基于改进的Kalman滤波的语音增强算法

被引:4
作者
余华 [1 ,2 ]
陈国明 [2 ]
赵力 [2 ]
邹采荣 [2 ]
机构
[1] 南京信息职业技术学院
[2] 东南大学信息科学与工程学院
关键词
语音增强; 卡尔曼滤波; 有色噪声;
D O I
暂无
中图分类号
TN912.35 [语音增强];
学科分类号
0711 ;
摘要
传统的kalman滤波方法在推导过程中假定观测噪声为白噪声。通常对于有色噪声需要用白噪声激励的方法予以模拟,并且需要以牺牲运算量作为代价。本文提出了一种改进的基于kalman滤波的语音增强算法,可以处理白噪声和有色噪声情况,不需要增加计算量,仿真结果表明了该算法对有色噪声的语音增强性能要优于基于传统kalman滤波方法。
引用
收藏
页码:763 / 767
页数:5
相关论文
共 10 条
[1]  
A generalized subspace approach for enhancing speech corrupted by colored noise. Y. Hu,P. C. Loizou. IEEE Transactions on Speech and Audio Processing . 2003
[2]  
Kalman-filtering speechenhancement method based on a voiced-unvoiced speech model. Zenton Goh,Kah-Chye Tan,Tan B T G. IEEE Trans.on Speech and Audio Proceeding . 1999
[3]  
"Spectral Subtraction Based on Minimum Statistics,". R. Martin. Proc. EUSPICO-94 . 1994
[4]  
Speech enhancement using a masking threshold constrained Kalman filter and its heuristic implementations. N.Ma,M.bouchard,R.A.Goubran. IEEE Transactions on audio,speech,language processing . 2006
[5]  
Time-Domain Approach Using Multiple Kalman Filters and EM Algorithm to Speech Enhance- ment with Nonstationary Noise. Yong L K,Jung Souhwan. IEEE Trans.Speech and Audio Processing . 2000
[6]  
Subband Kalman filtering for speech enhancement. W.R. Wu,P.C. Chen. IEEE Trans. Circuits and Systems-II . 1998
[7]  
A single microphone Kalman filter-based noise canceller. Gabrea M,Grivel E,Najim M. IEEE Signal Processing Letters . 1999
[8]  
Filtering of Colored Noise for Speech Enhancement and Coding. Gibson J D,Koo B,Gray S D. IEEE Transactions on Signal Processing . 1991
[9]  
A speech enhancement method based on Kalman filtering. PALIWAL K K,,BASU A. Proceedings of IEEE In-ternational Conference on Acoustics,Speech,and Signal Processing . 1987
[10]  
Codebook constrained Wiener filtering for speech enhancement. T. V. Sreenivas and P. Kimapure. IEEE Transactions on Speech and Audio Processing . 1996