{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T10:12:41Z","timestamp":1790763161625,"version":"4.1.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1006766","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2019,2,22]],"date-time":"2019-02-22T00:00:00Z","timestamp":1550793600000}}],"reference-count":68,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2019,2,11]],"date-time":"2019-02-11T00:00:00Z","timestamp":1549843200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61332007"],"award-info":[{"award-number":["61332007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61621136008"],"award-info":[{"award-number":["61621136008"]}],"id":[{"id":"10.13039\/501100001809","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.1006766","type":"journal-article","created":{"date-parts":[[2019,2,11]],"date-time":"2019-02-11T18:26:25Z","timestamp":1549909585000},"page":"e1006766","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["A hierarchical sparse coding model predicts acoustic feature encoding in both auditory midbrain and cortex"],"prefix":"10.1371","volume":"15","author":[{"given":"Qingtian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4907-7354","authenticated-orcid":true,"given":"Xiaolin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2019,2,11]]},"reference":[{"issue":"46","key":"ref1","doi-asserted-by":"crossref","first-page":"18035","DOI":"10.1073\/pnas.0805234105","article-title":"Ventral and dorsal pathways for language","volume":"105","author":"D Saur","year":"2008","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1493","key":"ref2","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1098\/rstb.2007.2151","article-title":"Neural representation of spectral and temporal information in speech","volume":"363","author":"ED Young","year":"2008","journal-title":"Philosophical Transactions of the Royal Society of London B: Biological Sciences"},{"issue":"2","key":"ref3","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1152\/physrev.00029.2003","article-title":"Neural processing of amplitude-modulated sounds","volume":"84","author":"P Joris","year":"2004","journal-title":"Physiological Reviews"},{"issue":"6","key":"ref4","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1038\/nn.2331","article-title":"Maps and streams in the auditory cortex: nonhuman primates illuminate human speech processing","volume":"12","author":"JP Rauschecker","year":"2009","journal-title":"Nat Neurosci"},{"issue":"5","key":"ref5","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1038\/nrn2113","article-title":"The cortical organization of speech processing","volume":"8","author":"G Hickok","year":"2007","journal-title":"Nat Rev Neurosci"},{"issue":"6174","key":"ref6","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1126\/science.1245994","article-title":"Phonetic feature encoding in human superior temporal gyrus","volume":"343","author":"N Mesgarani","year":"2014","journal-title":"Science"},{"key":"ref7","first-page":"275","article-title":"The Auditory Cortex","author":"CE Schreiner","year":"2011"},{"key":"ref8","first-page":"309","article-title":"The Auditory Cortex","author":"JJ Eggermont","year":"2011"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Lyon R. A computational model of filtering, detection, and compression in the cochlea. IEEE International Conference on Acoustics, Speech, and Signal Processing1982. p. 1282\u20135.","DOI":"10.1109\/ICASSP.1982.1171644"},{"issue":"5","key":"ref10","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1121\/1.393674","article-title":"A model for active elements in cochlear biomechanics","volume":"79","author":"ST Neely","year":"1986","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"1","key":"ref11","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/0378-5955(83)90136-3","article-title":"An active process in cochlear mechanics","volume":"9","author":"H. Davis","year":"1983","journal-title":"Hearing Research"},{"issue":"6","key":"ref12","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":"Journal of Neurophysiology"},{"issue":"5160","key":"ref13","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1126\/science.8171341","article-title":"Neural tuning for sound duration: role of inhibitory mechanisms in the inferior colliculus","volume":"264","author":"J Casseday","year":"1994","journal-title":"Science"},{"issue":"2","key":"ref14","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/0378-5955(94)00174-O","article-title":"Salicylate-induced abnormal activity in the inferior colliculus of rats","volume":"82","author":"PJ Jastreboff","year":"1995","journal-title":"Hearing Research"},{"issue":"1","key":"ref15","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/S0378-5955(02)00367-2","article-title":"Temporal and spatial coding of periodicity information in the inferior colliculus of awake chinchilla (Chinchilla laniger)","volume":"168","author":"G Langner","year":"2002","journal-title":"Hearing Research"},{"issue":"17","key":"ref16","doi-asserted-by":"crossref","first-page":"5483","DOI":"10.1523\/JNEUROSCI.4153-08.2009","article-title":"Stimulus-specific adaptation in the inferior colliculus of the anesthetized rat","volume":"29","author":"MS Malmierca","year":"2009","journal-title":"Journal of Neuroscience"},{"issue":"2","key":"ref17","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/0378-5955(92)90015-F","article-title":"Periodicity coding in the auditory system","volume":"60","author":"G. Langner","year":"1992","journal-title":"Hearing Research"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1111\/j.1460-9568.1995.tb00340.x","article-title":"Temporal coding of amplitude and frequency modulation in the rat auditory cortex","volume":"7","author":"BH Gaese","year":"1995","journal-title":"European Journal of Neuroscience"},{"issue":"5","key":"ref19","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1093\/cercor\/9.5.484","article-title":"Specialization of left auditory cortex for speech perception in man depends on temporal coding","volume":"9","author":"C Li\u00e9geois-Chauvel","year":"1999","journal-title":"Cerebral Cortex"},{"issue":"6583","key":"ref20","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"BA Olshausen","year":"1996","journal-title":"Nature"},{"issue":"23","key":"ref21","doi-asserted-by":"crossref","first-page":"3327","DOI":"10.1016\/S0042-6989(97)00121-1","article-title":"The "independent components" of natural scenes are edge filters","volume":"37","author":"AJ Bell","year":"1997","journal-title":"Vision Res"},{"issue":"4","key":"ref22","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1038\/nn831","article-title":"Efficient coding of natural sounds","volume":"5","author":"MS Lewicki","year":"2002","journal-title":"Nat Neurosci"},{"issue":"7","key":"ref23","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 Comput Biol"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Nagamine T, Seltzer ML, Mesgarani N. Exploring how deep neural networks form phonemic categories. INTERSPEECH; Dresden, Germany,2015. p. 1912\u20136.","DOI":"10.21437\/Interspeech.2015-422"},{"issue":"1","key":"ref25","doi-asserted-by":"crossref","first-page":"e16","DOI":"10.1371\/journal.pbio.0060016","article-title":"Sparse representation of sounds in the unanesthetized auditory cortex","volume":"6","author":"T Hrom\u00e1dka","year":"2008","journal-title":"PLoS Biol"},{"issue":"1","key":"ref26","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.neuron.2013.04.038","article-title":"Sparse and background-invariant coding of vocalizations in auditory scenes","volume":"79","author":"DM Schneider","year":"2013","journal-title":"Neuron"},{"issue":"6","key":"ref27","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.tins.2012.03.008","article-title":"Experimental evidence for sparse firing in the neocortex","volume":"35","author":"AL Barth","year":"2012","journal-title":"Trends Neurosci"},{"issue":"1","key":"ref28","article-title":"Sparsity-regularized HMAX for visual recognition","volume":"9","author":"X Hu","year":"2014","journal-title":"Sparsity-regularized HMAX for visual recognition"},{"issue":"18","key":"ref29","doi-asserted-by":"crossref","first-page":"4882","DOI":"10.1523\/JNEUROSCI.4342-06.2007","article-title":"Spectrotemporal receptive fields in the inferior colliculus revealing selectivity for spectral motion in conspecific vocalizations","volume":"27","author":"S Andoni","year":"2007","journal-title":"J Neurosci"},{"issue":"1","key":"ref30","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1152\/jn.00851.2002","article-title":"Gabor analysis of auditory midbrain receptive fields: spectro-temporal and binaural composition","volume":"90","author":"A Qiu","year":"2003","journal-title":"Journal of Neurophysiology"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1196\/annals.1298.020","article-title":"Methods for the analysis of auditory processing in the brain","volume":"1016","author":"FE Theunissen","year":"2004","journal-title":"Ann N Y Acad Sci"},{"issue":"6","key":"ref32","doi-asserted-by":"crossref","first-page":"2315","DOI":"10.1523\/JNEUROSCI.20-06-02315.2000","article-title":"Spectral-temporal receptive fields of nonlinear auditory neurons obtained using natural sounds","volume":"20","author":"FE Theunissen","year":"2000","journal-title":"Journal of Neuroscience"},{"issue":"3","key":"ref33","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1080\/net.12.3.289.316","article-title":"Estimating spatio-temporal receptive fields of auditory and visual neurons from their responses to natural stimuli","volume":"12","author":"FE Theunissen","year":"2001","journal-title":"Network-Comp Neural"},{"issue":"2","key":"ref34","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1152\/jn.00813.2009","article-title":"Spectral and temporal modulation tradeoff in the inferior colliculus","volume":"103","author":"FA Rodriguez","year":"2010","journal-title":"J Neurophysiol"},{"issue":"21","key":"ref35","doi-asserted-by":"crossref","first-page":"5412","DOI":"10.1523\/JNEUROSCI.0073-08.2008","article-title":"Dynamic spectrotemporal feature selectivity in the auditory midbrain","volume":"28","author":"NA Lesica","year":"2008","journal-title":"Journal of Neuroscience"},{"key":"ref36","first-page":"321","article-title":"Data mining and knowledge discovery handbook","author":"L Rokach","year":"2005"},{"key":"ref37","unstructured":"R\u00e4s\u00e4nen O, Nagamine T, Mesgarani N, Papafragou A, Grodner D, Mirman D, et al. Analyzing distributional learning of phonemic categories in unsupervised deep neural networks. Annual Conference of the Cognitive Science Society2016."},{"issue":"23","key":"ref38","doi-asserted-by":"crossref","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","article-title":"Sparse coding with an overcomplete basis set: a strategy employed by V1?","volume":"37","author":"BA Olshausen","year":"1997","journal-title":"Vision Res"},{"issue":"6","key":"ref39","doi-asserted-by":"crossref","first-page":"2907","DOI":"10.1152\/jn.00594.2010","article-title":"Sparse coding in striate and extrastriate visual cortex","volume":"105","author":"B Willmore","year":"2011","journal-title":"J Neurophysiol"},{"issue":"3","key":"ref40","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1080\/net.12.3.255.270","article-title":"Characterizing the sparseness of neural codes","volume":"12","author":"B Willmore","year":"2001","journal-title":"Network"},{"issue":"6","key":"ref41","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1038\/nn.2308","article-title":"Unraveling the principles of auditory cortical processing: can we learn from the visual system?","volume":"12","author":"AJ King","year":"2009","journal-title":"Nat Neurosci"},{"issue":"6","key":"ref42","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1038\/nrn3731","article-title":"Neural processing of natural sounds","volume":"15","author":"FE Theunissen","year":"2014","journal-title":"Nat Rev Neurosci"},{"issue":"2","key":"ref43","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1088\/0954-898X_7_2_005","article-title":"Learning the higher-order structure of a natural sound","volume":"7","author":"AJ Bell","year":"1996","journal-title":"Network: Computation in Neural Systems"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Taylor GW, Fergus R. Adaptive deconvolutional networks for mid and high level feature learning. IEEE International Conference on Computer Vision (ICCV) 2011. p. 2018\u201325.","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2017.00100","article-title":"Deep learning predicts correlation between a functional signature of higher visual areas and sparse firing of neurons","volume":"11","author":"C Zhuang","year":"2017","journal-title":"Front Comput Neurosc"},{"issue":"2","key":"ref46","first-page":"421","article-title":"Developmental changes in perception of nonnative vowel contrasts","volume":"20","author":"L Polka","year":"1994","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"3","key":"ref47","doi-asserted-by":"crossref","first-page":"B101","DOI":"10.1016\/S0010-0277(01)00157-3","article-title":"Infant sensitivity to distributional information can affect phonetic discrimination","volume":"82","author":"J Maye","year":"2002","journal-title":"Cognition"},{"issue":"33","key":"ref48","doi-asserted-by":"crossref","first-page":"13273","DOI":"10.1073\/pnas.0705369104","article-title":"Unsupervised learning of vowel categories from infant-directed speech","volume":"104","author":"GK Vallabha","year":"2007","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"Miyazawa K, Kikuchi H, Mazuka R. Unsupervised learning of vowels from continuous speech based on self-organized phoneme acquisition model. Eleventh Annual Conference of the International Speech Communication Association2010.","DOI":"10.21437\/Interspeech.2010-757"},{"issue":"3","key":"ref50","doi-asserted-by":"crossref","first-page":"B31","DOI":"10.1016\/j.cognition.2005.10.006","article-title":"The acquisition of allophonic rules: Statistical learning with linguistic constraints","volume":"101","author":"S Peperkamp","year":"2006","journal-title":"Cognition"},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"Synnaeve G, Schatz T, Dupoux E, editors. Phonetics embedding learning with side information. IEEE Spoken Language Technology Workshop (SLT); 2014: IEEE.","DOI":"10.1109\/SLT.2014.7078558"},{"key":"ref52","doi-asserted-by":"crossref","unstructured":"Thiolliere R, Dunbar E, Synnaeve G, Versteegh M, Dupoux E. A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling. Sixteenth Annual Conference of the International Speech Communication Association2015.","DOI":"10.21437\/Interspeech.2015-640"},{"issue":"4","key":"ref53","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1037\/a0034245","article-title":"A role for the developing lexicon in phonetic category acquisition","volume":"120","author":"NH Feldman","year":"2013","journal-title":"Psychological Review"},{"key":"ref54","unstructured":"Elsner M, Goldwater S, Eisenstein J. Bootstrapping a unified model of lexical and phonetic acquisition. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1: Association for Computational Linguistics; 2012. p. 184\u201393."},{"issue":"2","key":"ref55","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1080\/15475441.2005.9684216","article-title":"PRIMIR: A developmental framework of infant speech processing","volume":"1","author":"JF Werker","year":"2005","journal-title":"Language Learning and Development"},{"issue":"5","key":"ref56","doi-asserted-by":"crossref","first-page":"2490","DOI":"10.1152\/jn.1999.82.5.2490","article-title":"Responses to contour features in macaque area V4","volume":"82","author":"A Pasupathy","year":"1999","journal-title":"J Neurophysiol"},{"issue":"20","key":"ref57","doi-asserted-by":"crossref","first-page":"5532","DOI":"10.1523\/JNEUROSCI.4139-15.2016","article-title":"Contour curvature as an invariant code for objects in visual area V4","volume":"36","author":"Y El-Shamayleh","year":"2016","journal-title":"Journal of Neuroscience"},{"issue":"13","key":"ref58","doi-asserted-by":"crossref","first-page":"5475","DOI":"10.1523\/JNEUROSCI.4188-12.2013","article-title":"Inhibitory interneurons decorrelate excitatory cells to drive sparse code formation in a spiking model of V1","volume":"33","author":"PD King","year":"2013","journal-title":"J Neurosci"},{"issue":"6","key":"ref59","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1162\/neco.2008.02-07-466","article-title":"A canonical neural circuit for cortical nonlinear operations","volume":"20","author":"M Kouh","year":"2008","journal-title":"Neural Comput"},{"key":"ref60","doi-asserted-by":"crossref","unstructured":"Knoblich U, Bouvrie J, Poggio T, editors. Biophysical models of neural computation: Max and tuning circuits. International Workshop on Web Intelligence Meets Brain Informatics; 2006: Springer.","DOI":"10.21236\/ADA466426"},{"key":"ref61","article-title":"Theoretical Neuroscience: Cambridge","author":"P Dayan","year":"2001"},{"key":"ref62","article-title":"The DARPA TIMIT acoustic-phonetic continuous speech corpus cdrom","author":"JS Garofalo","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref63","first-page":"1998","article-title":"Auditory toolbox. Interval Research Corporation","volume":"10","author":"M. Slaney","year":"1998"},{"issue":"11","key":"ref64","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":"Nat Neurosci"},{"issue":"4","key":"ref65","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 Comput"},{"issue":"7553","key":"ref66","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"ref67","doi-asserted-by":"crossref","unstructured":"Mairal J, Bach F, Ponce J, Sapiro G. Online dictionary learning for sparse coding. International Conference on Machine Learning; Montreal, Quebec, Canada2009. p. 689\u201396.","DOI":"10.1145\/1553374.1553463"},{"key":"ref68","article-title":"The Sound Pattern of English","author":"N Chomsky","year":"1968"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1006766","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2019,2,22]],"date-time":"2019-02-22T00:00:00Z","timestamp":1550793600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1006766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,11]],"date-time":"2022-09-11T18:57:06Z","timestamp":1662922626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1006766"}},"subtitle":[],"editor":[{"given":"Fr\u00e9d\u00e9ric E.","family":"Theunissen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2019,2,11]]},"references-count":68,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,2,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1006766","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1006766","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,11]]}}}