Research on Single-channel Blind Deconvolution Algorithm for Multi-source Signals

LIU Ting; YIN Tiantian; GONG Zhenying; GUO Yina

doi:10.11999/JEIT200933

Volume 44 Issue 1

Jan. 2022

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2022 > 44(1): 230-236

LIU Ting, YIN Tiantian, GONG Zhenying, GUO Yina. Research on Single-channel Blind Deconvolution Algorithm for Multi-source Signals[J]. Journal of Electronics & Information Technology, 2022, 44(1): 230-236. doi: 10.11999/JEIT200933

Citation:

LIU Ting, YIN Tiantian, GONG Zhenying, GUO Yina. Research on Single-channel Blind Deconvolution Algorithm for Multi-source Signals[J]. Journal of Electronics & Information Technology, 2022, 44(1): 230-236. doi: 10.11999/JEIT200933

Citation:

PDF( 1466 KB)

Research on Single-channel Blind Deconvolution Algorithm for Multi-source Signals

doi: 10.11999/JEIT200933

Electronics and Communication Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China

Funds: The National Natural Science Foundation of China (61301250), China Scholarship Council[2020]1417, The Key Research and Development Project of Shanxi Province (201803D421035), The Natural Science Foundation for Young Scientists of Shanxi Province (201901D211313), Research, Teaching and Research Funding Project of Shanxi Province for Returned Overseas Students (HGKY2019080)

Received Date: 2020-11-02
Accepted Date: 2021-11-05
Rev Recd Date: 2021-10-02

Available Online: 2021-11-09

Publish Date: 2022-01-10

Abstract

Abstract

Traditional single-channel blind deconvolution method has the limitation that it can only separate two sources from a mixture. Considering this problem, a Single-Channel Blind Deconvolution algorithm based on optimized deep Convolutional generative adversarial networks (SCBDC) is proposed to separate and deconvolve more than three independent sources and mixing matrix only from a mixture. The experiments are carried on the occlusion Chinese character image datasets, four sources are randomly selected to be mixed with mixing matrix. Peak Signal to Noise Ratio (PSNR) and signal correlation index are combined to evaluate the separation effect. The result shows that the multiple sources can be effectively separated and deconvolved.
- Blind source seperation,
- Single-channel blind deconvolution,
- Multi-source separation,
- Generative adversarial networks,
- Mixing matrix estimation

FullText(HTML)

References(18)

References

[1]	付卫红, 周新彪, 农斌. 单通道盲源分离的研究现状与展望[J]. 北京邮电大学学报, 2017, 40(5): 1–11. doi: 10.13190/j.jbupt.2017-001 FU Weihong, ZHOU Xinbiao, and NONG Bin. The research of SCBSS technology: Survey and prospect[J]. Journal of Beijing University of Posts and Telecommunications, 2017, 40(5): 1–11. doi: 10.13190/j.jbupt.2017-001
[2]	LEE D D and SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755): 788–791. doi: 10.1038/44565
[3]	KITAMURA D, SARUWATARI H, SHIKANO K, et al. Music signal separation by supervised nonnegative matrix factorization with basis deformation[C]. Proceedings of the 18th International Conference on Digital Signal Processing, Fira, Greece, 2013: 1–6. doi: 10.1109/ICDSP.2013.6622812.
[4]	赵志强, 颜学龙. 基于EMD和ICA的单通道语音盲源分离算法[J]. 电子科技, 2012, 25(7): 66–68,75. doi: 10.3969/j.issn.1007-7820.2012.07.020 ZHAO Zhiqiang and YAN Xuelong. Algorithm for EMD and ICA-based single-channel voice blind source separation[J]. Electronic Science and Technology, 2012, 25(7): 66–68,75. doi: 10.3969/j.issn.1007-7820.2012.07.020
[5]	SEGARS W P, TSUI B M W, CAI Jing, et al. Application of the 4-D XCAT Phantoms in Biomedical Imaging and Beyond[J]. IEEE Transactions on Medical Imaging, 2018, 37(3): 680–692. doi: 10.1109/TMI.2017.2738448
[6]	KRISHNA P K M and RAMASWAMY K. Single channel speech separation based on empirical mode decomposition and Hilbert transform[J]. IET Signal Processing, 2017, 11(5): 579–586. doi: 10.1049/iet-spr.2016.0450
[7]	贾花萍. 盲去卷积算法在图像恢复中的应用研究[J]. 信息技术, 2011(5): 38–39. doi: 10.3969/j.issn.1009-2552.2011.05.013 JIA Huaping. Blind deconvolution algorithm in application of image restoration[J]. Information Technology, 2011(5): 38–39. doi: 10.3969/j.issn.1009-2552.2011.05.013
[8]	ANCUTI C O, ANCUTI C, DE VLEESCHOUWER C, et al. Color balance and fusion for underwater image enhancement[J]. IEEE Transactions on Image Processing, 2018, 27(1): 379–393. doi: 10.1109/TIP.2017.2759252
[9]	SATO Y. A method of self-recovering equalization for multilevel amplitude-modulation systems[J]. IEEE Transactions on Communications, 1975, 23(6): 679–682. doi: 10.1109/TCOM.1975.1092854
[10]	GODARD D. Self-recovering equalization and carrier tracking in two-dimensional data communication systems[J]. IEEE Transactions on Communications, 1980, 28(11): 1867–1875. doi: 10.1109/TCOM.1980.1094608
[11]	YELLIN D and WEINSTEIN E. Criteria for multichannel signal separation[J]. IEEE Transactions on Signal Processing, 1994, 42(8): 2158–2168. doi: 10.1109/78.301850
[12]	ZHANG Kai, ZUO Wangmeng, CHEN Yunjin, et al. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142–3155. doi: 10.1109/TIP.2017.2662206
[13]	GRAIS E M, ROMA G, SIMPSON A J R, et al. Two-stage single-channel audio source separation using deep neural networks[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017, 25(9): 1773–1783. doi: 10.1109/TASLP.2017.2716443
[14]	郑昌艳, 张雄伟, 曹铁勇, 等. 一种基于LSTM-RNN的喉振传声器语音盲增强算法[J]. 数据采集与处理, 2019, 34(4): 615–624. doi: 10.16337/j.1004-9037.2019.04.005 ZHENG Changyan, ZHANG Xiongwei, CAO Tieyong, et al. Blind enhancement algorithm for throat microphone speech based on LSTM re-current neural networks[J]. Data Collection &Processing, 2019, 34(4): 615–624. doi: 10.16337/j.1004-9037.2019.04.005
[15]	王恬, 仇春春, 俞婧, 等. 基于改进SAE网络的自然图像分类[J]. 信息技术, 2016(8): 1–4,8. doi: 10.13274/j.cnki.hdzj.2016.08.001 WANG Tian, QIU Chunchun, YU Jing, et al. Natural image classification with improved SAE network[J]. Information Technology, 2016(8): 1–4,8. doi: 10.13274/j.cnki.hdzj.2016.08.001
[16]	SUBAKAN Y C and SMARAGDIS P. Generative adversarial source separation[C]. Proceedings of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, Canada, 2018: 26–30. doi: 10.1109/ICASSP.2018.8461671.
[17]	KONG Qiuqiang, XU Yong, JACKSON P J B, et al. Single-channel signal separation and deconvolution with generative adversarial networks[C]. Proceedings of the 28th International Joint Conference on Artificial, Macao, China, 2019: 2747–2753. doi: 10.24963/ijcai.2019/381.
[18]	CICHOCKI A, ZDUNEK R, PHAN A H, et al. Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation[M]. Chichester: John Wiley, 2009: 132–138, 197.