DNN-Based Speech Enhancement via Integrating NMF and CASA - 文章详情页

作者：

Yan, Bofang (Yan, Bofang.) | Bao, Changchun (Bao, Changchun.) (学者：鲍长春) | Bai, Zhigang (Bai, Zhigang.)

收录：

EI Scopus

摘要：

In　this　paper,　we　come　up　with　a　novel　speech　enhancement　method,　which　integrates　nonnegative　matrix　factorization　(NMF)　and　computational　auditory　scene　analysis　(CASA)　using　deep　neural　network　(DNN).　Firstly,　we　can　obtain　the　basis　matrices　of　speech　and　noise　respectively　via　NMF　and　get　the　ideal　ratio　mask　(IRM)　that　is　based　on　CASA　by　using　deep　neural　network.　Then,　a　linear　minimum　mean　square　error　(LMMSE)　filter　in　fast　Fourier　transform　(FFT)　domain　is　constructed　and　transformed　to　the　Gammatone　domain.　Finally,　an　integrated　Wiener-like　filter　is　obtained　by　combining　the　filter　of　NMF　with　the　mask　of　CASA.　By　comparing　with　NMF　and　CASA　methods,　the　experiments　present　the　superiority　of　the　proposed　method.　©　2018　IEEE.

关键词：

Deep neural networks Factorization Fast Fourier transforms Image processing Matrix algebra Mean square error Neural networks Patient rehabilitation Signal receivers Speech enhancement

作者机构：

[ 1 ] [Yan, Bofang]Faculty of Information Technology, Beijing University of Technology, Speech and Audio Signal Processing Laboratory, Beijing, China
[ 2 ] [Bao, Changchun]Faculty of Information Technology, Beijing University of Technology, Speech and Audio Signal Processing Laboratory, Beijing, China
[ 3 ] [Bai, Zhigang]Faculty of Information Technology, Beijing University of Technology, Speech and Audio Signal Processing Laboratory, Beijing, China

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至