听觉选择性注意的认知神经机制与显著性计算模型

Cognitive Neural Mechanisms and Saliency Computational Model of Auditory Selective Attention

根据听觉认知神经信息处理的结构和功能,借鉴图像处理原理实现显著性计算方法,提出了一种基于选择性注意的认知神经机制的听觉显著性计算模型。该模型兼容了自上而下和自下而上两种听觉注意机制,可很好地模拟人类的听觉注意系统。在仿真和自然音频实验中,本模型在选择性注意的显著性提取、背景音抑制等方面都取得了令人满意的结果。

According to structure and function of auditory cognitive neural information processing, a new auditory sali- ency computing model based on mechanisms of selective attention cognitive neural was proposed in this paper, and refer- ring to principle of image processing, algorithms of auditory saliency were presented. This model simulates both the bot- tom-up and top-down human auditory attention mechanism. In selective attention saliency extraction and background noise restrain, the model has achieved satisfactory results in simulation and natural audio experiments.