基于层次稀疏DBN的瓶颈特征提取方法  

Bottleneck Feature Extraction Method Based on Hierarchical Deep Sparse Belief Network

作　　者：王一[1,2] 杨俊安[1,2] 刘辉[1,2] 柳林[3] 

机构地区：[1]中国人民解放军电子工程学院,合肥230037 [2]安徽省电子制约技术重点实验室,合肥230037 [3]安徽科大讯飞信息科技股份有限公司,合肥230088

出　　处：《模式识别与人工智能》2015年第2期173-180,共8页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.60872113);安徽省自然科学基金项目(No.1208085MF94;1308085QF99)资助

摘　　要：针对现有语音特征无法有效利用长时段语音和监督性类别信息,及现有瓶颈特征提取方法耗时过长等缺陷,提出基于层次结构稀疏深度可信神经网络的瓶颈特征提取方法.该方法将重叠组套索作为深度可信神经网络目标函数的稀疏正则项使用,从而构建训练速度更快的稀疏深度可信神经网络.然后利用层次结构的网络架构方式,将两个稀疏深度可信神经网络串联后使用,进一步增强瓶颈特征的判决能力.文中将此瓶颈特征应用于音素识别中,实验表明该特征的有效性.To overcome the drawbacks of original speech features that long temporal speeches and the supervised information can not be effectively utilized and the training time cost is high, a bottleneck feature extraction method based on hierarchical deep sparse belief network is presented. The overlapping group lasso is used as the sparse regularization constraint of the objective function of deep belief network to obtain a deep sparse belief network with a higher speed. To make full use of the hierarchical structure, two sparse deep belief networks are connected in series to enhance the discriminant ability of the bottleneck features. The experimental results on phoneme recognition task show that the proposed feature is effective.

关 键 词：音素识别 深度可信神经网络(DBN) 重叠组套索 层次结构 

分 类 号：TN912.34[电子电信—通信与信息系统]