{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:11:18Z","timestamp":1784301078398,"version":"3.55.0"},"reference-count":56,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2014,12,18]],"date-time":"2014-12-18T00:00:00Z","timestamp":1418860800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1003985","type":"journal-article","created":{"date-parts":[[2014,12,19]],"date-time":"2014-12-19T08:08:05Z","timestamp":1418976485000},"page":"e1003985","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":77,"title":["Segregating Complex Sound Sources through Temporal Coherence"],"prefix":"10.1371","volume":"10","author":[{"given":"Lakshmi","family":"Krishnan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mounya","family":"Elhilali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihab","family":"Shamma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2014,12,18]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"Bregman AS (1990) Auditory Scene Analysis: The Perceptual Organization of Sound. MIT Press.","DOI":"10.7551\/mitpress\/1486.001.0001"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1121\/1.1907229","article-title":"Some experiments on the recognition of speech, with one and with two ears","volume":"25","author":"EC Cherry","year":"1953","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1037\/0735-7036.122.3.235","article-title":"The \u201cCocktail party problem\u201d: What is it? how can it be solved? and why should animal behaviorists study it?","volume":"122","author":"MA Bee","year":"2008","journal-title":"Journal of comparative psychology"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"3394","DOI":"10.1121\/1.1624067","article-title":"Modulation spectra of natural sounds and ethological theories of auditory processing","volume":"114","author":"NC Singh","year":"2003","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1167\/9.1.32","article-title":"The influence of clutter on real-world scene search: Evidence from search efficiency and eye movements","volume":"9","author":"JM Henderson","year":"2009","journal-title":"Journal of Vision"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"R249","DOI":"10.1016\/j.cub.2013.02.016","article-title":"Sensory biology: Listening in the dark for echoes from silent and stationary prey","volume":"23","author":"G Jones","year":"2013","journal-title":"Current Biology"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"Kristjansson T, Hershey J, Olsen P, Rennie S, Gopinath R (2006) Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system. In: in ICSLP. pp. 97\u2013100.","DOI":"10.21437\/Interspeech.2006-25"},{"key":"ref8","unstructured":"Comon P, Jutten C (2010) Handbook of Blind Source Separation: Independent Component Analysis and Applications. Academic Press."},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Smaragdis P (2004) Non-negative matrix factor deconvolution; extraction of multiple sound sources from monophonic inputs. In: PuntonetCG, PrietoA, editors, Independent Component Analysis and Blind Signal Separation, Springer Berlin Heidelberg, number 3195 in Lecture Notes in Computer Science. pp. 494\u2013499.","DOI":"10.1007\/978-3-540-30110-3_63"},{"key":"ref10","unstructured":"Ellis DPW (2006) Model-based scene analysis. In: Computational Auditory Scene Analysis: Principles, Algorithms, and Applications, Wiley\/IEEE Press. pp. 115\u2013146."},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"King B, Atlas L (2010) Single-channel source separation using simplified-training complex matrix factorization. In: 2010 IEEE International Conference on Acoustics Speech and Signal Processing. pp. 4206\u20134209.","DOI":"10.1109\/ICASSP.2010.5495699"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.csl.2009.02.006","article-title":"Monaural speech separation and recognition challenge","volume":"24","author":"M Cooke","year":"2010","journal-title":"Computer Speech & Language"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"Brown GJ (2010) Physiological models of auditory scene analysis. In: Meddis R, opez-Poveda L E A, Fay R R, Popper A N, editors, Computational Models of the Auditory System, Springer US, number 35 in Springer Handbook of Auditory Research. pp. 203\u2013236.","DOI":"10.1007\/978-1-4419-5934-8_8"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1016\/j.specom.2009.02.003","article-title":"Sequential organization of speech in computational auditory scene analysis","volume":"51","author":"Y Shao","year":"2009","journal-title":"Speech Communication"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"155","DOI":"10.2307\/40285527","article-title":"Stream segregation and peripheral channeling","volume":"9","author":"WM Hartmann","year":"1991","journal-title":"Music Perception: An Interdisciplinary Journal"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1121\/1.415414","article-title":"Computer simulation of auditory stream segregation in alternating-tone sequences","volume":"99","author":"MW Beauvois","year":"1996","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1121\/1.418176","article-title":"A model of auditory streaming","volume":"101","author":"SL McCabe","year":"1997","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/TASL.2010.2047419","article-title":"Source-filter-based single-channel speech separation using pitch information","volume":"19","author":"M Stark","year":"2011","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"G Hu","year":"2010","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"4323","DOI":"10.1109\/TSP.2009.2025107","article-title":"Time-frequency coherent modulation filtering of nonstationary signals","volume":"57","author":"P Clark","year":"2009","journal-title":"IEEE Transactions on Signal Processing"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Mill R, Bohm T, Bendixen A, Winkler I, Denham S (2011) CHAINS: competition and cooperation between fragmentary event predictors in a model of auditory scene analysis. In: 2011 45th Annual Conference on Information Sciences and Systems (CISS). pp. 1\u20136.","DOI":"10.1109\/CISS.2011.5766095"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"942","DOI":"10.1098\/rstb.2011.0368","article-title":"The initial phase of auditory and visual scene analysis","volume":"367","author":"JM Hupe","year":"2012","journal-title":"Philosophical transactions of the Royal Society of London Series B, Biological sciences"},{"key":"ref23","first-page":"95119","article-title":"The correlation theory of brain function","volume":"2","author":"C Von Der Malsburg","year":"1994","journal-title":"Models of neural networks"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1162\/neco.1990.2.1.94","article-title":"Pattern segmentation in associative memory","volume":"2","author":"D Wang","year":"1990","journal-title":"Neural Computation"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.tins.2010.11.002","article-title":"Temporal coherence and attention in auditory scene analysis","volume":"34","author":"SA Shamma","year":"2011","journal-title":"Trends in Neurosciences"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.neuron.2008.12.005","article-title":"Temporal coherence in the perceptual organization and cortical representation of auditory scenes","volume":"61","author":"M Elhilali","year":"2009","journal-title":"Neuron"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1037\/a0017601","article-title":"Auditory stream segregation and the perception of across-frequency synchrony","volume":"36","author":"C Micheyl","year":"2010","journal-title":"Journal of experimental psychology Human perception and performance"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"Teki S, Chait M, Kumar S, Shamma S, Griffiths TD (2013) Segregation of complex acoustic scenes based on temporal coherence. eLife 2.","DOI":"10.7554\/eLife.00699"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1207\/s15516709cog2003_3","article-title":"Primitive auditory segregation based on oscillatory correlation","volume":"20","author":"D Wang","year":"1996","journal-title":"Cognitive Science"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1037\/0033-295X.106.1.119","article-title":"The dynamics of attending: How people track time-varying events","volume":"106","author":"EW Large","year":"1999","journal-title":"Psychological Review"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/72.761727","article-title":"Separation of speech from interfering sounds based on oscillatory correlation","volume":"10","author":"D Wang","year":"1999","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1109\/TNN.2004.832710","article-title":"A computational model of auditory selective attention","volume":"15","author":"S Wrigley","year":"2004","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.physd.2005.09.014","article-title":"Integration and segregation in auditory streaming","volume":"212","author":"F Almonte","year":"2005","journal-title":"Physica D: Nonlinear Phenomena"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1121\/1.1945807","article-title":"Multiresolution spectrotemporal analysis of complex sounds","volume":"118","author":"T Chi","year":"2005","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"MA Kramer","year":"1991","journal-title":"AIChE Journal"},{"key":"ref36","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10). pp. 807\u2013814."},{"key":"ref37","doi-asserted-by":"crossref","first-page":"2631","DOI":"10.1121\/1.428649","article-title":"The case of the missing pitch templates: how harmonic templates emerge in the early auditory system","volume":"107","author":"S Shamma","year":"2000","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1038\/nature03867","article-title":"The neuronal representation of pitch in primate auditory cortex","volume":"436","author":"D Bendor","year":"2005","journal-title":"Nature"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1152\/jn.1988.60.6.1799","article-title":"Periodicity coding in the inferior colliculus of the cat. i. neuronal mechanisms","volume":"60","author":"G Langner","year":"1988","journal-title":"J Neurophysiol"},{"key":"ref40","doi-asserted-by":"crossref","unstructured":"Viemeister NF, Stellmack MA, Byrne AJ (2005) The role of temporal structure in envelope processing. In: Pressnitzer D, Cheveign A d, McAdams S, Collet L, editors, Auditory Signal Processing, Springer New York. pp. 220\u2013228.","DOI":"10.1007\/0-387-27045-0_27"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"e1000436","DOI":"10.1371\/journal.pcbi.1000436","article-title":"The natural statistics of audiovisual speech","volume":"5","author":"C Chandrasekaran","year":"2009","journal-title":"PLoS Comput Biol"},{"key":"ref42","unstructured":"Lee DD, Seung HS (2000) Algorithms for non-negative matrix factorization. In: Advances in neural information processing systems. pp. 556\u2013562."},{"key":"ref43","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/BF00337113","article-title":"A neural cocktail-party processor","volume":"54","author":"C von der Malsburg","year":"1986","journal-title":"Biological cybernetics"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"Schimmel S, Atlas L, Nie K (2007) Feasibility of single channel speaker separation based on modulation frequency analysis. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. volume 4, pp. 605\u2013608.","DOI":"10.1109\/ICASSP.2007.366985"},{"key":"ref45","unstructured":"Moore BCJ (2003) An introduction to the psychology of hearing. Amsterdam; Boston: Academic Press."},{"key":"ref46","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.heares.2009.09.012","article-title":"Pitch, harmonicity and concurrent sound segregation: psychoacoustical and neurophysiological findings","volume":"266","author":"C Micheyl","year":"2010","journal-title":"Hearing research"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1121\/1.4845675","article-title":"Effects of tonotopicity, adaptation, modulation tuning, and temporal coherence in primitive auditory stream segregationa)","volume":"135","author":"SK Christiansen","year":"2014","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1007\/978-1-4614-1590-9_59","article-title":"Temporal coherence and the streaming of complex sounds","volume":"787","author":"S Shamma","year":"2013","journal-title":"Advances in experimental medicine and biology"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"Sejnowski TJ, Tesauro G (1989) The hebb rule for synaptic plasticity: algorithms and implementations. In: Neural models of plasticity: Experimental and theoretical approaches, Academic Press, New York. pp. 94\u2013103.","DOI":"10.1016\/B978-0-12-148955-7.50010-2"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1038\/81453","article-title":"Synaptic plasticity: taming the beast","volume":"3","author":"LF Abbott","year":"2000","journal-title":"Nature Neuroscience"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"3751","DOI":"10.1121\/1.3001672","article-title":"A cocktail party with a cortical twist: How cortical mechanisms contribute to sound segregation","volume":"124","author":"M Elhilali","year":"2008","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref52","unstructured":"Duda RO, Hart PE (1973) Pattern classification and scene analysis. New York: Wiley."},{"key":"ref53","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1177\/1534582305276839","article-title":"The role of temporal structure in human vision","volume":"4","author":"R Blake","year":"2005","journal-title":"Behavioral and Cognitive Neuroscience Reviews"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1038\/1151","article-title":"Visual features that vary together over time group together over space","volume":"1","author":"D Alais","year":"1998","journal-title":"Nature neuroscience"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1109\/89.294356","article-title":"Self-normalization and noise-robustness in early auditory representations","volume":"2","author":"K Wang","year":"1994","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref56","unstructured":"Schmidt M (2012). minFunc - unconstrained differentiable multivariate optimization in matlab. URL <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.di.ens.fr\/mschmidt\/Software\/minFunc.html\" xlink:type=\"simple\">http:\/\/www.di.ens.fr\/mschmidt\/Software\/minFunc.html<\/ext-link>."}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,24]],"date-time":"2022-04-24T16:31:57Z","timestamp":1650817917000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003985"}},"subtitle":[],"editor":[{"given":"Michael","family":"Lewicki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2014,12,18]]},"references-count":56,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2014,12,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1003985","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12,18]]}}}