Speech enhancement based on leakage constraints DF-GSC  

基于泄漏约束的DF-GSC语音增强(英文)

作　　者：邹采荣[1] 陈国明[1] 赵力[1] 

机构地区：[1]东南大学信息科学与工程学院

出　　处：《Journal of Southeast University(English Edition)》2007年第4期507-511,共5页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No60472058);the Ph.D.Programs Foundation of Ministry of Educa-tion of China(No20050286001);Program for New Century Excellent Talents in University(NoNCET-04-0483)

摘　　要：In order to improve the performance of general sidelobe canceller （GSC） based speech enhancement, a leakage constraints decision feedback generalized sidelobe canceller（LCDF-GSC） algorithm is proposed. The method adopts DF-GSC against signal mismatch, and introduces a leakage factor in the cost function to deal with the speech leakage problem which is caused by the part of the speech signal in the noise reference signal. Simulation results show that although the signal-to-noise ratio （SNR） of the speech signal through LCDF-GSC is slightly less than that of DF-GSC, the IS measurements show that the distortion of the former is less than that of the latter. MOS （mean opinion score） scores also indicate that the LCDF-GSC algorithm is better than DF- GSC and the Weiner filter algorithm,为了改善广义旁瓣抵消(GSC)语音增强方法的性能,提出了一种带有泄漏约束的判决反馈旁瓣抵消(LCDF-GSC)方法.采用DF-GSC方法以解决GSC对波达方向敏感的问题,在代价函数中引入泄漏因子,以此改善语音失真的问题,而这种问题是由于噪声参考信号中含有语音成份造成的.试验结果表明,尽管经过LCDF-GSC处理后的语音信号信噪比要略低于DF-GSC,IS测度表明这时前者的语音信号失真度要小于后者.MOS分也表明LCDF-GSC方法要优于DF-GSC和单通道Weiner滤波算法.

关 键 词：speech enhancement general sidelobe canceller （GSC） speech leakage 

分 类 号：TN912.35[电子电信—通信与信息系统]