{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T21:10:24Z","timestamp":1688505024057},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,9,25]],"date-time":"2013-09-25T00:00:00Z","timestamp":1380067200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1007\/s00034-013-9656-6","type":"journal-article","created":{"date-parts":[[2013,9,25]],"date-time":"2013-09-25T01:55:48Z","timestamp":1380074148000},"page":"565-588","source":"Crossref","is-referenced-by-count":0,"title":["Co-channel Speech Separation Based on Amplitude Modulation Spectrum Analysis"],"prefix":"10.1007","volume":"33","author":[{"given":"Qi","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man-Gui","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,9,25]]},"reference":[{"issue":"5","key":"9656_CR1","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/78.382394","volume":"43","author":"F. Auger","year":"1995","unstructured":"F. Auger, P. Flandrin, Improving the readability of time-frequency and time-scale representations by the reassignment method. IEEE Trans. Signal Process. 43(5), 1068\u20131089 (1995)","journal-title":"IEEE Trans. Signal Process."},{"key":"9656_CR2","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1486.001.0001","volume-title":"Auditory Scene Analysis","author":"A. Bregman","year":"1990","unstructured":"A. Bregman, Auditory Scene Analysis (MIT Press, Cambridge, 1990)"},{"key":"9656_CR3","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1006\/csla.1994.1016","volume":"8","author":"G. Brown","year":"1994","unstructured":"G. Brown, M. Cooke, Computational auditory scene analysis. Comput. Speech Lang. 8, 297\u2013336 (1994)","journal-title":"Comput. Speech Lang."},{"key":"9656_CR4","unstructured":"P. Boersma, D. Weenink, Praat: doing phonetics by computer (Version 4.3.14) (2005). Accessed 21 August 2013. See http:\/\/www.fon.hum.uva.nl\/praat"},{"issue":"6","key":"9656_CR5","doi-asserted-by":"crossref","first-page":"3615","DOI":"10.1121\/1.414959","volume":"99","author":"T. Dau","year":"1996","unstructured":"T. Dau, D. Puschel, A. Kohlrausch, A quantitative model of the \u201ceffective\u201d signal processing in the auditory system. I. Model structure. J. Acoust. Soc. Am. 99(6), 3615\u20133622 (1996)","journal-title":"J. Acoust. Soc. Am."},{"key":"9656_CR6","unstructured":"D. Ellis, Prediction-driven computational auditory scene analysis. Ph.D. Dissertation, Mass. Inst. of Technol, Cambridge, MA (1996)"},{"issue":"6","key":"9656_CR7","doi-asserted-by":"crossref","first-page":"2174","DOI":"10.1109\/TSA.2005.858523","volume":"14","author":"C. Fevotte","year":"2006","unstructured":"C. Fevotte, S. Godsill, A Bayesian approach for blind separation of sparse sources. IEEE Trans. Audio Speech Lang. Process. 14(6), 2174\u20132188 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9656_CR8","first-page":"179","volume-title":"Applications in Time-Frequency Signal Processing","author":"P. Flandrin","year":"2003","unstructured":"P. Flandrin, F. Auger, E. Chassande-Mottin, Time-frequency reassignment: from principles to algorithms, in Applications in Time-Frequency Signal Processing, ed. by P. Antonia (CRC Press, Boca Raton, 2003), pp. 179\u2013203"},{"key":"9656_CR9","doi-asserted-by":"crossref","unstructured":"J. Garofolo, L. Lamel, W. Fisher, J. Fiscus, D. Pallett, N. Dahlgren, DARPA TIMIT acoustic-phonetic continuous speech corpus. Technical Report NISTIR 4930, National Inst. of Standards and Technol, Gaithersburg, MD (1993)","DOI":"10.6028\/NIST.IR.4930"},{"issue":"1","key":"9656_CR10","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1121\/1.396427","volume":"83","author":"D. Hermes","year":"1988","unstructured":"D. Hermes, Measurement of pitch by subharmonic summation. J. Acoust. Soc. Am. 83(1), 257\u2013264 (1988)","journal-title":"J. Acoust. Soc. Am."},{"issue":"5","key":"9656_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. 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":"8","key":"9656_CR12","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","volume":"18","author":"G. Hu","year":"2010","unstructured":"G. Hu, D. Wang, A tandem algorithm for pitch estimation and voiced speech segregation. IEEE Trans. Audio Speech Lang. Process. 18(8), 2067\u20132079 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"9656_CR13","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TASL.2006.881700","volume":"15","author":"G. Hu","year":"2007","unstructured":"G. Hu, D. 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":"9656_CR14","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 multi-talker speech recognition: a\u00a0graphical modeling approach. Comput. Speech Lang. 24, 45\u201366 (2010)","journal-title":"Comput. Speech Lang."},{"key":"9656_CR15","unstructured":"J. Holdsworth, I. Nimmo-Smith, R. Patterson, P. Rice, Implementing a gammatone filter bank. MRC Appl. Psychology Unit Rep. (1988)"},{"issue":"5","key":"9656_CR16","doi-asserted-by":"crossref","first-page":"3475","DOI":"10.1121\/1.4754541","volume":"132","author":"K. Han","year":"2012","unstructured":"K. Han, D. Wang, A classification based approach to speech segregation. J. Acoust. Soc. Am. 132(5), 3475\u20133483 (2012)","journal-title":"J. Acoust. Soc. Am."},{"issue":"1","key":"9656_CR17","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TASL.2012.2215591","volume":"21","author":"K. Hu","year":"2013","unstructured":"K. Hu, D. Wang, An unsupervised approach to cochannel speech separation. IEEE Trans. Audio Speech Lang. Process. 21(1), 122\u2013131 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9656_CR18","first-page":"1173","volume-title":"Advances in Neural Inf. Process, Syst.","author":"G. Jang","year":"2003","unstructured":"G. Jang, T. Lee, A probabilistic approach to single channel blind source separation, in Advances in Neural Inf. Process, Syst., (2003), pp. 1173\u20131180"},{"issue":"5","key":"9656_CR19","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/TASL.2010.2077280","volume":"19","author":"Z. Jin","year":"2011","unstructured":"Z. Jin, D. Wang, HMM-based multipitch tracking for noisy and reverberant speech. IEEE Trans. Audio Speech Lang. Process. 19(5), 1091\u20131102 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9656_CR20","unstructured":"A. Klapuri, Signal processing methods for the automatic transcription of music. Ph.D. Dissertation, Tampere University of Technol, Finland (2004)"},{"issue":"2","key":"9656_CR21","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1109\/TASL.2007.908129","volume":"16","author":"A. Klapuri","year":"2008","unstructured":"A. Klapuri, Multipitch analysis of polyphonic music and speech signals using an auditory model. IEEE Trans. Audio Speech Lang. Process. 16(2), 255\u2013266 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"9656_CR22","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1121\/1.408546","volume":"95","author":"B. Kollmeier","year":"1994","unstructured":"B. Kollmeier, R. Koch, Speech enhancement based on physiological and psychoacoustical models of modulation perception and binaural interaction. J. Acoust. Soc. Am. 95(3), 1593\u20131602 (1994)","journal-title":"J. Acoust. Soc. Am."},{"issue":"3","key":"9656_CR23","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1121\/1.3184603","volume":"129","author":"G. Kim","year":"2009","unstructured":"G. Kim, Y. Lu, Y. Hu, P. Loizou, An algorithm that improves speech intelligibility in noise for normal-hearing listeners. J. Acoust. Soc. Am. 129(3), 1486\u20131494 (2009)","journal-title":"J. Acoust. Soc. Am."},{"key":"9656_CR24","volume-title":"Advances in Neural Inf. Process. Syst.","author":"M. Lewicki","year":"1998","unstructured":"M. Lewicki, T. Sejnowski, Learning nonlinear overcomplete representations for efficient coding, in Advances in Neural Inf. Process. Syst., ed. by M. Jordan, M. Kearns, S. Solla (MIT Press, Cambridge, 1998)"},{"issue":"3","key":"9656_CR25","doi-asserted-by":"crossref","first-page":"1673","DOI":"10.1121\/1.2832617","volume":"123","author":"N. Li","year":"2008","unstructured":"N. Li, P. Loizou, Factors infuencing intelligibility of ideal binary-masked speech: implications for noise reduction. J. Acoust. Soc. Am. 123(3), 1673\u20131682 (2008)","journal-title":"J. Acoust. Soc. Am."},{"issue":"6","key":"9656_CR26","doi-asserted-by":"crossref","first-page":"2014","DOI":"10.1109\/TASL.2006.883258","volume":"14","author":"P. Li","year":"2006","unstructured":"P. Li, Y. Guan, B. Xu, W. Liu, Monaural speech separation based on computational auditory scene analysis and objective quality assessment of speech. IEEE Trans. Audio Speech Lang. Process. 14(6), 2014\u20132023 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9656_CR27","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.specom.2008.09.001","volume":"51","author":"Y. Li","year":"2009","unstructured":"Y. Li, D. Wang, On the optimality of ideal binary time frequency masks. Speech Commun. 51, 230\u2013239 (2009)","journal-title":"Speech Commun."},{"key":"9656_CR28","author":"A. Mahmoodzadeh","year":"2012","unstructured":"A. Mahmoodzadeh, H. Abutalebi, H. Soltanian-Zadeh, H. Sheikhzadeh, Single channel speech separation in modulation frequency domain based on a novel pitch range estimation method. EURASIP J. Adv. Signal Process. (2012). doi: 10.1186\/1687-6180-2012-67","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"9656_CR29","volume-title":"An Introduction to the Psychology of Hearing","author":"B. Moore","year":"2003","unstructured":"B. Moore, An Introduction to the Psychology of Hearing (Academic Press, San Diego, 2003)"},{"issue":"5","key":"9656_CR30","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/TASL.2010.2089520","volume":"19","author":"P. Mowlaee","year":"2011","unstructured":"P. Mowlaee, M. Christensen, S. Jensen, New results on single-channel speech separation using sinusoidal modeling. IEEE Trans. Audio Speech Lang. Process. 19(5), 1265\u20131277 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"9656_CR31","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1121\/1.1910339","volume":"41","author":"A. Noll","year":"1967","unstructured":"A. Noll, Cepstrum pitch determination. J. Acoust. Soc. Am. 41(2), 293\u2013309 (1967)","journal-title":"J. Acoust. Soc. Am."},{"issue":"3","key":"9656_CR32","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1109\/89.668821","volume":"6","author":"F. Plante","year":"1998","unstructured":"F. Plante, G. Meyer, W. Ainsworth, Improvement of speech spectrogram accuracy by the method of reassignment. IEEE Trans. Speech Audio Process. 6(3), 282\u2013286 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"9656_CR33","unstructured":"R. Patterson, I. Nimmo-Smith, J. Holdsworth, P. Rice, An efficient auditory filterbank based on the gammatone function. MRC Appl. Psychology Unit Rep. pp. 1\u201333 (1988)"},{"issue":"6","key":"9656_CR34","doi-asserted-by":"crossref","first-page":"1766","DOI":"10.1109\/TASL.2007.901310","volume":"15","author":"A. Reddy","year":"2007","unstructured":"A. Reddy, B. Raj, Soft mask methods for single-channel speaker separation. IEEE Trans. Audio Speech Lang. Process. 15(6), 1766\u20131776 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"8","key":"9656_CR35","doi-asserted-by":"crossref","first-page":"2299","DOI":"10.1109\/TASL.2007.904233","volume":"15","author":"M. Radfar","year":"2007","unstructured":"M. Radfar, R. Dansereau, Single-channel speech separation using soft mask filtering. IEEE Trans. Audio Speech Lang. Process. 15(8), 2299\u20132310 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9656_CR36","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.21437\/Eurospeech.2003-345","volume-title":"Proc. ISCA European Conference Speech Communication and Technology (EuroSeech)","author":"S. Roweis","year":"2003","unstructured":"S. Roweis, Factorial models and refiltering for speech separation and denoising, in Proc. ISCA European Conference Speech Communication and Technology (EuroSeech) (2003), pp. 1009\u20131012"},{"issue":"1","key":"9656_CR37","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1121\/1.3132525","volume":"126","author":"A. Shapiro","year":"2009","unstructured":"A. Shapiro, C. Wang, A versatile pitch tracking algorithm: from human speech to killer whale vocalizations. J. Acoust. Soc. Am. 126(1), 451\u2013459 (2009)","journal-title":"J. Acoust. Soc. Am."},{"issue":"2","key":"9656_CR38","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1121\/1.425118","volume":"105","author":"H. Strube","year":"1999","unstructured":"H. Strube, H. Wilmers, Noise reduction for speech signals by operation on the modulation frequency spectrum. J. Acoust. Soc. Am. 105(2), 1092 (1999)","journal-title":"J. Acoust. Soc. Am."},{"issue":"2","key":"9656_CR39","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 Lang. Process. 19(2), 242\u2013255 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"9656_CR40","first-page":"2614","volume-title":"Proc. of the International Conference on Spoken Lang. Process. (ICSLP)","author":"M. Schmidt","year":"2006","unstructured":"M. Schmidt, R. Olsson, Single-channel speech separation using sparse non-negative matrix factorization, in Proc. of the International Conference on Spoken Lang. Process. (ICSLP) (2006), pp. 2614\u20132617"},{"key":"9656_CR41","first-page":"261","volume-title":"Proceedings of the International Conference on Acoust., Speech, and Signal Process (ICASSP)","author":"S. Schimmel","year":"2006","unstructured":"S. Schimmel, K. Fitz, L. Atlas, Frequency reassignment for coherent modulation filtering, in Proceedings of the International Conference on Acoust., Speech, and Signal Process (ICASSP) (2006), pp. 261\u2013264"},{"issue":"3","key":"9656_CR42","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1109\/TSA.2003.811542","volume":"11","author":"J. Tchorz","year":"2001","unstructured":"J. Tchorz, B. Kollmeier, SNR estimation based on amplitude modulation analysis with applications to noise suppression. IEEE Trans. Speech Audio Process. 11(3), 184\u2013192 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"9656_CR43","first-page":"1143","volume-title":"Proceedings of the International Conference on Acoust., Speech, and Signal Process (ICASSP)","author":"C. Wang","year":"2000","unstructured":"C. Wang, S. Seneff, Robust pitch tracking for prosodic modeling in telephone speech, in Proceedings of the International Conference on Acoust., Speech, and Signal Process (ICASSP), Istanbul, Turkey (2000), pp. 1143\u20131146"},{"key":"9656_CR44","volume-title":"Computational Auditory Scene Analysis: Principles, Algorithms, and Applications","year":"2006","unstructured":"D. Wang, G. Brown (eds.), Computational Auditory Scene Analysis: Principles, Algorithms, and Applications (Wiley\/IEEE Press, New York, 2006)"},{"issue":"4","key":"9656_CR45","doi-asserted-by":"crossref","first-page":"2303","DOI":"10.1121\/1.2967865","volume":"125","author":"D. Wang","year":"2008","unstructured":"D. Wang, U. Kjems, M. Pedersen, J. Boldt, Speech perception of noise with binary gains. J. Acoust. Soc. Am. 125(4), 2303\u20132307 (2008)","journal-title":"J. Acoust. Soc. Am."},{"key":"9656_CR46","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/0-387-22794-6_12","volume-title":"Speech Separation by Humans and Machines","author":"D. Wang","year":"2005","unstructured":"D. Wang, On ideal binary masks as the computational goal of auditory scene analysis, in Speech Separation by Humans and Machines, ed. by P. Divenyi (Kluwer Academic, Boston, 2005), pp. 181\u2013197"},{"key":"9656_CR47","unstructured":"M. Weintraub, A theory and computational model of auditory monaural sound separation. Ph.D. Dissertation, Stanford University, CA, USA (1985)"},{"key":"9656_CR48","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.csl.2008.03.003","volume":"24","author":"R. Weiss","year":"2010","unstructured":"R. Weiss, D. Ellis, Speech separation using speaker-adapted eigenvoice speech models. Comput. Speech Lang. 24, 16\u201329 (2010)","journal-title":"Comput. Speech Lang."},{"key":"9656_CR49","first-page":"0511","volume-title":"Proc. of the International Conference on Spoken Lang. Process. (ICSLP)","author":"D. Yang","year":"1998","unstructured":"D. Yang, G. Meyer, W. Ainsworth, Vowel separation using the reassigned amplitude-modulation spectrum, in Proc. of the International Conference on Spoken Lang. Process. (ICSLP) (1998), p. 0511"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-013-9656-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-013-9656-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-013-9656-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T20:38:56Z","timestamp":1688503136000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-013-9656-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,25]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["9656"],"URL":"https:\/\/doi.org\/10.1007\/s00034-013-9656-6","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,25]]}}}