{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:19:43Z","timestamp":1761059983772,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319224817"},{"type":"electronic","value":"9783319224824"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-22482-4_30","type":"book-chapter","created":{"date-parts":[[2015,8,14]],"date-time":"2015-08-14T07:06:02Z","timestamp":1439535962000},"page":"259-267","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Audio Source Separation with Discriminative Scattering Networks"],"prefix":"10.1007","author":[{"given":"Pablo","family":"Sprechmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joan","family":"Bruna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yann","family":"LeCun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,8,15]]},"reference":[{"issue":"6755","key":"30_CR1","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"DD Lee","year":"1999","unstructured":"Lee, D.D., Seung, H.S.: Learning parts of objects by non-negative matrix factorization. Nature 401(6755), 788\u2013791 (1999)","journal-title":"Nature"},{"issue":"3","key":"30_CR2","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MSP.2013.2297715","volume":"31","author":"P Smaragdis","year":"2014","unstructured":"Smaragdis, P., Fevotte, C., Mysore, G., Mohammadiha, N., Hoffman, M.: Static and dynamic source separation using nonnegative factorizations: a unified view. IEEE Sig. Process. Mag. 31(3), 66\u201375 (2014)","journal-title":"IEEE Sig. Process. Mag."},{"issue":"4","key":"30_CR3","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1109\/TPAMI.2011.156","volume":"34","author":"J Mairal","year":"2012","unstructured":"Mairal, J., Bach, F., Ponce, J.: Task-driven dictionary learning. IEEE Trans. Pattern Anal. Mach. Intel. 34(4), 791\u2013804 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intel."},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Sprechmann, P., Bronstein, A.M., Sapiro, G.: Supervised non-euclidean sparse NMF via bilevel optimization with applications to speech enhancement. In: HSCMA, pp. 11\u201315. IEEE (2014)","DOI":"10.1109\/HSCMA.2014.6843241"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Weninger, F., Le Roux, J., Hershey, J.R., Watanabe, S.: Discriminative NMF and its application to single-channel source separation. In: Proceedings of ISCA Interspeech (2014)","DOI":"10.21437\/Interspeech.2014-218"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Huang, P.-S., Kim, M., Hasegawa-Johnson, M., Smaragdis, P.: Deep learning for monaural speech separation. In: ICASSP, pp. 1562\u20131566 (2014)","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Sprechmann, P., Bronstein, A., Bronstein, M., Sapiro, G.: Learnable low rank sparse models for speech denoising. In: ICASSP, pp. 136\u2013140 (2013)","DOI":"10.1109\/ICASSP.2013.6637624"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Weninger, F., Le Roux, J., Hershey, J.R., Schuller, B.: Discriminatively trained recurrent neural networks for single-channel speech separation. In: Proceedings IEEE GlobalSIP 2014 Symposium on Machine Learning Applications in Speech Processing (2014)","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"F\u00e9votte, C.: Majorization-minimization algorithm for smooth itakura-saito nonnegative matrix factorization. In: ICASSP, pp. 1980\u20131983. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5946898"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Wilson, K.W., Raj, B., Smaragdis, P., Divakaran, A.: Speech denoising using nonnegative matrix factorization with priors. In: ICASSP, pp. 4029\u20134032 (2008)","DOI":"10.1109\/ICASSP.2008.4518538"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Mysore, G.J., Smaragdis, P.: A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics. In: ICASSP, pp. 17\u201320 (2011)","DOI":"10.1109\/ICASSP.2011.5946317"},{"key":"30_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/978-3-642-28551-6_43","volume-title":"Latent Variable Analysis and Signal Separation","author":"J Han","year":"2012","unstructured":"Han, J., Mysore, G.J., Pardo, B.: Audio imputation using the non-negative hidden markov model. In: Theis, F., Cichocki, A., Yeredor, A., Zibulevsky, M. (eds.) LVA\/ICA 2012. LNCS, vol. 7191, pp. 347\u2013355. Springer, Heidelberg (2012)"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"F\u00e9votte, C., Le Roux, J., Hershey, J.R.: Non-negative dynamical system with application to speech and audio. In: ICASSP (2013)","DOI":"10.1109\/ICASSP.2013.6638240"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Boulanger-Lewandowski, N., Mysore, G.J., Hoffman, M.: Exploiting long-term temporal dependencies in NMF using recurrent neural networks with application to source separation. In: ICASSP, May 2014, pp. 6969\u20136973 (2014)","DOI":"10.1109\/ICASSP.2014.6854951"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Bruna, J., Sprechmann, P., LeCun, Y.: Source separation with scattering non-negative matrix factorization (2014, submitted)","DOI":"10.1109\/ICASSP.2015.7178296"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Mohamed, A., Hinton, G., Penn, G.: Understanding how deep belief networks perform acoustic modelling. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4273\u20134276. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288863"},{"issue":"8","key":"30_CR17","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2012.230","volume":"35","author":"J Bruna","year":"2013","unstructured":"Bruna, J., Mallat, S.: Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intel. 35(8), 1872\u20131886 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intel."},{"key":"30_CR18","unstructured":"And\u00e9n, J., Mallat, S.: Deep scattering spectrum (2013). arXiv preprint arXiv:1304.6763"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Schmidt, M.N., Larsen, J., Hsiao, F.-T.: Wind noise reduction using non-negative sparse coding. In: MLSP, August 2007, pp. 431\u2013436 (2007)","DOI":"10.1109\/MLSP.2007.4414345"},{"issue":"9","key":"30_CR20","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1162\/NECO_a_00168","volume":"23","author":"C F\u00e9votte","year":"2011","unstructured":"F\u00e9votte, C., Idier, J.: Algorithms for nonnegative matrix factorization with the $$\\beta $$-divergence. Neural Comput. 23(9), 2421\u20132456 (2011)","journal-title":"Neural Comput."},{"key":"30_CR21","unstructured":"Mallat, S.: Recursive interferometric representation. In: Proceedings of EUSICO Conference, Denmark (2010)"},{"key":"30_CR22","volume-title":"A Wavelet Tour of Signal Processing","author":"S Mallat","year":"1999","unstructured":"Mallat, S.: A Wavelet Tour of Signal Processing. Academic Press, New York (1999)"},{"key":"30_CR23","unstructured":"Bruna, J., Mallat, S.: Audio texture synthesis with scattering moments (2013). arXiv preprint arXiv:1311.0407"},{"issue":"4","key":"30_CR24","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., F\u00e9votte, C.: Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Proc. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Proc."},{"key":"30_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556"}],"container-title":["Lecture Notes in Computer Science","Latent Variable Analysis and Signal Separation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-22482-4_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T06:23:59Z","timestamp":1676960639000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-22482-4_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319224817","9783319224824"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-22482-4_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"15 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}