Improved Sparse NMF based Speech Enhancement Method with Deep Neural Network

DOI

10.2991/ifmeita-17.2018.39How to use a DOI?

Keywords

Speech enhancement; Deep neural network; Sparse non-negative matrix factorization.

Abstract

Considering the sparsity characteristic of speech signal in time-frequency domain and the non-linear model ability of deep neural network, an improved sparse non-negative matrix factorization based speech enhancement method is presented in this paper. Deep neural network is employed to learn the sparse encoding coefficients of speech and noise from noisy observation. The estimated clean speech is obtained by applying the wiener filter on the magnitude spectrogram of noisy speech. The experimental results show the superiority of proposed method under stationary and non-stationary conditions.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xia Zou
AU  - Xiongwei Zhang
AU  - Wenhua Shi
AU  - Fupeng Wang
AU  - Jingtao Zhang
AU  - Mingyue Gao
PY  - 2018/02
DA  - 2018/02
TI  - Improved Sparse NMF based Speech Enhancement Method with Deep Neural Network
BT  - Proceedings of the 2nd International Forum on Management, Education and Information Technology Application (IFMEITA 2017)
PB  - Atlantis Press
SP  - 231
EP  - 234
SN  - 2352-5398
UR  - https://doi.org/10.2991/ifmeita-17.2018.39
DO  - 10.2991/ifmeita-17.2018.39
ID  - Zou2018/02
ER  -