联合贝叶斯估计与深度神经网络的语音增强方法  

Joint Bayesian Estimation and Deep Neural Network Based Speech Enhancement Method

作　　者：黄张翼 周翊[1] 舒晓峰 刘宏清[1] HUANG Zhang-yi;ZHOU Yi;SHU Xiao-feng;LIU Hong-qing(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学通信与信息工程学院,重庆400065

出　　处：《小型微型计算机系统》2019年第1期40-44,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61501072)资助;重庆市科委自然科学基金项目(cstc2015jcyjA40027)资助

摘　　要：目前,深度学习的研究方法已经成为了语音增强算法的新趋势,而输入的特征是影响增强效果的关键因素.实验表明,输入增强过的语音特征相对原始特征能更好地提升神经网络的语音增强效果.因此,本文首先提出一种改进的Chi分布下基于听觉感知广义加权的贝叶斯估计器,接着将改进的贝叶斯估计器作为深度神经网络的输入特征提取器,进而得到一种联合深度神经网络与Chi分布下基于听觉感知广义加权的贝叶斯估计器预处理的新型网络结构.实验仿真证明,提出的联合算法较传统语音增强算法与基于深度神经网络的语音增强算法在各个噪声环境下,各种性能指标均有了明显的提升.Recently,deep learning based methods have become a newtrend for speech enhancement research,and the input features play an important role in these methods. The experimental results reveal that the enhanced speech features can benefit the speech enhancement effects of neural network,showing superior performance than the conventional features. So firstly,in this paper,a generalized weighted Bayesian estimator with Chi prior pre-processing is extracted. Then,the improved Bayesian estimator is used as the input feature extractor of the deep neural network,a newnetwork structure based on the deep neural network with a generalized weighted Bayesian estimator with Chi prior pre-processing is obtained. Evaluation results showthat a significant improvement is achieved by the proposed method compared to the other algorithms.

关 键 词：语音增强 贝叶斯估计 深度神经网络 特征提取 

分 类 号：TN912[电子电信—通信与信息系统]