基于最小统计量和掩蔽效应的单通道语音增强  

Single channel speech enhancement based on masking properties and minimum statistics

作　　者：江小平[1] 姚天任[1] 傅华[1] 

机构地区：[1]华中科技大学电子与信息工程系,湖北武汉430074

出　　处：《通信学报》2003年第6期23-31,共9页Journal on Communications

摘　　要：利用人耳感知的掩蔽特性,并结合含噪语音能量的最小统计量估计,提出了一种低信噪比下的单通道语音增强算法。该算法对原始语音在Bark频带能量的最小统计量进行估计,从而准确估计含噪语音信噪比,再从感知的角度,在时域和Bark频域上合理调整增强系数,以实现语音增强的目的。实验表明,该增强算法能够在减小语音失真的同时,很好地抑制背景噪声和残余音乐噪声。The paper presents a single channel speech enhancement method of noisy speech signals at very low signal-to-noise ratios, which is based on masking properties of the human auditory system and power spectral density estimation of non-stationary noise. It allows for an automatic adaptation in time and frequency of the parametric enhancement system, and finds the best tradeoff between noise reduction, the speech distortion, and the level of musical residual noise based on a criterion correlated with perception. The results show that the enhanced method leads to a significant reduction of background noise and the unnatural structure of the residual noise.

关 键 词：语音增强 听觉掩蔽 最小统计量 信噪比估计 

分 类 号：TN912[电子电信—通信与信息系统]