{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T03:32:08Z","timestamp":1769916728728,"version":"3.49.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T00:00:00Z","timestamp":1578441600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T00:00:00Z","timestamp":1578441600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s00034-019-01338-0","type":"journal-article","created":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T09:02:42Z","timestamp":1578474162000},"page":"3652-3681","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Novel Singing Voice Separation Method Based on a Learnable Decomposition Technique"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8138-1014","authenticated-orcid":false,"given":"Samira","family":"Mavaddati","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,1,8]]},"reference":[{"key":"1338_CR1","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","volume":"54","author":"M Aharon","year":"2006","unstructured":"M. Aharon, M. Elad, A. Bruckstein, K-SVD: an algorithm for designing over-complete dictionaries for sparse representation. IEEE Trans. Signal Process. 54, 4311\u20134322 (2006)","journal-title":"IEEE Trans. Signal Process."},{"key":"1338_CR2","doi-asserted-by":"publisher","first-page":"2055","DOI":"10.1109\/TSP.2013.2245663","volume":"61","author":"D Barchiesi","year":"2013","unstructured":"D. Barchiesi, M.D. Plumbley, Learning incoherent dictionaries for sparse approximation using iterative projections and rotations. IEEE Trans. Signal Process. 61, 2055\u20132065 (2013)","journal-title":"IEEE Trans. Signal Process."},{"key":"1338_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9","volume-title":"Springer Handbook of Speech Processing","author":"J Benesty","year":"2008","unstructured":"J. Benesty, Springer Handbook of Speech Processing (Springer, Berlin, 2008)"},{"key":"1338_CR4","unstructured":"N. Boulanger, G. Mysore, M. Hoffman, Exploiting long-term temporal dependencies in NMF using recurrent neural networks with application to source separation, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014), pp. 7019\u20137023"},{"key":"1338_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1970392.1970395","volume":"58","author":"EJ Candes","year":"2011","unstructured":"E.J. Candes, L. Xiaodong, Y. Ma, J. Wright, Robust principal component analysis? J. ACM 58, 1\u201339 (2011)","journal-title":"J. ACM"},{"key":"1338_CR6","unstructured":"P. Chandna, M. Miron, J. Janer, E. Gomez, Monoaural audio source separation using deep convolutional neural networks, in International Conference on Latent Variable Analysis and Signal Separation (2017), pp. 258\u2013266"},{"key":"1338_CR7","unstructured":"G. Chen, C. Xiong, J.J. Corso, Dictionary transfer for image denoising via domain adaptation, in Proceedings of IEEE International Conference on Image Processing (2012), pp. 1189\u20131192"},{"key":"1338_CR8","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"J. Demsar, Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"1338_CR9","doi-asserted-by":"publisher","first-page":"2845","DOI":"10.1109\/18.959265","volume":"47","author":"DL Donoho","year":"2001","unstructured":"D.L. Donoho, X. Huo, Uncertainty principles and ideal atomic decomposition. IEEE Trans. Inf. Theory 47, 2845\u20132862 (2001)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"1338_CR10","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1109\/TASL.2010.2041114","volume":"18","author":"JL Durrieu","year":"2010","unstructured":"J.L. Durrieu, G. Richard, B. David, C. Fevotte, Source\/filter model for unsupervised main melody extraction from polyphonic audio signals. IEEE Trans. Audio Speech Lang. Process. 18, 564\u2013575 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1338_CR11","doi-asserted-by":"crossref","unstructured":"Z.C. Fan, Y.L. Lai, J.S.R. Jang, SVSGAN: singing voice separation via generative adversarial network, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018)","DOI":"10.1109\/ICASSP.2018.8462091"},{"key":"1338_CR12","unstructured":"H. Fujihara, M. Goto, A music information retrieval system based on singing voice timbre, in ISMIR (2007), pp. 467\u2013470"},{"key":"1338_CR13","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.1109\/JSTSP.2011.2159577","volume":"5","author":"H Fujihara","year":"2011","unstructured":"H. Fujihara, M. Goto, J. Ogata, H.G. Okuno, Lyric synchronizer: automatic synchronization system between musical audio signals and lyrics. J. Sel. Top. Signal Process. 5, 1252\u20131261 (2011)","journal-title":"J. Sel. Top. Signal Process."},{"key":"1338_CR14","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1109\/TASSP.1976.1162849","volume":"24","author":"A Gray","year":"1976","unstructured":"A. Gray, J. Markel, Distance measures for speech processing. IEEE Trans. Acoust. Speech Signal Process. 24, 380\u2013391 (1976)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"1338_CR15","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1109\/TASL.2009.2026503","volume":"18","author":"CL Hsu","year":"2010","unstructured":"C.L. Hsu, J.S.R. Jang, On the improvement of singing voice separation for monaural recordings using the MIR-1\u00a0K dataset. IEEE Trans. Audio Speech Lang. Process. 18, 310\u2013319 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1338_CR16","unstructured":"P.S. Huang, S.D. Chen, P. Smaragdis, M. Hasegawa, Singing voice separation from monaural recordings using robust principal component analysis, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2012), pp. 57\u201360"},{"key":"1338_CR17","unstructured":"P.S. Huang, M. Kim, M. Johnson, P. Smaragdis, Singing-voice separation from monaural recordings using deep recurrent neural networks, in International Society for Music Information Retrieval Conference (2014)"},{"key":"1338_CR18","first-page":"2084","volume":"24","author":"Y Ikemiya","year":"2016","unstructured":"Y. Ikemiya, K. Itoyama, K. Yoshii, Singing voice separation and vocal F0 estimation based on mutual combination of robust principal component analysis and subharmonic summation. J. IEEE\/ACM TASLP 24, 2084\u20132095 (2016)","journal-title":"J. IEEE\/ACM TASLP"},{"key":"1338_CR19","unstructured":"A. Jansson, E.J. Humphrey, N. Montecchio, R. Bittner, A. Kumar, T. Weyde, Singing voice separation with deep U-Net convolutional networks, in Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR) (2017), pp. 745\u2013751"},{"key":"1338_CR20","unstructured":"M. Lagrange, A. Ozerov, E. Vincent, Robust singer identification in polyphonic music using melody enhancement and uncertainty-based learning, in Proceedings of the ISMIR (2012), pp. 595\u2013560"},{"key":"1338_CR21","first-page":"801","volume":"19","author":"H Lee","year":"2007","unstructured":"H. Lee, A. Battle, R. Raina, A.Y. Ng, Efficient sparse coding algorithms, advances in neural information processing systems. Adv. Neural. Inf. Process. Syst. 19, 801\u2013808 (2007)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1338_CR22","unstructured":"Y. Li, D.L. Wang, Singing voice separation from monaural recordings, in Proceedings of the International Conference of Music Information Retrieval (2006), pp. 176\u2013179"},{"key":"1338_CR23","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836","volume-title":"Speech Enhancement: Theory and Practice","author":"PC Loizou","year":"2007","unstructured":"P.C. Loizou, Speech Enhancement: Theory and Practice (Taylor and Francis, London, 2007)"},{"key":"1338_CR24","unstructured":"Y. Luo, Z. Chen, D.P.W. Ellis, Deep clustering for singing voice separation, in MIREX, task of Singing Voice Separation (2016), pp. 1\u20132"},{"key":"1338_CR25","unstructured":"Y. Luo, Z. Chen, J.R. Hershey, J.L. Roux, N. Mesgarani, Deep clustering and conventional networks for music separation: Stronger together, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2017), pp. 61\u201365"},{"key":"1338_CR26","doi-asserted-by":"publisher","first-page":"3387","DOI":"10.1121\/1.3097493","volume":"125","author":"J Ma","year":"2009","unstructured":"J. Ma, Y. Hu, P.C. Loizou, Objective measures for predicting speech intelligibility in noisy conditions based on new band importance functions. J. Acoust. Soc. Am. 125, 3387\u20133405 (2009)","journal-title":"J. Acoust. Soc. Am."},{"key":"1338_CR27","first-page":"1","volume":"15","author":"S Mavaddati","year":"2019","unstructured":"S. Mavaddati, A novel singing voice separation method based on sparse non-negative matrix factorization and low-rank modeling. Iran. J. Electr. Electron. Eng. 15, 1\u201317 (2019)","journal-title":"Iran. J. Electr. Electron. Eng."},{"key":"1338_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.specom.2015.11.003","volume":"76","author":"S Mavaddaty","year":"2016","unstructured":"S. Mavaddaty, S.M. Ahadi, S. Seyedin, A novel speech enhancement method by learnable sparse and low-rank decomposition and domain adaptation. Speech Commun. 76, 42\u201360 (2016)","journal-title":"Speech Commun."},{"key":"1338_CR29","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1049\/iet-spr.2014.0148","volume":"9","author":"S Mavaddaty","year":"2015","unstructured":"S. Mavaddaty, S.M. Ahadi, S. Seyedin, Modified coherence-based dictionary learning method for speech enhancement. Signal Process. IET 9, 537\u2013545 (2015)","journal-title":"Signal Process. IET"},{"key":"1338_CR30","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.csl.2017.01.009","volume":"44","author":"S Mavaddaty","year":"2017","unstructured":"S. Mavaddaty, S.M. Ahadi, S. Seyedin, Speech enhancement using sparse dictionary learning in wavelet packet transform domain. Comput. Speech Lang. 44, 22\u201347 (2017)","journal-title":"Comput. Speech Lang."},{"key":"1338_CR31","unstructured":"A.R. Nerkar, M.A. Joshi, Singing-voice separation from monaural recordings using empirical wavelet transform, in International Conference on Advanced Communication Control and Computing Technologies (2016), pp. 795\u2013800"},{"key":"1338_CR32","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","volume":"37","author":"BA Olshausen","year":"1997","unstructured":"B.A. Olshausen, D.J. Field, Sparse coding with an overcomplete basis set: a strategy employed by V1. Vis. Res. 37, 3311\u20133325 (1997)","journal-title":"Vis. Res."},{"key":"1338_CR33","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1109\/TASL.2007.899291","volume":"15","author":"A Ozerov","year":"2007","unstructured":"A. Ozerov, P. Philippe, F. Bimbot, R. Gribonval, Adaptation of Bayesian models for single-channel source separation and its application to voice\/music separation in popular songs. IEEE Trans. Audio Speech Lang. Process. 15, 1564\u20131578 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1338_CR34","unstructured":"Z. Rafii, B. Pardo, A simple music\/voice separation method based on the extraction of the repeating musical structure, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2011), pp. 221\u2013224"},{"key":"1338_CR35","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TASL.2012.2213249","volume":"21","author":"Z Rafii","year":"2013","unstructured":"Z. Rafii, B. Pardo, Repeating pattern extraction technique (REPET): a simple method for music\/voice separation. IEEE Trans. Audio Speech Lang. Process. 21, 73\u201384 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1338_CR36","unstructured":"A. Rix, J. Beerends, M. Hollier, A. Hekstra, Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs, in Proceedings of International Conference on Acoustics, Speech, Signal Processing (2001), pp. 749\u2013752"},{"key":"1338_CR37","volume-title":"Handbook of Parametric and Nonparametric Statistical Procedures","author":"DJ Sheskin","year":"2000","unstructured":"D.J. Sheskin, Handbook of Parametric and Nonparametric Statistical Procedures, 4th edn. (Chapman & Hall\/CRC, Boca Raton, 2000)","edition":"4"},{"key":"1338_CR38","first-page":"1698","volume":"20","author":"CD Sigg","year":"2012","unstructured":"C.D. Sigg, T. Dikk, J.M. Buhmann, Speech enhancement using generative dictionary learning. IEEE Trans. Acoust. Speech Signal Process. 20, 1698\u20131712 (2012)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"1338_CR39","unstructured":"P. Sprechmann, A. Bronstein, G. Sapiro, Real-time online singing voice separation from monaural recordings using robust low-rank modeling, in Proceedings of the 13th International Society for Music Information Retrieval Conference (2012), pp. 67\u201372"},{"key":"1338_CR40","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1109\/LSP.2013.2252615","volume":"20","author":"P Teng","year":"2013","unstructured":"P. Teng, Y. Jia, Voice activity detection via noise reducing using non-negative sparse coding. IEEE Signal Process. Lett. 20, 475\u2013478 (2013)","journal-title":"IEEE Signal Process. Lett."},{"key":"1338_CR41","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"E. Vincent, R. Gribonval, C. Fevotte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14, 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1338_CR42","unstructured":"Y.H. Yang, Low-rank representation of both singing voice and music accompaniment via learned dictionaries, in Proceedings of the 14th International Society for Music Information Retrieval Conference (2013), pp. 427\u2013432"},{"key":"1338_CR43","unstructured":"Y.H. Yang, On sparse and low-rank matrix decomposition for singing voice separation, in ACM Multimedia (2012), pp. 757\u2013760"},{"key":"1338_CR44","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.1109\/TASL.2006.889789","volume":"15","author":"L Yipeng","year":"2007","unstructured":"L. Yipeng, W. DeLiang, Separation of singing voice from music accompaniment for monaural recordings. IEEE Trans. Audio Speech Lang. Process. 15, 1475\u20131487 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1338_CR45","unstructured":"D.T. You, J.Q. Han, G.B. Zheng, T.R. Zheng, Sparse power spectrum based robust voice activity detector, in IEEE International Conference on Acoustics, Speech, and Signal Processing (2012), pp. 289\u2013292"},{"key":"1338_CR46","doi-asserted-by":"publisher","first-page":"2267","DOI":"10.1007\/s00034-014-9748-y","volume":"33","author":"DT You","year":"2014","unstructured":"D.T. You, J.Q. Han, G.B. Zheng, T.R. Zheng, J. Li, Sparse representation with optimized learned dictionary for robust voice activity detection. Circuits Syst. Signal Process. 33, 2267\u20132291 (2014)","journal-title":"Circuits Syst. Signal Process."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01338-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-019-01338-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-019-01338-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T00:51:14Z","timestamp":1609980674000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-019-01338-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,8]]},"references-count":46,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["1338"],"URL":"https:\/\/doi.org\/10.1007\/s00034-019-01338-0","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,8]]},"assertion":[{"value":"27 January 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}