Abstract: This paper proposes a Voice Activity Detection（VAD） method based on wavelet transform C₀ complexity（WC₀），which improves the traditional C₀ complexity，using fuzzy C means clustering algorithm and Bayesian information criterion algorithm to estimate the thresholds of the WC₀ characteristic，and using dual threshold method for VAD.Experiments on the TIMIT continuous speech database show that at low SNR environments，WC₀ method is superior to C₀ method.Especially in the vehicle noise and vehicle interior noise environments，WC₀ method shows better detection performance.

摘要： 对传统的C₀复杂度语音端点检测方法改进，提出一种基于小波变换的C₀复杂度（WC₀）方法，其特征门限估计采用模糊C均值聚类算法和贝叶斯信息准则算法，并采用双门限法进行语音端点检测。在TIMIT连续语音库上的实验表明，在低信噪比环境下，WC₀法的检测性能明显优于基于传统的C₀复杂度法，特别是在车辆噪声和车内噪声环境下，WC₀法表现出更好的检测性能。