parameters for a standard pattern. Hence, a DP matching unit (16) recognizes a voice based on a distance between an input voice of the three parameters and the standard pattern.