{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T01:40:03Z","timestamp":1651628403442},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2015,3,31]],"date-time":"2015-03-31T00:00:00Z","timestamp":1427760000000},"content-version":"tdm","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":[[2015,12]]},"DOI":"10.1007\/s00034-015-0033-5","type":"journal-article","created":{"date-parts":[[2015,3,30]],"date-time":"2015-03-30T22:05:41Z","timestamp":1427753141000},"page":"3861-3882","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Single-channel Speech Separation Using Dictionary-updated Orthogonal Matching Pursuit and Temporal Structure Information"],"prefix":"10.1007","volume":"34","author":[{"given":"Haiyan","family":"Guo","sequence":"first","affiliation":[]},{"given":"Xiaoxiong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zhenyang","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,3,31]]},"reference":[{"issue":"1","key":"33_CR1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1109\/TSA.2005.854110","volume":"14","author":"L Benaroya","year":"2006","unstructured":"L. Benaroya, F. Bimbot, R. Gribonval, Audio source separation with a single sensor. IEEE Trans. Audio Speech 14(1), 191\u2013199 (2006)","journal-title":"IEEE Trans. Audio Speech"},{"key":"33_CR2","first-page":"613","volume":"6","author":"L Benaroya","year":"2003","unstructured":"L. Benaroya, L.M. Donagh, F. Bimbot, R. Gribonval, Non negative sparse representation for wiener based source separation with a single sensor. ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc. 6, 613\u2013616 (2003). doi: 10.1109\/ICASSP.2003.1201756","journal-title":"ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc."},{"issue":"1","key":"33_CR3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1137\/S1064827596304010","volume":"20","author":"SS Chen","year":"1998","unstructured":"S.S. Chen, D.L. Donoho, M.A. Saunders, Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20(1), 33\u201361 (1998)","journal-title":"SIAM J. Sci. Comput."},{"issue":"1","key":"33_CR4","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1137\/S003614450037906X","volume":"43","author":"SS Chen","year":"2001","unstructured":"S.S. Chen, D.L. Donoho, Atomic decomposition by basis pursuit. SIAM Rev. 43(1), 129\u2013159 (2001)","journal-title":"SIAM Rev."},{"issue":"5","key":"33_CR5","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"MP Cooke","year":"2006","unstructured":"M.P. Cooke, J. Barker, S.P. Cunningham, X. Shao, An audiovisual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"33_CR6","doi-asserted-by":"crossref","DOI":"10.1515\/9781400884179","volume-title":"Linear Programming and Extensions","author":"GB Dantzig","year":"1963","unstructured":"G.B. Dantzig, Linear Programming and Extensions (Princeton University Press, Princeton, 1963)"},{"issue":"2","key":"33_CR7","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1109\/TIT.2011.2173241","volume":"58","author":"DL Donoho","year":"2012","unstructured":"D.L. Donoho, Y. Tsaig, I. Drori, J.L. Starck, Sparse solution of underdetermined systems of linear equations by stagewise orthogonal matching pursuit. IEEE Trans. Inform. Theory 58(2), 1094\u20131121 (2012)","journal-title":"IEEE Trans. Inform. Theory"},{"key":"33_CR8","first-page":"957","volume":"5","author":"DPW Ellis","year":"2006","unstructured":"D.P.W. Ellis, R.J. Weiss, Model-based monaural source separation using a vector-quantized phase-vocoder representation. ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc. 5, 957\u2013960 (2006)","journal-title":"ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc."},{"key":"33_CR9","volume-title":"Numerical Linear Algebra and Optimization","author":"PE Gill","year":"1991","unstructured":"P.E. Gill, W. Murray, M.H. Wright, Numerical Linear Algebra and Optimization (Addison-Wesley, Redwood City, 1991)"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"J.R. Hershey, S.J. Rennie, P.A. Olsen, T.T. Kristjansson, Superhuman multi-talker speech recognition: a graphical modeling approach. Comput. Speech Lang. 24(1), 45\u201366 (2010)","DOI":"10.1016\/j.csl.2008.11.001"},{"issue":"5","key":"33_CR11","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1109\/TNN.2004.832812","volume":"15","author":"G Hu","year":"2004","unstructured":"G. Hu, D.L. Wang, Monaural speech segregation based on pitch tracking and amplitude modulation. IEEE Trans. Neural Netw. 15(5), 1135\u20131150 (2004)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"2","key":"33_CR12","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TASL.2006.881700","volume":"15","author":"G Hu","year":"2007","unstructured":"G. Hu, D.L. Wang, Auditory segmentation based on onset and offset analysis. IEEE Trans. Audio Speech 15(2), 396\u2013405 (2007)","journal-title":"IEEE Trans. Audio Speech"},{"issue":"7\u20138","key":"33_CR13","first-page":"1365","volume":"4","author":"GJ Jang","year":"2003","unstructured":"G.J. Jang, T.W. Lee, A maximum likelihood approach to single-channel source separation. J. Mach. Learn. Res. 4(7\u20138), 1365\u20131392 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"33_CR14","unstructured":"G.J. Jang, T.W. Lee, A probabilistic approach to single channel source separation. in 16th Annual Neural Information Processing Systems Conference (2003)"},{"key":"33_CR15","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/LSP.2003.811630","volume":"10","author":"GJ Jang","year":"2003","unstructured":"G.J. Jang, T.W. Lee, Y.H. Oh, Single-channel signal separation using time-domain basis functions. IEEE Signal Process. Lett. 10, 168\u2013171 (2003)","journal-title":"IEEE Signal Process. Lett."},{"key":"33_CR16","first-page":"45","volume":"5","author":"GJ Jang","year":"2003","unstructured":"G.J. Jang, T.W. Lee, Y.H. Oh, A subspace approach to single channel signal separation using maximum likelihood weighting filters. IEEE Int. Conf. Acoust. Speech Signal Process. 5, 45\u201348 (2003). doi: 10.1109\/ICASSP.2003.1199864","journal-title":"IEEE Int. Conf. Acoust. Speech Signal Process."},{"key":"33_CR17","first-page":"297","volume":"4","author":"H Katmeoka","year":"2004","unstructured":"H. Katmeoka, T. Nishimoto, S. Sagayama, Separation of harmonic structures based on tied Gaussian mixture model and information criterion for concurrent sounds. IEEE Int. Conf. Acoust. Speech Signal Process. 4, 297\u2013300 (2004)","journal-title":"IEEE Int. Conf. Acoust. Speech Signal Process."},{"key":"33_CR18","unstructured":"M. Moussallam, G. Richard, L. Daudet, Audio source separation informed by redundancy with greedy multiscale decompositions. in European Signal Processing Conference (2012), pp. 2644\u20132648"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"P. Mowlaee, M.G. Christensen, S.H. Jensen, Improved single-channel speech separation using sinusoidal modeling. ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc. 21\u201324 (2010). doi: 10.1109\/ICASSP.2010.5496263","DOI":"10.1109\/ICASSP.2010.5496263"},{"issue":"5","key":"33_CR20","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/TASL.2010.2089520","volume":"19","author":"P Mowlaee","year":"2011","unstructured":"P. Mowlaee, M.G. Christensen, S.H. Jensen, New results on single-channel speech separation using sinusoidal modeling. IEEE Trans. Audio Speech 19(5), 1265\u20131277 (2011)","journal-title":"IEEE Trans. Audio Speech"},{"issue":"3","key":"33_CR21","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1631\/jzus.C0910087","volume":"11","author":"P Mowlaee","year":"2010","unstructured":"P. Mowlaee, A. Sayadiyan, H. Sheikhzadeh, Evaluating single-channel speech separation performance in transform-domain. Sci. C J. Zhejiang Univ. 11(3), 160\u2013174 (2010)","journal-title":"Sci. C J. Zhejiang Univ."},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Y.C. Pati, R. Rezaiifar, P.S. Krishnaprasad, Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. in Conference Record of Asilomar Conference Signals Systems Computers (1993), pp 40\u201344","DOI":"10.1109\/ACSSC.1993.342465"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"B.A. Pearlmutter, R.K. Olsson, Linear program differentiation for single-channel speech separation. in Proceedings of IEEE Signal Processing Society Workshop. Machine Learning Signal Processing MLSP 2006. pp. 421\u2013426 (2006). doi: 10.1109\/MLSP.2006.275587","DOI":"10.1109\/MLSP.2006.275587"},{"issue":"1","key":"33_CR24","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/29.45618","volume":"38","author":"TF Quatieri","year":"1990","unstructured":"T.F. Quatieri, R.G. Danisewicz, An approach to co-channel talker interference suppression using a sinusoidal model for speech. IEEE Trans. Audio Speech 38(1), 56\u201369 (1990)","journal-title":"IEEE Trans. Audio Speech"},{"issue":"8","key":"33_CR25","doi-asserted-by":"crossref","first-page":"2299","DOI":"10.1109\/TASL.2007.904233","volume":"15","author":"MH Radfar","year":"2007","unstructured":"M.H. Radfar, R.M. Dansereau, Single-channel speech separation using soft mask filtering. IEEE Trans. Audio Speech 15(8), 2299\u20132310 (2007)","journal-title":"IEEE Trans. Audio Speech"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"M.H. Radfar, R.M. Dansereau, A. Sayadiyan, A maximum likelihood estimation of vocal-tract-related filter characteristics for single channel speech separation. EURASIP J. Audio Speech Music Process 2007, 084186 (2007). doi: 10.1155\/2007\/84186","DOI":"10.1155\/2007\/84186"},{"issue":"6","key":"33_CR27","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1016\/j.specom.2007.04.007","volume":"49","author":"MH Radfar","year":"2007","unstructured":"M.H. Radfar, R.M. Dansereau, A. Sayadiyan, Monaural speech segregation based on fusion of source-driven with model-driven techniques. Speech Commun. 49(6), 464\u2013476 (2007)","journal-title":"Speech Commun."},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"B. Raj, P. Smaragdis, Latent variable decomposition of spectrograms for single channel speaker separation. in IEEE ASSP Workshop Applications Signal Processing to Audio Acoustics, pp. 17\u201320, doi: 10.1109\/ASPAA.2005.1540157","DOI":"10.1109\/ASPAA.2005.1540157"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"A.M. Reddy, B. Raj, A minimum mean squared error estimator for single channel speaker separation. in INTERSPEECH- 2004, pp. 2445\u20132448 (2004)","DOI":"10.21437\/Interspeech.2004-394"},{"issue":"6","key":"33_CR30","doi-asserted-by":"crossref","first-page":"1766","DOI":"10.1109\/TASL.2007.901310","volume":"15","author":"AM Reddy","year":"2007","unstructured":"A.M. Reddy, B. Raj, Soft mask methods for single-channel speaker separation. IEEE Trans. Audio Speech 15(6), 1766\u20131776 (2007)","journal-title":"IEEE Trans. Audio Speech"},{"key":"33_CR31","first-page":"641","volume":"5","author":"MJ Reyes-Gomez","year":"2004","unstructured":"M.J. Reyes-Gomez, D.P.W. Ellis, N. Jojic, Multiband audio modeling for single-channel acoustic source separation. ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc. 5, 641\u2013644 (2004). doi: 10.1109\/ICASSP.2004.1327192","journal-title":"ICASSP IEEE Int. Conf. Acoust. Speech Signal Process. Proc."},{"key":"33_CR32","unstructured":"S.T. Roweis, One microphone source separation. Adv. Neural. In. 13, 793\u2013799 (2000)"},{"key":"33_CR33","unstructured":"S.T. Roweis, Factorial models and refiltering for speech separation and denoising. in EUROSPEECH (2003), pp. 1009\u20131012"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"M.N. Schmidt, R.K. Olsson, Linear regression on sparse features for single-channel speech separation. in IEEE ASSP Workshop Applications of Signal Processing to Audio Acoustics, pp. 26\u201329 (2007). doi: 10.1109\/ASPAA.2007.4393010","DOI":"10.1109\/ASPAA.2007.4393010"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"M.N. Schmidt, R.K. Olsson, Single-channel speech separation using sparse non-negative matrix factorization. in INTERSPEECH 2006","DOI":"10.21437\/Interspeech.2006-655"},{"issue":"1","key":"33_CR36","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.csl.2008.03.004","volume":"24","author":"Y Shao","year":"2010","unstructured":"Y. Shao, S. Srinivasan, Z. Jin, D. Wang, A computational auditory scene analysis system for speech segregation and robust speech recognition. Comput. Speech Lang. 24(1), 77\u201393 (2010)","journal-title":"Comput. Speech Lang."},{"key":"33_CR37","first-page":"641","volume":"2","author":"MVS Shashanka","year":"2007","unstructured":"M.V.S. Shashanka, B. Raj, P. Smaragdis, Sparse overcomplete decomposition for single channel speaker separation. IEEE Trans. Audio Speech 2, 641\u2013644 (2007)","journal-title":"IEEE Trans. Audio Speech"},{"issue":"2","key":"33_CR38","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/TASL.2010.2047419","volume":"19","author":"M Stark","year":"2011","unstructured":"M. Stark, M. Wohlmayr, F. Pernkopf, Source-filter-based single-channel speech separation using pitch information. IEEE Trans. Audio Speech 19(2), 242\u2013255 (2011)","journal-title":"IEEE Trans. Audio Speech"},{"issue":"12","key":"33_CR39","doi-asserted-by":"crossref","first-page":"4655","DOI":"10.1109\/TIT.2007.909108","volume":"53","author":"JA Tropp","year":"2007","unstructured":"J.A. Tropp, A.C. Gilbert, Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans. Inform. Theory 53(12), 4655\u20134666 (2007)","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"3","key":"33_CR40","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"T. Virtanen, Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Audio Speech 15(3), 1066\u20131074 (2007)","journal-title":"IEEE Trans. Audio Speech"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"T. Virtanen, Speech recognition using factorial hidden Markov models for separation in the feature space. in INTERSPEECH 2006, pp. 89\u201392 (2006)","DOI":"10.21437\/Interspeech.2006-23"},{"key":"33_CR42","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/0-387-22794-6_12","volume-title":"Speech Separation by Humans and Machines","author":"DL Wang","year":"2005","unstructured":"D.L. Wang, On ideal binary mask as the computational goal of auditory scene analysis, in Speech Separation by Humans and Machines, ed. by D.L. Wang (Kluwer Academic, Norwell, 2005), pp. 181\u2013197"},{"key":"33_CR43","doi-asserted-by":"crossref","DOI":"10.1109\/9780470043387","volume-title":"Computational Auditory Scene Analysis: Principles, Algorithms, and Applications","author":"DL Wang","year":"2006","unstructured":"D.L. Wang, G.J. Brown, Computational Auditory Scene Analysis: Principles, Algorithms, and Applications (Wiley, NY, 2006)"},{"key":"33_CR44","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/72.761727","volume":"10","author":"DL Wang","year":"1999","unstructured":"D.L. Wang, G.J. Brown, Separation of speech from interfering sounds based on oscillatory correlation. IEEE Trans. Neural Netw. 10, 684\u2013697 (1999)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"1","key":"33_CR45","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.csl.2008.03.003","volume":"24","author":"RJ Weiss","year":"2010","unstructured":"R.J. Weiss, D.P.W. Ellis, Speech separation using speaker-adapted eigenvoice speech models. Comput. Speech Lang. 24(1), 16\u201329 (2010)","journal-title":"Comput. Speech Lang."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-015-0033-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-015-0033-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-015-0033-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T01:12:47Z","timestamp":1651626767000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-015-0033-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3,31]]},"references-count":45,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["33"],"URL":"https:\/\/doi.org\/10.1007\/s00034-015-0033-5","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3,31]]}}}