一种鲁棒自适应阈值的语音端点检测方法  

Robust adaptive threshold speech endpoint detection method

作　　者：张君昌[1] 张丹[1] 崔力[1] 

机构地区：[1]西北工业大学电子信息学院,陕西西安710129

出　　处：《西安电子科技大学学报》2015年第5期115-119,共5页Journal of Xidian University

基　　金：陕西省自然科学基金资助项目(2011JQ8038)

摘　　要：针对基于特征的语音端点检测方法在低信噪比及非平稳噪声下检测性能急剧下降的问题,提出了一种鲁棒自适应阈值的语音端点检测方法.采用表征较长时段语音谱平坦度的长时段语音谱平坦度特征,并融合Burg谱估计,与其他传统语音特征相比,提高了语音与噪声的区分度;能更准确地反映背景噪声特征,克服了固定阈值适应性较差的缺陷,从而更大程度上提高了检测的准确率.仿真结果表明,该方法在低信噪比及非平稳噪声下,检测准确率更高,说明该方法在低信噪比及非平稳噪声环境下鲁棒性更好.Due to the fact that traditional Speech Endpoint Detection methods＇performance degrads greatly in a low signal-to-noise ratio and nonstationary noise,a novel robust adatpive threshold endpoint detection method is proposed.First of all,the LSFM parameter is employed as the distinctive feature and the Burg spectrum estimation is applied to figure out the power spectrum,which can enhance the discriminative ability in classifying speech signals and noise,compared with the traditional speech features.Furthermore,an adaptive threshold based on the Bayes estimation criterion is involved in the final judgment,which overcomes the defect of the fixed threshold in adaptability and improves the detection performance to a greater degree.Simulation results show that compared with the traditional feature-based Speech Endpoint Detection methods,the accuracy of the proposed method has a high accuracy rate,which proves that the new method has a better robust performance in a low SNR and nonstationary noise.

关 键 词：低信噪比 非平稳噪声 语音端点检测 长时段信号谱平坦度 Burg谱估计 

分 类 号：TN702[电子电信—电路与系统]