一种基于听觉掩蔽模型的语音增强算法  

A speech enhancement algorithm based on masking properties of human auditory system

作　　者：蔡汉添[1] 袁波涛[1] 

机构地区：[1]华南理工大学电子与通信工程系,广东广州510640

出　　处：《通信学报》2002年第8期93-98,共6页Journal on Communications

基　　金：国家自然科学基金资助项目(69896240)

摘　　要：本文提出一种基于听觉掩蔽模型的语音增强算法。该算法对应用于语音编码中的听觉掩蔽模型进行了适当的修正,动态地确定每一帧语音信号各个关键频率段的听觉掩蔽阈值,有选择性地进行谱减。计算机仿真表明所提算法优于基本谱减法,不仅信噪比有较大的提高而且有效地减少了主观听觉的失真和残留音乐噪声。An approach to speech enhancement based on masking properties of human auditory system is presented. In this approach, the masking model of human auditory system used in speech coding is modified, the masking thresholds of the key frequency segments of each speech frame are determined dynamically, and the selective spectral subtraction is performed. The experiment results show that the proposed algorithm is superior to the general spectral subtraction methods, not only in the SNR improvement, but also in the reduction of audible distortion and music residual noise.

关 键 词：语音增强 谱减算法 听觉掩蔽模型 语音处理 

分 类 号：TN912.35[电子电信—通信与信息系统]