Intelligibility enhancement for noisy whispered speech using asymmetric cost function  

作　　者：ZHOU Jian ZHENG Wenming WANG Qingyun ZHAO Li 

机构地区：[1]Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education,Anhui University [2]Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education,Southeast University [3]Key Laboratory of Child Development and Learning Science of Ministry of Education,Southeast University

出　　处：《Chinese Journal of Acoustics》2014年第3期312-322,共11页声学学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(61301295,61273266,61231002);the Natural Science Foundation of Anhui Province(1308085QF100,1408085MF113);the Doctoral Fund of Anhui University

摘　　要：We proposed two whispered speech enhancement methods based on asymmetric cost functions in this paper to deal with the amplification and attenuation distortions of whispered speech distinctively.The modified Itakura-Saito（MIS）distance function provides more penalties to speech amplification distortion,whereas the Kullback-Leibler（KL）divergence function gives more penalties to speech attenuation distortion.The experimental results show that the MIS function based method achieves significant improvement of intelligibility in contrast to the conventional speech enhancement algorithms when the signal-to-noise ratio（SNR）falls below-6 dB,whereas the KL function based one achieves the similar result as the minimum mean square error（MMSE）speech enhancement method.The results show that the effects of the amplification and attenuation distortions on the intelligibility of the enhanced whisper are different,where larger attenuation distortion may result in better intelligibility of speech with low SNR.However,the attenuation distortion has small effects on intelligibility of speech with high SNR.We proposed two whispered speech enhancement methods based on asymmetric cost functions in this paper to deal with the amplification and attenuation distortions of whispered speech distinctively.The modified Itakura-Saito（MIS）distance function provides more penalties to speech amplification distortion,whereas the Kullback-Leibler（KL）divergence function gives more penalties to speech attenuation distortion.The experimental results show that the MIS function based method achieves significant improvement of intelligibility in contrast to the conventional speech enhancement algorithms when the signal-to-noise ratio（SNR）falls below-6 dB,whereas the KL function based one achieves the similar result as the minimum mean square error（MMSE）speech enhancement method.The results show that the effects of the amplification and attenuation distortions on the intelligibility of the enhanced whisper are different,where larger attenuation distortion may result in better intelligibility of speech with low SNR.However,the attenuation distortion has small effects on intelligibility of speech with high SNR.

关 键 词：SNR MIS MMSE 

分 类 号：TN912.3[电子电信—通信与信息系统]