基于长时信息的自适应话音激活检测  

Adaptive Voice Activity Detection Based on Long-Term Information

作　　者：杨绪魁 屈丹[1] 张文林[1] 闫红刚[1] YANG Xu-kui;QU Dan;ZHANG Wen-lin;YAN Hong-gang(PLA Information Engineering University,Zhengzhou,Henan 450001,China)

机构地区：[1]解放军信息工程大学,河南郑州450001

出　　处：《电子学报》2018年第4期878-885,共8页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61673395;No.61403415);河南省自然科学基金(No.162300410331)

摘　　要：语音信号的长时信息应用于话音激活检测中表现优越.利用三种听觉滤波器组,对语音信号进行非线性的谱分解,本文提出了六种基于听觉滤波器组的长时信息,并提出了基于长时信息的自适应话音激活检测算法.该算法无需训练数据,根据多种长时信息,直接在待测信号中挑选出类别明确的信号,然后利用这些信号训练分类模型,对待测信号按帧进行语音-非语音分类.在TIMIT语音库和NOISEX-92噪声库上的实验表明,该算法在极低信噪比环境下,仍表现出更高的准确性和更强的稳健性.同时,在线实验表明,算法在实时处理中仍能取得优异的性能.The long-term information of speech signals shows excellent performances in the applications of voice activity detection.Six types of long-term information based on auditory filter banks are proposed through the non-linear spectral decomposition with three different auditory filters.Further,an adaptive voice activity detection algorithm based on these types of long-term information is proposed.Without additional training data,this algorithm use the data selecting from the test signals according to long-term information to train a speech/non-speech classifier,and classifies the current test signals using the speech/non-speech classifier frame by frame.Experiments on TIMIT dataset and NOISEX-92 dataset show that the algorithm improves the performance of VAD with higher accuracy and stronger robustness in low SNR noisy environments.The online experiments show that it can also obtain a good performance in real-time processing conditions.

关 键 词：话音激活检测 长时信息 听觉滤波器 自适应 

分 类 号：TN912.34[电子电信—通信与信息系统]