%0 Journal Article
%T Blind Separation of Noisy Speech Mixtures Based on Wavelet Transform and Independent Component Analysis<br>基于小波变换和独立分量分析的含噪混叠语音盲分离
%A Zhao Cai-hua
%A Liu Ju
%A Sun Jian-de
%A Yan Hua
%A <br>赵彩华
%A 刘琚
%A 孙建德
%A 闫华
%J 电子与信息学报
%D 2006
%I 
%X A vital issue in speech processing is to extract source speeches from noisy mixtures. A method is presented based on wavelet transform and independent component analysis in this paper. Firstly, de-noise the noisy mixtures with discrete wavelet transform. Secondly, get them separated by independent component analysis. Finally, do the post-processing to the separated signals, then the estimated source speeches are got. Simulation results exhibit a high level of separating performance.
%K Speech separation
%K Wavelet transform
%K Independent Component Analysis(ICA)
%K De-noising<br>语音分离
%K 小波变换
%K 独立分量分析
%K 噪声消除
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=63AC8B613764A3E4&yid=37904DC365DD7266&vid=D3E34374A0D77D7F&iid=9CF7A0430CBB2DFD&sid=CA107AA458C36D25&eid=E826542BD0A89666&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=6&reference_num=11