噪声环境下语音多子带端点检测方法

Sub-bands Endpoints Detection of Noisy Speech

为了克服传统端点检测算法在有噪环境下的不足,提出了一种新的语音多子带端点检测算法,它能根据子带背景噪声大小动态设置门限。实验结果表明,所提出的算法较传统的检测方法有更好的检测性能。

In order to overcome the shortcoming of the traditional speech endpoints detection algorithm in noisy environment, a new multiple sub-bands speech endpoints detection algorithm is proposed in this paper, which can dynamically adjust the threshold according to sub-bands background noise. Experimental results show that the proposed method has good detection performance compared with the other baseline algorithms.