Among the environment of speech recognition and control

the non-speech signal(noise) was very easy to confuse with speech signal

apart of noise could be mistaken for speech result inthe deteriorate of system. To solve this problem

this article based on the theory of speaker recognition

a method with vector quantization is presented to confirm the type of audio signal

so that to distinguish the nonpeech signal and eliminate it later

adwance the system’s work efficiency. This article has designed a simulation...