新的听觉注意显著图计算模型研究  

Research on a novel saliency map computational model of auditory attention

作　　者：王雪君[1] 夏秀渝[1] 张欣[1] 何培宇[1] 

机构地区：[1]四川大学电子信息学院,成都610064

出　　处：《信号处理》2013年第9期1142-1147,共6页Journal of Signal Processing

基　　金：国家自然科学基金(61071159)

摘　　要：外源性听觉注意计算模型的一个关键问题是如何计算声学信号的听觉显著图,因此,本文提出了一种有效的自底而上听觉显著图计算模型。该模型首先通过听觉外周计算模型处理得到信号每个频率通道的听觉神经响应,并对各通道分帧求短时能量得到听觉图谱,然后以听觉流的时间特性为基础,采用高斯滤波器组对各通道能量谱进行不同尺度的时域滤波,再利用中心-周边差算子计算各频率通道的听觉显著度,最后将各通道听觉显著度线性合并得到声学信号的听觉显著图。本文对不同声学信号、信噪比进行实验研究,仿真结果及分析表明该听觉显著图计算模型比现有模型能更准确地计算声学信号的显著度,突出信号突变时刻的显著性,对低信噪比信号也有较好的适用性。A key problem of the computational model of exogenous auditory attention is how to calculate the saliency map of acoustic signal, in order to detect the saliency of speech signals, an effective bottom-up auditory saliency map computa- tional model is proposed in this paper. To get this model, the auditory nerve response of each frequency channel which pro- cessed by the peripheral auditory system was obtained firstly, and divided them into sub-frames to calculate short-term ener- gy, then, basing on the characteristics of auditory stream, energy spectrum of each channel was time-domain filtered in dif- ferent scales through Gaussian filter groups. Afterwards auditory saliency of each frequency channel was computed by using center-surround differences operator, and the auditory saliency map was achieved by linear combination of each frequency channel saliency finally. The effectiveness of the proposed model was validated via the simulation experiments of different a- coustic signals and SNR. Comparing with the traditional model, the simulation results and analyses indicated that the pro- posed model could calculate the saliency map of acoustic signal more accurately and highlight the saliency of signal mutation moments, also had fine applicability to low SNR signals.

关 键 词：听觉选择性注意 听觉显著图 显著性 外源性注意 

分 类 号：TN912.3[电子电信—通信与信息系统]