基于人耳掩蔽效应的电子耳蜗语音增强方法  

Speech Enhancement Method in Electronic Cochlear Implant Based on Human Auditory Masking Properties

作　　者：黄雅婷[1] 陶智[1] 顾济华[1] 赵鹤鸣[2] 严冬明[1] 

机构地区：[1]苏州大学物理科学与技术学院,苏州215006 [2]苏州大学电子信息学院,苏州215006

出　　处：《计算机工程》2008年第10期280-282,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(60572076);江苏省高校自然科学研究计划基金资助项目(05JKB510113);苏州大学学生科研基金资助项目

摘　　要：提出一种符合人耳听觉感知的语音增强方法,使电子耳蜗能在噪声环境下获得准确的语音信息。利用Bark子波变换实现电子耳蜗中的语音处理,结合人耳听觉系统特性实现语音增强。使用根据人耳听觉掩蔽效应提出的自适应减参数。实验结果表明该算法在低信噪比情况下,信噪比可提高30 dB左右,更好地抑制了残留噪声和背景噪声,合成的语音具有较好清晰度和可懂度。To acquire accurate speech information in cochlear implant under noise enviroments, a speech enhancement in cochlear implant based on human auditory masking properties is proposed. Bark wavelet transform is used to realize speech in electronic cochlear implant and to realize speech enhancement combined with human ear＇s auditory system. Subtract paraineter is got based on the masking properties of human auditory and self-adaptive.The result shows that the SNR output can be improved by 30 dB even if the SNR input is low and can reduce the residual noise and backgrand noise more effectively. The enhanced speech is more clear and intelligible.

关 键 词：电子耳蜗 语音增强 掩蔽效应 Bark子波 

分 类 号：TN912.35[电子电信—通信与信息系统]