{"type":"ScholarlyArticle","title":"Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks","authors":[{"name":"Qiuqiang Kong","slug":"qiuqiang-kong","given":"Qiuqiang","family":"Kong","affiliation":"University of Surrey , Guildford , UK"},{"name":"Yong Xu","slug":"yong-xu","given":"Yong","family":"Xu","affiliation":"Tencent AI lab , Bellevue , USA"},{"name":"Philip J. B. Jackson","slug":"philip-j-b-jackson","given":"Philip J. B.","family":"Jackson","affiliation":"University of Surrey , Guildford , UK"},{"name":"Wenwu Wang","slug":"wenwu-wang","given":"Wenwu","family":"Wang","affiliation":"University of Surrey , Guildford , UK"},{"name":"Mark D. Plumbley","slug":"mark-d-plumbley","given":"Mark D.","family":"Plumbley","affiliation":"University of Surrey , Guildford , UK"}],"abstract":"Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture. Single-channel signal separation and deconvolution is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may contain non-stationary noise which is unseen in the training set. We propose a synthesizing-decomposition (S-D) approach to solve the single-channel separation and deconvolution problem. In synthesizing, a generative model for sources is built using a generative adversarial network (GAN). In decomposition, both mixing filters and sources are optimized to minimize the reconstruction error of the mixture. The proposed S-D approach achieves a peak-to-noise-ratio (PSNR) of 18.9 dB and 15.4 dB in image inpainting and completion, outperforming a baseline convolutional neural network PSNR of 15.3 dB and 12.2 dB, respectively and achieves a PSNR of 13.2 dB in source separation together with deconvolution, outperforming a convolutive non-negative matrix factorization (NMF) baseline of 10.1 dB.","doi":"10.24963/ijcai.2019/381","url":"https://ijcai.org/proceedings/2019/381","pdf":"https://ijcai.org/proceedings/2019/0381.pdf","markdown":"https://ijcai.org/proceedings/2019/381.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/381","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":381,"pages":{"first":2747,"last":2753},"keywords":["Machine Learning: Learning Generative Models","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Campisi and Egiazarian, 2017] Patrizio Campisi and Karen Egiazarian. Blind image deconvolution: theory and appli- cations. CRC press, 2017.","title":"Blind image deconvolution: theory and applications","authors":"Patrizio Campisi, Karen Egiazarian","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cichocki et al., 2006] A. Cichocki, R. Zdunek, and S. Amari. New algorithms for non-negative matrix factorization in applications to blind source separation. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2006.","title":"New algorithms for non-negative matrix factorization in applications to blind source separation","authors":"A Cichocki, R Zdunek, S Amari","year":"2006","venue":"IEEE International Conference on Acoustics, Speech and Signal Processing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cichocki et al., 2009] A. Cichocki, R. Zdunek, A. H. Phan, and S. Amari. Nonnegative matrix and tensor factoriza- tions: applications to exploratory multi-way data analysis and blind source separation. John Wiley & Sons, 2009.","title":"Nonnegative matrix and tensor factorizations: applications to exploratory multi-way data analysis and blind source separation","authors":"A Cichocki, R Zdunek, A H Phan, S Amari","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fan et al., 2018] Z. Fan, Y. Lai, and J. Jang. SVSGAN: Singing voice separation via generative adversarial net- work. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.","title":"SVSGAN: Singing voice separation via generative adversarial network","authors":"Z Fan, Y Lai, J Jang","year":"2018","venue":"IEEE International Conference on Acoustics, Speech and Signal Processing","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Goodfellow et al., 2014] I.","title":null,"authors":"Goodfellow","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Advances in Neural Information Processing Systems (NIPS), pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"J Goodfellow, M Pouget-Abadie, B Mirza, D Xu, S Warde-Farley, A Ozair, Y Courville, Bengio","year":"2014","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Grais et al., 2014] E. M. Grais, M. Sen, and H. Erdogan. Deep neural networks for single channel source separa- tion. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 3734- 3738, 2014.","title":"Deep neural networks for single channel source separation","authors":"E M Grais, M Sen, H Erdogan","year":"2014","venue":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ioffe and Szegedy, 2015] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by re- ducing internal covariate shift. In International Confer- ence on Machine Learning (ICML), 2015.","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","authors":"S Ioffe, C Szegedy","year":"2015","venue":"International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jain and Seung, 2009] V. Jain and S. Seung. Natural im- age denoising with convolutional networks. In Advances in Neural Information Processing Systems (NIPS), pages 769-776, 2009.","title":"Natural image denoising with convolutional networks","authors":"V Jain, S Seung","year":"2009","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kingma and Ba, 2015] D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In International Con- ference on Learning Representations (ICLR), 2015.","title":"Adam: A method for stochastic optimization","authors":"D P Kingma, J Ba","year":"2015","venue":"International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kitamura et al., 2013] D. Kitamura, H. Saruwatari, K. Shikano, K. Kondo, and Y. Takahashi. Music signal separation by supervised nonnegative matrix factorization with basis deformation. In International Conference on Digital Signal Processing (DSP), 2013.","title":"Music signal separation by supervised nonnegative matrix factorization with basis deformation","authors":"D Kitamura, H Saruwatari, K Shikano, K Kondo, Y Takahashi","year":"2013","venue":"International Conference on Digital Signal Processing (DSP)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[LeCun et al., 1998] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Y Lecun, L Bottou, Y Bengio, P Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lee and Seung, 1999] D. D. Lee and H. S. Seung. Learning the parts of objects by non-negative matrix factorization. Nature, 1999.","title":"Learning the parts of objects by non-negative matrix factorization","authors":"D D Lee, H S Seung","year":"1999","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Levin et al., 2009] Anat Levin, Yair Weiss, Fredo Durand, and William T Freeman. Understanding and evaluating blind deconvolution algorithms. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.","title":"Understanding and evaluating blind deconvolution algorithms","authors":"Levin","year":"2009","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mijovic et al., 2010] B. Mijovic, M. De Vos, I. Gligorije- vic, J. Taelman, and S. Van Huffel. Source separation from single-channel recordings by combining empirical- mode decomposition and independent component analy- sis. IEEE Transactions on Biomedical Engineering, 2010.","title":"Source separation from single-channel recordings by combining empiricalmode decomposition and independent component analysis","authors":"B Mijovic, M De Vos, I Gligorijevic, J Taelman, S Van Huffel","year":"2010","venue":"IEEE Transactions on Biomedical Engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Radford et al., 2015] A. Radford, L. Metz, and S. Chintala. Unsupervised representation learning with deep convo- lutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.","title":"Unsupervised representation learning with deep convolutional generative adversarial networks","authors":"A Radford, L Metz, S Chintala","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Stoller et al., 2017] D. Stoller, S. Ewert, and S. Dixon. Adversarial semi-supervised audio source separation ap- plied to singing voice extraction. arXiv preprint arXiv:1711.00048, 2017.","title":"Adversarial semi-supervised audio source separation applied to singing voice extraction","authors":"D Stoller, S Ewert, S Dixon","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Subakan and Smaragdis, 2017] Cem Subakan and Paris Smaragdis. Generative adversarial source separation. arXiv preprint arXiv:1710.10779, 2017.","title":"Generative adversarial source separation","authors":"Smaragdis Subakan","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Xie et al., 2012] J. Xie, L. Xu, and E. Chen. Image denois- ing and inpainting with deep neural networks. In Advances in Neural Information Processing Systems (NIPS), pages 341-349, 2012.","title":"Image denoising and inpainting with deep neural networks","authors":"J Xie, L Xu, E Chen","year":"2012","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Xu et al., 2014] L. Xu, J. Ren, C. Liu, and J. Jia. Deep con- volutional neural network for image deconvolution. In Ad- vances in Neural Information Processing Systems (NIPS), pages 1790-1798, 2014.","title":"Deep convolutional neural network for image deconvolution","authors":"L Xu, J Ren, C Liu, J Jia","year":"2014","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yeh et al., 2016] R. Yeh, C. Chen, T. Y. Lim, M. Hasegawa- Johnson, and M. N. Do. Semantic image inpainting with perceptual and contextual losses. arXiv preprint arXiv:1607.07539, 2016.","title":"Semantic image inpainting with perceptual and contextual losses","authors":"R Yeh, C Chen, T Y Lim, M Hasegawa-Johnson, M N Do","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yosinski et al., 2014] J. Yosinski, J. Clune, Y. Bengio, and H. Lipson. How transferable are features in deep neural networks? In Advances in Neural Information Processing Systems (NIPS), pages 3320-3328, 2014.","title":"How transferable are features in deep neural networks","authors":"J Yosinski, J Clune, Y Bengio, H Lipson","year":"2014","venue":"Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhang et al., 2017] K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans- actions on Image Processing, 26(7):3142-3155, 2017.","title":"Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising","authors":"K Zhang, W Zuo, Y Chen, D Meng, L Zhang","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}