Auto-Correlation Property of Speech and its Application in Voice Activity Detection

The paper analyzes short term auto-correlation property of speech signal and confirms it through detailed comparing experiment with other kinds of signals. By applying the auto-correlation property of current speech frame and frames nearby, a new feature for voice activity detecting called weighted short-term summation of auto-correlation (WSAC) is formed. It is testified that the new VAD feature can robustly used in environment degraded by noise which has poor correlation, and its performance has little connection with various SNRs, change of noise power etc., in contrast with traditional features commonly used in VAD. Properties of the new feature and principle of robust VAD algorithm based on it are explained in this paper, experiment results and correlative analysis are also given.