{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T11:02:54Z","timestamp":1740135774953,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2016,8,26]],"date-time":"2016-08-26T00:00:00Z","timestamp":1472169600000},"content-version":"unspecified","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":[[2017,5]]},"DOI":"10.1007\/s00034-016-0388-2","type":"journal-article","created":{"date-parts":[[2016,8,26]],"date-time":"2016-08-26T11:15:48Z","timestamp":1472210148000},"page":"1970-1988","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hybrid Approach to Single-Channel Speech Separation Based on Coherent\u2013Incoherent Modulation Filtering"],"prefix":"10.1007","volume":"36","author":[{"given":"Azar","family":"Mahmoodzadeh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1408-5637","authenticated-orcid":false,"given":"Hamid Reza","family":"Abutalebi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,26]]},"reference":[{"key":"388_CR1","unstructured":"H.R. Abutalebi, H. Sheikhzadeh, R.L. Brennan, G.H. Freeman, Affine projection algorithm for oversampled subband adaptive filters. in Proceedings of IEEE ICASSP (2003), pp. 209\u2013212"},{"key":"388_CR2","doi-asserted-by":"crossref","unstructured":"T. Arai, M. Pavel, H. Hermansky, C. Avendano, Intelligibility of Speech with Filtered Time Trajectories of Spectral Envelopes. in Proceedings of ICSLP (1996), pp. 90\u201393","DOI":"10.1109\/ICSLP.1996.607318"},{"key":"388_CR3","unstructured":"L. Atlas, P. Clark, S. Schimmel, Modulation Toolbox Version 2.1 for MATLAB. (2012). https:\/\/sites.google.com\/a\/uw.edu\/isdl\/projects\/modulation-toolbox"},{"key":"388_CR4","doi-asserted-by":"crossref","unstructured":"L. Atlas, C. Janssen, Coherent modulation spectral filtering for single-channel music source separation. in Proceedings of IEEE ICASSP (2005), vol. IV, pp. 461\u2013464","DOI":"10.1109\/ICASSP.2005.1416045"},{"key":"388_CR5","doi-asserted-by":"crossref","unstructured":"L. Atlas, Q. Li, J. Thompson, Homomorphic modulation spectra. in Proceedings of IEEE ICASSP (2004), vol. II, pp. 761\u2013764","DOI":"10.1109\/ICASSP.2004.1326369"},{"issue":"1","key":"388_CR6","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 Lang. Process 14(1), 191\u2013199 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"388_CR7","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1006\/csla.1994.1016","volume":"8","author":"GJ Brown","year":"1994","unstructured":"G.J. Brown, M. Cooke, Computational auditory scene analysis. Comput. Speech Lang. 8, 297\u2013336 (1994)","journal-title":"Comput. Speech Lang."},{"issue":"11","key":"388_CR8","doi-asserted-by":"crossref","first-page":"4323","DOI":"10.1109\/TSP.2009.2025107","volume":"57","author":"P Clark","year":"2009","unstructured":"P. Clark, L. Atlas, Time-frequency coherent modulation filtering of non-stationary signals. IEEE Trans. Signal Process. 57(11), 4323\u20134332 (2009)","journal-title":"IEEE Trans. Signal Process."},{"key":"388_CR9","volume-title":"Modeling Auditory Processing and Organization","author":"MP Cooke","year":"1993","unstructured":"M.P. Cooke, Modeling Auditory Processing and Organization (Cambridge Univ. Press, Cambridge, 1993)"},{"issue":"1","key":"388_CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.csl.2009.02.006","volume":"24","author":"M Cooke","year":"2010","unstructured":"M. Cooke, J.R. Hershey, S.J. Rennie, Monaural speech separation and recognition challenge. Comput. Speech Lang. 24(1), 1\u201315 (2010)","journal-title":"Comput. Speech Lang."},{"key":"388_CR11","unstructured":"L.A. Drake, Sound source separation via computational auditory scene analysis (CASA) enhanced beamforming. Ph.D. dissertation, Dept. Elect. Eng., Northwestern Univ., Evanston, IL, 2001"},{"issue":"2","key":"388_CR12","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1121\/1.408467","volume":"95","author":"R Drullman","year":"1994","unstructured":"R. Drullman, J. Festen, R. Plomp, Effect of temporal envelope smearing on speech reception. J. Acoust. Soc. Am. 95(2), 1053\u20131064 (1994)","journal-title":"J. Acoust. Soc. Am."},{"key":"388_CR13","unstructured":"J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, N.L. Dahlgren, DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus. (1993). http:\/\/www.ldc.upenn.edu\/Catalog\/LDC93S1.html"},{"issue":"3","key":"388_CR14","doi-asserted-by":"crossref","first-page":"1628","DOI":"10.1121\/1.1396325","volume":"110","author":"O Ghitza","year":"2001","unstructured":"O. Ghitza, On the upper cutoff frequency of the auditory critical-band envelope detectors in the context of speech perception. J. Acoust. Soc. Am. 110(3), 1628\u20131640 (2001)","journal-title":"J. Acoust. Soc. Am."},{"key":"388_CR15","doi-asserted-by":"crossref","unstructured":"S. Greenberg, B.E.D. Kingsbury, The Modulation Spectrogram: in Pursuit of an Invariant Representation of Speech,\u201d in Proceedings of IEEE ICASSP, (1997) pp. 1647\u20131650","DOI":"10.1109\/ICASSP.1997.598826"},{"key":"388_CR16","unstructured":"L. Gu, R.M. Stern, Single-channel speech separation based on modulation frequency. in Proceedings of IEEE ICASSP (2008), pp. 25\u201328"},{"issue":"1","key":"388_CR17","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.csl.2008.11.001","volume":"24","author":"J Hershey","year":"2010","unstructured":"J. Hershey, S. Rennie, P. Olsen, T. Kristjansson, Super-human multitalker speech recognition: a graphical modeling approach. Comput. Speech Lang. 24(1), 45\u201366 (2010)","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"388_CR18","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2008","unstructured":"Y. Hu, P.C. Loizou, Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio Speech Lang. Process. 16(1), 229\u2013238 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"388_CR19","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 Lang. Process. 15(2), 396\u2013405 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"388_CR20","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 separation based on fundamental frequency tracking and amplitude modulation. IEEE Trans. Neural Netw. 15, 1135\u20131150 (2004)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"8","key":"388_CR21","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","volume":"18","author":"G Hu","year":"2010","unstructured":"G. Hu, D.L. Wang, A tandem algorithm for fundamental frequency estimation and voiced speech segregation. IEEE Trans. Audio Speech Lang. Process. 18(8), 2067\u20132079 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"388_CR22","doi-asserted-by":"crossref","unstructured":"M. Karjalainen, T. Tolonen, Multi-pitch and periodicity analysis model for sound separation and auditory scene analysis. in Proceedings of IEEE ICASSP (1999), pp. 929\u2013932","DOI":"10.1109\/ICASSP.1999.759824"},{"key":"388_CR23","doi-asserted-by":"crossref","unstructured":"A. Kusumoto, T. Arai, T. Kitamura, M. Takahasi, Y. Murahara, Modulation enhancement of speech as preprocessing for reverberant chambers with the hearing-impaired. in Proceedings of IEEE ICASSP (2000), pp. 853\u2013856","DOI":"10.1109\/ICASSP.2000.859094"},{"key":"388_CR24","doi-asserted-by":"crossref","unstructured":"H. Laurberg, Uniqueness of non-negative matrix factorization. in Proceedings of IEEE 14th Workshop on Statistical Signal Processing (2007), pp. 44\u201348","DOI":"10.1109\/SSP.2007.4301215"},{"issue":"1","key":"388_CR25","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.csl.2008.05.005","volume":"24","author":"P Li","year":"2010","unstructured":"P. Li, Y. Guan, S. Wang, B. Xu, W. Liu, Monaural speech separation based on MAXVQ and CASA for robust speech recognition. Comput. Speech Lang. 24(1), 30\u201344 (2010)","journal-title":"Comput. Speech Lang."},{"issue":"3","key":"388_CR26","doi-asserted-by":"crossref","first-page":"1594","DOI":"10.1121\/1.416061","volume":"100","author":"PJ Loughlin","year":"1996","unstructured":"P.J. Loughlin, B. Tacer, On the amplitude- and frequency-modulation decomposition of signals. J. Acoust. Soc. Am. 100(3), 1594\u20131601 (1996)","journal-title":"J. Acoust. Soc. Am."},{"key":"388_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-67","author":"A Mahmoodzadeh","year":"2012","unstructured":"A. Mahmoodzadeh, H.R. Abutalebi, H. Soltanian-Zadeh, H. Sheikhzadeh, Single channel speech separation in modulation frequency domain based on a novel fundamental frequency range estimation method. EURASIP J. Adv. Signal Process. (2012). doi: 10.1186\/1687-6180-2012-67","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"388_CR28","doi-asserted-by":"crossref","unstructured":"A. Mahmoodzadeh, H. Sheikhzadeh, H.R. Abutalebi, H. Soltanian-Zadeh, A hybrid coherent-incoherent method of modulation filtering for single channel speech separation. in Proceedings of IEEE ICASSP (2012), pp. 329\u2013332","DOI":"10.1109\/ICASSP.2012.6287883"},{"issue":"1","key":"388_CR29","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.csl.2007.12.004","volume":"24","author":"J Ming","year":"2010","unstructured":"J. Ming, T. Hazen, J. Glass, Combining missing-feature theory, speech enhancement, and speaker-dependent-independent modeling for speech separation. Comput. Speech Lang. 24(1), 67\u201376 (2010)","journal-title":"Comput. Speech Lang."},{"key":"388_CR30","doi-asserted-by":"crossref","unstructured":"P. Mowlaee, New Strategies for Single-channel Speech Separation. Ph.D. dissertation, Dept. Electronic Systems, Aalborg University (2010)","DOI":"10.1109\/ICASSP.2010.5495679"},{"key":"388_CR31","volume-title":"Theory and Applications of Digital Speech Processing","author":"LR Rabiner","year":"2011","unstructured":"L.R. Rabiner, R.W. Schafer, Theory and Applications of Digital Speech Processing (Prentice-Hall Inc, Upper Saddle River, 2011)"},{"issue":"6","key":"388_CR32","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1016\/j.specom.2007.04.007","volume":"49","author":"M Radfar","year":"2007","unstructured":"M. Radfar, R. 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":"388_CR33","unstructured":"S.T. Roweis, One microphone source separation. in Proceedings of Neural Information Processing Systems (2000), pp. 793\u2013799"},{"issue":"4","key":"388_CR34","doi-asserted-by":"crossref","first-page":"1086","DOI":"10.1109\/78.827542","volume":"48","author":"SG Sankaran","year":"2000","unstructured":"S.G. Sankaran, A.A. Beex, Convergence behavior of affine projection algorithms. IEEE Trans. Signal Process. 48(4), 1086\u20131096 (2000)","journal-title":"IEEE Trans. Signal Process."},{"key":"388_CR35","unstructured":"S.M. Schimmel, Theory of modulation frequency analysis and modulation filtering with applications to hearing devices. Ph.D. dissertation, Dept. Comput. Sci. & Eng., Washington University (2007)"},{"key":"388_CR36","doi-asserted-by":"crossref","unstructured":"S.M. Schimmel, L.E. Atlas, Coherent envelope detection for modulation filtering of speech. in Proceedings of IEEE ICASSP (2005), vol. I, pp. 221\u2013224","DOI":"10.1109\/ICASSP.2005.1415090"},{"key":"388_CR37","doi-asserted-by":"crossref","unstructured":"S.M. Schimmel, L.E. Atlas, K. Nie, Feasibility of single channel speaker separation based on modulation frequency analysis. in Proceedings of IEEE ICASSP (2007), vol. 4, Apr., pp. 605\u2013608","DOI":"10.1109\/ICASSP.2007.366985"},{"key":"388_CR38","doi-asserted-by":"crossref","unstructured":"S.M. Schimmel, K.R. Fitz, L.E. Atlas, Frequency reassignment for coherent modulation filtering. in Proceedings of IEEE ICASSP (2006), vol. 5, pp. 261\u2013264","DOI":"10.1109\/ICASSP.2006.1661262"},{"issue":"1","key":"388_CR39","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.L. 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":"388_CR40","doi-asserted-by":"crossref","unstructured":"M. S. Vinton, L. E. Atlas, Scalable and progressive audio codec. in Proceedings of IEEE ICASSP (2001), vol. 5, pp. 3277\u20133280","DOI":"10.1109\/ICASSP.2001.940358"},{"key":"388_CR41","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-IEEE Press, Hoboken, 2006)"},{"key":"388_CR42","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."},{"key":"388_CR43","doi-asserted-by":"crossref","unstructured":"M. Wu, D.L. Wang, G.J. Brown, A multi-pitch tracking algorithm for noisy speech. in Proceedings of IEEE ICASSP (2002), pp. 369\u2013372","DOI":"10.1109\/ICASSP.2002.5743731"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-016-0388-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-016-0388-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-016-0388-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-016-0388-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T21:23:14Z","timestamp":1692480194000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-016-0388-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,26]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2017,5]]}},"alternative-id":["388"],"URL":"https:\/\/doi.org\/10.1007\/s00034-016-0388-2","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2016,8,26]]}}}