{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T10:50:32Z","timestamp":1767178232433,"version":"build-2238731810"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1006711","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000}}],"reference-count":145,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T00:00:00Z","timestamp":1548115200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["R01HL133043"],"award-info":[{"award-number":["R01HL133043"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141612045"],"award-info":[{"award-number":["N000141612045"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U01AG058532"],"award-info":[{"award-number":["U01AG058532"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141712736"],"award-info":[{"award-number":["N000141712736"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1006711","type":"journal-article","created":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T16:59:52Z","timestamp":1548176392000},"page":"e1006711","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":19,"title":["A Gestalt inference model for auditory scene segregation"],"prefix":"10.1371","volume":"15","author":[{"given":"Debmalya","family":"Chakrabarty","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2597-738X","authenticated-orcid":true,"given":"Mounya","family":"Elhilali","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2019,1,22]]},"reference":[{"key":"ref1","first-page":"199","article-title":"Scene analysis in the natural environment","volume":"5","author":"MS Lewicki","year":"2014","journal-title":"Frontiers in psychology"},{"key":"ref2","first-page":"120","article-title":"Sensation and Perception","author":"JM Wolfe","year":"2015"},{"issue":"9","key":"ref3","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/S1364-6613(97)01097-8","article-title":"Auditory grouping","volume":"1","author":"CJ Darwin","year":"1997","journal-title":"Trends in Cognitive Sciences"},{"issue":"6","key":"ref4","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1037\/a0029333","article-title":"A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure\u2013ground organization","volume":"138","author":"J Wagemans","year":"2012","journal-title":"Psychological Bulletin"},{"issue":"9","key":"ref5","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1162\/0899766054322964","article-title":"The cocktail party problem","volume":"17","author":"S Haykin","year":"2005","journal-title":"Neural computation"},{"key":"ref6","article-title":"Pattern Classification","author":"RO Duda","year":"2000"},{"key":"ref7","article-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1486.001.0001","article-title":"Auditory scene analysis: the perceptual organization of sound","author":"AS Bregman","year":"1990"},{"issue":"11","key":"ref9","first-page":"887","article-title":"What is an auditory object?","volume":"5","author":"TD Griffiths","year":"2004","journal-title":"Nature neuroscreviews"},{"issue":"18","key":"ref10","first-page":"2991","article-title":"Sound classification in hearing aids inspired by auditory scene analysis","volume":"2005","author":"M Buchler","year":"2005","journal-title":"Eurasip Journal on Applied Signal Processing"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Ellis DPW, Weiss RJ. Model-based monaural source separation using vector-quantized phase-vocoder representation. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. vol. 5; 2006. p. 957\u2013960.","DOI":"10.1109\/ICASSP.2006.1661436"},{"issue":"7-8","key":"ref12","first-page":"1365","article-title":"A Maximum Likelihood Approach to Single-channel Source Separation","volume":"4","author":"GJ Jang","year":"2003","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"ref13","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/S0003-682X(97)00105-9","article-title":"Automatic classification of environmental noise events by hidden Markov models","volume":"54","author":"C Couvreur","year":"1998","journal-title":"Applied Acoustics"},{"issue":"4","key":"ref14","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.neunet.2003.10.002","article-title":"ARTSTREAM: a neural network model of auditory scene analysis and source segregation","volume":"17","author":"S Grossberg","year":"2004","journal-title":"Neural networks"},{"issue":"12","key":"ref15","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.tics.2009.09.003","article-title":"Modeling the auditory scene: predictive regularity representations and perceptual objects","volume":"13","author":"I Winkler","year":"2009","journal-title":"Trends in cognitive sciences"},{"issue":"3","key":"ref16","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1109\/TASL.2006.889788","article-title":"Combined estimation of spectral envelopes and sound source direction of concurrent voices by multidimensional statistical filtering","volume":"15","author":"J Nix","year":"2007","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"ref17","first-page":"111","article-title":"The auditory system at the cocktail party","author":"M Elhilali","year":"2017"},{"issue":"11","key":"ref18","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1038\/14819","article-title":"Hierarchical models of object recognition in cortex","volume":"2","author":"M Riesenhuber","year":"1999","journal-title":"Nature neuroscience"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"Bo L, Ren X, Fox D. Kernel descriptors for visual recognition. In: NIPS; 2010. p. 1\u20139.","DOI":"10.1109\/IROS.2011.6095119"},{"key":"ref20","first-page":"1","article-title":"Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification","author":"Lj Li","year":"2010","journal-title":"Nips"},{"issue":"4","key":"ref21","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation Applied to Handwritten Zip Code Recognition","volume":"1","author":"Y LeCun","year":"1989","journal-title":"Neural Computation"},{"key":"ref22","first-page":"49","article-title":"Deep Learning with Denoising Autoencoders","volume":"27","author":"P Vincent","year":"2008","journal-title":"Journal of Machine Learning"},{"issue":"3","key":"ref23","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.cviu.2008.08.006","article-title":"Object tracking using SIFT features and mean shift","volume":"113","author":"H Zhou","year":"2009","journal-title":"Computer Vision and Image Understanding"},{"issue":"5","key":"ref24","doi-asserted-by":"crossref","DOI":"10.1167\/11.5.5","article-title":"Eye guidance in natural vision: Reinterpreting salience","volume":"11","author":"BW Tatler","year":"2011","journal-title":"Journal of Vision"},{"key":"ref25","first-page":"490","article-title":"Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)","volume":"vol. 3954","author":"E Nowak","year":"2006"},{"key":"ref26","unstructured":"Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. International Conference on Learning Representations (ICRL). 2015; p. 1\u201314."},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Lee H, Grosse R, Ranganath R, Ng AY. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning. ACM; 2009. p. 1\u20138.","DOI":"10.1145\/1553374.1553453"},{"key":"ref28","unstructured":"Radford A, Metz L, Chintala S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv. 2015; p. 1\u201315."},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"Coates A, Carpenter B, Case C, Satheesh S, Suresh B, Wang T, et al. Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning. 2011 International Conference on Document Analysis and Recognition. 2011; p. 440\u2013445.","DOI":"10.1109\/ICDAR.2011.95"},{"issue":"7","key":"ref30","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A Fast Learning Algorithm for Deep Belief Nets","volume":"18","author":"GE Hinton","year":"2006","journal-title":"Neural Computation"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"Taylor GW, Sigal L, Fleet DJ, Hinton GE. Dynamical binary latent variable models for 3D human pose tracking. Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. 2010; p. 631\u2013638.","DOI":"10.1109\/CVPR.2010.5540157"},{"issue":"2","key":"ref32","doi-asserted-by":"crossref","first-page":"155","DOI":"10.2307\/40285527","article-title":"Stream segregation and peripheral channeling","volume":"9","author":"W Hartmann","year":"1991","journal-title":"Music Perception"},{"issue":"3","key":"ref33","first-page":"517","article-title":"A computer model of auditory stream segregation","volume":"43","author":"MW Beauvois","year":"1991","journal-title":"Human experimental psychology"},{"issue":"3","key":"ref34","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":"Journal of the Acoustical Society of America"},{"issue":"1","key":"ref35","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s11571-007-9035-8","article-title":"An oscillatory correlation model of auditory streaming","volume":"2","author":"D Wang","year":"2008","journal-title":"Cognitive neurodynamics"},{"issue":"8","key":"ref36","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"},{"issue":"3","key":"ref37","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":"DL Wang","year":"1999","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"12","key":"ref38","doi-asserted-by":"crossref","first-page":"e1003985","DOI":"10.1371\/journal.pcbi.1003985","article-title":"Segregating complex sound sources through temporal coherence","volume":"10","author":"L Krishnan","year":"2014","journal-title":"PLoS computational biology"},{"issue":"2","key":"ref39","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"},{"issue":"SEP","key":"ref40","article-title":"Sound stream segregation: A neuromorphic approach to solve the \u201ccocktail party problem\u201d in real-time","volume":"9","author":"CS Thakur","year":"2015","journal-title":"Frontiers in Neuroscience"},{"key":"ref41","unstructured":"Lee H, Pham P, Largman Y, Ng AY. Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in neural information processing systems; 2009. p. 1096\u20131104."},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"Simpson AJR, Roma G, Plumbley MD. Deep karaoke: Extracting vocals from musical mixtures using a convolutional deep neural network. In: Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics). vol. 9237; 2015. p. 429\u2013436.","DOI":"10.1007\/978-3-319-22482-4_50"},{"issue":"6","key":"ref43","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.1109\/TASLP.2017.2690563","article-title":"Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging","volume":"25","author":"Y Xu","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"Sainath TN, Kanevsky D, Iyengar G. Unsupervised audio segmentation using extended Baum-Welch transformations. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing\u2014Proceedings. vol. 1; 2007. p. 209\u2013212.","DOI":"10.1109\/ICASSP.2007.366653"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"Hershey JR, Chen Z, Le Roux J, Watanabe S. Deep clustering: Discriminative embeddings for segmentation and separation. In: Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE; 2016. p. 31\u201335.","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref46","article-title":"Speaker-Independent Speech Separation with Deep Attractor Network","author":"Y Luo","year":"2018","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref47","first-page":"387","article-title":"Hearing","volume":"vol. 6","author":"CJ Darwin","year":"1995"},{"issue":"29","key":"ref48","doi-asserted-by":"crossref","first-page":"12223","DOI":"10.1073\/pnas.0704641104","article-title":"A sound element gets lost in perceptual competition","volume":"104","author":"B Shinn-Cunningham","year":"2007","journal-title":"ProcNatAcadSci"},{"issue":"8","key":"ref49","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.3758\/BF03193643","article-title":"Simultaneous Grouping and Auditory Continuity","volume":"67","author":"CJ Darwin","year":"2005","journal-title":"Perception & Psychoacoustics"},{"issue":"2 I","key":"ref50","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1121\/1.413513","article-title":"Grouping in pitch perception: Evidence for sequential constraints","volume":"98","author":"CJ Darwin","year":"1995","journal-title":"Journal of the Acoustical Society of America"},{"key":"ref51","first-page":"320","article-title":"Factors influencing sequential stream segregation","volume":"88","author":"BCJ Moore","year":"2002","journal-title":"Acta Acustica"},{"issue":"2","key":"ref52","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1162\/089892904322984607","article-title":"Grouping of Sequential Sounds\u2014An Event-Related Potential Study Comparing Musicians and Nonmusicians","volume":"16","author":"TL van Zuijen","year":"2004","journal-title":"Journal of Cognitive Neuroscience"},{"issue":"2","key":"ref53","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1121\/1.2407738","article-title":"Binaural interference and auditory grouping","volume":"121","author":"V Best","year":"2007","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref54","first-page":"81","article-title":"The perceptual grouping of musical Sequences: Pitch and timing as competing cues","volume":"11","author":"K Hamaoui","year":"2011","journal-title":"Proceedings of the 11th International Conference on Music Perception and Cognition"},{"issue":"3","key":"ref55","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/TAMD.2010.2072150","article-title":"Top-down connections in self-organizing hebbian networks: Topographic class grouping","volume":"2","author":"M Luciw","year":"2010","journal-title":"IEEE Transactions on Autonomous Mental Development"},{"issue":"2","key":"ref56","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/089976606775093891","article-title":"A simple Hebbian\/anti-Hebbian network learns the sparse, independent components of natural images","volume":"18","author":"MS Falconbridge","year":"2006","journal-title":"Neural computation"},{"issue":"2","key":"ref57","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1162\/089976603762552988","article-title":"Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network","volume":"15","author":"X Xie","year":"2003","journal-title":"Neural Computation"},{"issue":"10","key":"ref58","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/j.tics.2004.08.008","article-title":"How the brain separates sounds","volume":"8","author":"RP Carlyon","year":"2004","journal-title":"Trends in cognitive sciences"},{"issue":"1","key":"ref59","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1037\/0735-7036.111.1.3","article-title":"Auditory scene analysis by songbirds: stream segregation of birdsong by European starlings (Sturnus vulgaris)","volume":"111","author":"SH Hulse","year":"1997","journal-title":"Journal of computational psychology"},{"issue":"1-2","key":"ref60","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0378-5955(98)00058-6","article-title":"Auditory stream segregation in goldfish (Carassius auratus)","volume":"120","author":"RR Fay","year":"1998","journal-title":"Hearing research"},{"issue":"3","key":"ref61","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/S0010-0277(01)00161-5","article-title":"Auditory stream segregation in Japanese monkeys","volume":"82","author":"A Izumi","year":"2002","journal-title":"Cognition"},{"issue":"2","key":"ref62","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1590\/S0001-37652004000200015","article-title":"Penguins and their noisy world","volume":"76","author":"T Aubin","year":"2004","journal-title":"Annals of the Brazilian Academy of Sciences"},{"issue":"6","key":"ref63","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1152\/jn.91333.2008","article-title":"Auditory streaming of amplitude-modulated sounds in the songbird forebrain","volume":"101","author":"N Itatani","year":"2009","journal-title":"Journal of neurophysiology"},{"issue":"3","key":"ref64","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":"ref65","doi-asserted-by":"crossref","first-page":"13900","DOI":"10.1038\/ncomms13900","article-title":"Temporal coherence structure rapidly shapes neuronal interactions","volume":"8","author":"K Lu","year":"2017","journal-title":"Nature communications"},{"issue":"2","key":"ref66","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/18.119739","article-title":"Auditory representations of acoustic signals","volume":"38","author":"X Yang","year":"1992","journal-title":"IEEE Trans Inf Theory"},{"key":"ref67","first-page":"599","article-title":"Neural Networks: Tricks of the Trade","volume":"vol. 7700","author":"GE Hinton","year":"2012"},{"key":"ref68","article-title":"Deep Learning","author":"I Goodfellow","year":"2016"},{"issue":"8","key":"ref69","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training Products of Experts by Minimizing Contrastive Divergence","volume":"14","author":"GE Hinton","year":"2002","journal-title":"Neural Computation"},{"key":"ref70","first-page":"33","article-title":"Handbook of Modern Techniques in Auditory Cortex","author":"M Elhilali","year":"2013"},{"key":"ref71","doi-asserted-by":"crossref","unstructured":"Taylor GW, Hinton GE. Factored conditional restricted Boltzmann Machines for modeling motion style. In: Proceedings of the 26th Annual International Conference on Machine Learning\u2014ICML\u201909; 2009. p. 1\u20138.","DOI":"10.1145\/1553374.1553505"},{"key":"ref72","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"},{"issue":"8","key":"ref73","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural networks and physical systems with emergent collective computational abilities","volume":"79","author":"JJ Hopfield","year":"1982","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"6","key":"ref74","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1016\/S0893-6080(99)00038-6","article-title":"The basins of attraction of a new Hopfield learning rule","volume":"12","author":"AJ Storkey","year":"1999","journal-title":"Neural Networks"},{"key":"ref75","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":"106","author":"N Singh","year":"2003","journal-title":"Journal of the Acoustical Society of America"},{"issue":"3","key":"ref76","doi-asserted-by":"crossref","first-page":"e1000302","DOI":"10.1371\/journal.pcbi.1000302","article-title":"The modulation transfer function for speech intelligibility","volume":"5","author":"TM Elliott","year":"2009","journal-title":"PLoS computational biology"},{"key":"ref77","doi-asserted-by":"crossref","unstructured":"Shamma SA, Versnel H, Kowalski N. Ripple Analysis in Ferret Primary Auditory Cortex. I. Response Characteristics of Single Units to Sinusoidally Rippled Spectra. Institute for Systems Research Technical Reports. 1994.","DOI":"10.21236\/ADA452778"},{"key":"ref78","first-page":"39","article-title":"Spectral envelope coding in cat primary auditory cortex: Properties of ripple transfer functions","volume":"1","author":"C Schreiner","year":"1995","journal-title":"Journal of Auditory Neuroscience"},{"issue":"34","key":"ref79","doi-asserted-by":"crossref","first-page":"14611","DOI":"10.1073\/pnas.0907682106","article-title":"Spectro-temporal modulation transfer function of single voxels in the human auditory cortex measured with high-resolution fMRI","volume":"106","author":"M Schonwiesner","year":"2009","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"issue":"3","key":"ref80","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1152\/jn.2001.85.3.1220","article-title":"Spectro-temporal response field characterization with dynamic ripples in ferret primary auditory cortex","volume":"85","author":"DA Depireux","year":"2001","journal-title":"Journal of neurophysiology"},{"issue":"1","key":"ref81","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1152\/jn.00395.2001","article-title":"Spectrotemporal receptive fields in the lemniscal auditory thalamus and cortex","volume":"87","author":"LM Miller","year":"2002","journal-title":"Journal of neurophysiology"},{"issue":"37","key":"ref82","doi-asserted-by":"crossref","first-page":"11489","DOI":"10.1523\/JNEUROSCI.23-37-11489.2003","article-title":"Naturalistic auditory contrast improves spectrotemporal coding in the cat inferior colliculus","volume":"23","author":"MA Escabi","year":"2003","journal-title":"Journal of Neuroscience"},{"issue":"5","key":"ref83","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1016\/j.conb.2011.05.027","article-title":"Hierarchical representations in the auditory cortex","volume":"21","author":"TO Sharpee","year":"2011","journal-title":"Current opinion in neurobiology"},{"issue":"3","key":"ref84","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1037\/0096-1523.1.3.263","article-title":"Auditory segregation: stream or streams?","volume":"1","author":"AS Bregman","year":"1975","journal-title":"Journal of Experimental Psychology-Human Perception and Performance"},{"issue":"4","key":"ref85","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1121\/1.381388","article-title":"Minimun differences of level and frequency for perceptual fission of tone sequences ABAB","volume":"61","author":"LP van Noorden","year":"1977","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"6","key":"ref86","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1037\/a0032241","article-title":"Auditory stream segregation for alternating and synchronous tones","volume":"39","author":"C Micheyl","year":"2013","journal-title":"Journal of experimental psychologyHuman perception and performance"},{"key":"ref87","article-title":"Signal detection theory and psychophysics","volume":"vol. 1","author":"DM Green","year":"1966"},{"issue":"5","key":"ref88","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1121\/1.380764","article-title":"A probe-signal investigation of uncertain-frequency detection","volume":"58","author":"NA Macmillan","year":"1975","journal-title":"Journal of the Acoustical Society of America"},{"issue":"5","key":"ref89","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0166-2236(00)01790-2","article-title":"\u201cPrimitive intelligence\u201d in the auditory cortex","volume":"24","author":"R Naatanen","year":"2001","journal-title":"Trends in neurosciences"},{"issue":"1","key":"ref90","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neuron.2005.08.039","article-title":"Perceptual organization of tone sequences in the auditory cortex of awake macaques","volume":"48","author":"C Micheyl","year":"2005","journal-title":"Neuron"},{"key":"ref91","doi-asserted-by":"crossref","first-page":"148","DOI":"10.2741\/2666","article-title":"The auditory organization of complex sounds","volume":"13","author":"V Ciocca","year":"2008","journal-title":"Frontiers in bioscience: a journal and virtual library"},{"issue":"3","key":"ref92","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1121\/1.1452740","article-title":"Auditory stream segregation on the basis of amplitude-modulation rate","volume":"111","author":"N Grimault","year":"2002","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"3","key":"ref93","doi-asserted-by":"crossref","first-page":"EL188","DOI":"10.1121\/1.4789866","article-title":"Temporal coherence versus harmonicity in auditory stream formation","volume":"133","author":"C Micheyl","year":"2013","journal-title":"Journal of the Acoustical Society of America"},{"issue":"2","key":"ref94","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1121\/1.428288","article-title":"A Speech Corpus for Multitalker Communications Research","volume":"107","author":"RS Bolia","year":"2000","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"5","key":"ref95","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1121\/1.1357812","article-title":"Evaluation of speech intelligibility with the coordinate response measure","volume":"109","author":"DS Brungart","year":"2001","journal-title":"Journal of the Acoustical Society of America"},{"issue":"2","key":"ref96","doi-asserted-by":"crossref","first-page":"EL177","DOI":"10.1121\/1.3678680","article-title":"Psychometric properties of the coordinate response measure corpus with various types of background interference","volume":"131","author":"DA Eddins","year":"2012","journal-title":"The Journal of the Acoustical Society of America"},{"key":"ref97","doi-asserted-by":"crossref","unstructured":"Elhilali M, Shamma S. Information-bearing components of speech intelligibility under babble-noise and bandlimiting distortions. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2008. p. 4205\u20134208.","DOI":"10.1109\/ICASSP.2008.4518582"},{"key":"ref98","article-title":"An Introduction to the Physiology of Hearing","author":"JO Pickles","year":"1988"},{"issue":"7","key":"ref99","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1038\/nn0705-851","article-title":"Auditory cortex cheers the overture and listens through the finale","volume":"8","author":"JC Middlebrooks","year":"2005","journal-title":"Nature neuroscience"},{"issue":"11","key":"ref100","doi-asserted-by":"crossref","first-page":"e1000211","DOI":"10.1371\/journal.pcbi.1000211","article-title":"Hierarchical models in the brain","volume":"4","author":"KJ Friston","year":"2008","journal-title":"PLoS computational biology"},{"issue":"3","key":"ref101","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.neuron.2010.01.020","article-title":"Nonoverlapping Sets of Synapses Drive On Responses and Off Responses in Auditory Cortex","volume":"65","author":"B Scholl","year":"2010","journal-title":"Neuron"},{"key":"ref102","doi-asserted-by":"crossref","DOI":"10.3389\/fnsys.2013.00114","article-title":"The harmonic organization of auditory cortex","volume":"7","author":"X Wang","year":"2013","journal-title":"Frontiers in Systems Neuroscience"},{"issue":"4","key":"ref103","doi-asserted-by":"crossref","first-page":"1928","DOI":"10.1152\/jn.00469.2007","article-title":"Responses of auditory cortex to complex stimuli: functional organization revealed using intrinsic optical signals","volume":"99","author":"I Nelken","year":"2008","journal-title":"Journal of neurophysiology"},{"issue":"10","key":"ref104","doi-asserted-by":"crossref","first-page":"4114","DOI":"10.1523\/JNEUROSCI.22-10-04114.2002","article-title":"Nonlinear spectrotemporal sound analysis by neurons in the auditory midbrain","volume":"22","author":"MA Escabi","year":"2002","journal-title":"Journal of Neuroscience"},{"issue":"10","key":"ref105","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1038\/nn1536","article-title":"Tuning for spectro-temporal modulations as a mechanism for auditory discrimination of natural sounds","volume":"8","author":"SMN Woolley","year":"2005","journal-title":"Nature Neurosci"},{"issue":"5","key":"ref106","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/s00422-003-0445-3","article-title":"Primary auditory cortex of cats: feature detection or something else?","volume":"89","author":"I Nelken","year":"2003","journal-title":"Biological Cybernetics"},{"key":"ref107","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/S0074-7742(05)70007-6","article-title":"Neural mechanisms for spectral analysis in the auditory midbrain, thalamus, and cortex","volume":"70","author":"MA Escabi","year":"2005","journal-title":"International review of neurobiology"},{"issue":"11","key":"ref108","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1038\/nn737","article-title":"Temporal and rate representations of time-varying signals in the auditory cortex of awake primates","volume":"4","author":"T Lu","year":"2001","journal-title":"Nature neuroscience"},{"issue":"46","key":"ref109","doi-asserted-by":"crossref","first-page":"10440","DOI":"10.1523\/JNEUROSCI.1905-04.2004","article-title":"Multiple time scales of adaptation in auditory cortex neurons","volume":"24","author":"N Ulanovsky","year":"2004","journal-title":"J Neurosci"},{"key":"ref110","article-title":"Auditory Processing of Temporal Fine Structure: Effects of age and hearing loss","author":"BCJ Moore","year":"2014"},{"key":"ref111","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1121\/1.1914448","article-title":"An optimum processor theory for the central formation of the pitch of complex tones","volume":"54","author":"JL Goldstein","year":"1973","journal-title":"Journal of the Acoustical Society of America"},{"issue":"5","key":"ref112","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1073\/pnas.0306958101","article-title":"Correct tonotopic representation is necessary for complex pitch perception","volume":"101","author":"AJ Oxenham","year":"2004","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"ref113","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":"Journal of the Acoustical Society of America"},{"issue":"5","key":"ref114","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.1073\/pnas.1506903113","article-title":"Central auditory neurons have composite receptive fields","volume":"113","author":"AS Kozlov","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"ref115","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/0006-8993(80)91257-3","article-title":"Binaural response-specific bands in primary auditory cortex (AI) of the cat: topographical organization orthogonal to isofrequency contours","volume":"181","author":"JC Middlebrooks","year":"1980","journal-title":"Brain research"},{"issue":"2-3","key":"ref116","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1159\/000013785","article-title":"Spatial distribution of responses to simple and complex sounds in the primary auditory cortex","volume":"3","author":"CE Schreiner","year":"1998","journal-title":"Audiology and Neuro-otology"},{"issue":"6","key":"ref117","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"},{"issue":"7","key":"ref118","first-page":"659","article-title":"Sparse spectrotemporal coding of sounds","volume":"2003","author":"DJ Klein","year":"2003","journal-title":"EURASIP JApplSigProc"},{"issue":"7","key":"ref119","doi-asserted-by":"crossref","first-page":"e1002594","DOI":"10.1371\/journal.pcbi.1002594","article-title":"Sparse Codes for Speech Predict Spectrotemporal Receptive Fields in the Inferior Colliculus","volume":"8","author":"NL Carlson","year":"2012","journal-title":"PLoS CompBio"},{"issue":"4","key":"ref120","first-page":"382","article-title":"RASTA Processing of Speech","volume":"2","author":"H Hermansky","year":"1994","journal-title":"IEEE TransSpeech and Audio Process"},{"issue":"2","key":"ref121","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1109\/TASL.2012.2219526","article-title":"A Multistream Feature Framework Based on Bandpass Modulation Filtering for Robust Speech Recognition","volume":"21","author":"SK Nemala","year":"2013","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"ref122","doi-asserted-by":"crossref","unstructured":"Pearse D, Hirsch H. The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ICSLP 2000 (6th International Conference on Spokel Language Processing). vol. 6; 2000. p. 16\u201319.","DOI":"10.21437\/ICSLP.2000-743"},{"key":"ref123","article-title":"Temporal coherence in the perception of tone sequences","author":"LP van Noorden","year":"1975","journal-title":"Temporal coherence in the perception of tone sequences"},{"issue":"1","key":"ref124","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 review"},{"issue":"18","key":"ref125","doi-asserted-by":"crossref","first-page":"7256","DOI":"10.1523\/JNEUROSCI.4973-14.2015","article-title":"Evidence for Neural Computations of Temporal Coherence in an Auditory Scene and Their Enhancement during Active Listening","volume":"35","author":"JA O\u2019Sullivan","year":"2015","journal-title":"The Journal of neuroscience"},{"issue":"9","key":"ref126","doi-asserted-by":"crossref","first-page":"3669","DOI":"10.1093\/cercor\/bhw173","article-title":"Neural Correlates of Auditory Figure-Ground Segregation Based on Temporal Coherence","volume":"26","author":"S Teki","year":"2016","journal-title":"Cerebral cortex"},{"key":"ref127","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/S0925-2312(02)00741-5","article-title":"Temporal dynamics of attention-modulated neuronal synchronization in macaque V4","volume":"52-54","author":"H Liang","year":"2003","journal-title":"Neurocomputing"},{"issue":"9","key":"ref128","doi-asserted-by":"crossref","first-page":"2256","DOI":"10.1162\/neco.2006.18.9.2256","article-title":"Assessing neuronal coherence with single-unit, multi-unit, and local field potentials","volume":"18","author":"M Zeitler","year":"2006","journal-title":"Neural Comp"},{"issue":"4","key":"ref129","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"},{"issue":"2","key":"ref130","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1152\/jn.00884.2003","article-title":"Primitive auditory stream segregation: a neurophysiological study in the songbird forebrain","volume":"92","author":"MA Bee","year":"2004","journal-title":"Journal of neurophysiology"},{"issue":"15","key":"ref131","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1016\/j.cub.2008.06.053","article-title":"Perceptual organization of sound begins in the auditory periphery","volume":"18","author":"D Pressnitzer","year":"2008","journal-title":"Current Biology"},{"issue":"1-2","key":"ref132","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.heares.2007.01.007","article-title":"The role of auditory cortex in the formation of auditory streams","volume":"229","author":"C Micheyl","year":"2007","journal-title":"Hearing Research"},{"key":"ref133","first-page":"497","article-title":"Auditory Physiology, Perception and Models","author":"M Elhilali","year":"2010"},{"issue":"4","key":"ref134","first-page":"992","article-title":"Effects of the build-up and resetting of auditory stream segregation on temporal discrimination","volume":"34","author":"B Roberts","year":"2007","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"5","key":"ref135","doi-asserted-by":"crossref","first-page":"3019","DOI":"10.1121\/1.3488675","article-title":"Build-up of the tendency to segregate auditory streams: Resetting effects evoked by a single deviant tone","volume":"128","author":"NR Haywood","year":"2010","journal-title":"Journal of the Acoustical Society of America"},{"key":"ref136","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fpsyg.2012.00461","article-title":"The build-up of auditory stream segregation: a different perspective","volume":"3","author":"S Deike","year":"2012","journal-title":"Frontiers in Psychology"},{"key":"ref137","article-title":"Biomimetic Technologies: Principles and Applications","author":"TD Ngo","year":"2015"},{"key":"ref138","article-title":"A survey of deep neural network architectures and their applications","author":"W Liu","year":"2017","journal-title":"Neurocomputing"},{"issue":"3","key":"ref139","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1162\/NECO_a_00397","article-title":"Enhanced Gradient for Training Restricted Boltzmann Machines","volume":"25","author":"K Cho","year":"2013","journal-title":"Neural Computation"},{"issue":"4","key":"ref140","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1162\/089976698300017502","article-title":"Neural Networks with Dynamic Synapses","volume":"10","author":"M Tsodyks","year":"1998","journal-title":"Neural computation"},{"key":"ref141","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.IR.4930","article-title":"DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus","author":"JS Garofolo","year":"1993","journal-title":"DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus"},{"key":"ref142","unstructured":"BBC. The BBC Sound Effects Library; 1990."},{"issue":"5","key":"ref143","doi-asserted-by":"crossref","first-page":"2719","DOI":"10.1121\/1.428100","article-title":"Spectro-temporal modulation transfer functions and speech intelligibility","volume":"106","author":"T Chi","year":"1999","journal-title":"Journal of the Acoustical Society of America"},{"key":"ref144","first-page":"321","article-title":"Data Mining and Knowledge Discovery Handbook","author":"L Rokach","year":"2005"},{"issue":"1","key":"ref145","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/89.365379","article-title":"Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models","volume":"3","author":"DA Reynolds","year":"1995","journal-title":"IEEE Transactions on Speech and Audio Processing"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1006711","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1006711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,10]],"date-time":"2022-09-10T15:58:23Z","timestamp":1662825503000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1006711"}},"subtitle":[],"editor":[{"given":"Fr\u00e9d\u00e9ric E.","family":"Theunissen","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2019,1,22]]},"references-count":145,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,1,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1006711","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,22]]}}}