一种基于马可夫过程统计模型的语音激活检测方法

A Voice Activity Detection Method Based on Markov Process Model

根据语音的特点 ,以一阶马可夫过程统计模型对语音进行建模 ,并在此基础上对语音的激活检测进行了性能分析。在方案的实现过程中 ,采用了多种平滑因子 ,进一步改进了语音判决的正确性。与通常所用的检测方法相比 。

In term of the voice characters, a voice activity detection(VAD)method based on a first-order Markov process is proposed in this paper and its performance is evaluated. The developed VAD employs kinds of smoothing factors so as to alleviate the detection errors at the offset and onset regions of voice. Objective test results show that the proposed scheme is useful to improve consideraby the performance of the VAD.