{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T07:59:20Z","timestamp":1758095960680,"version":"3.44.0"},"reference-count":55,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2018,3,1]],"date-time":"2018-03-01T00:00:00Z","timestamp":1519862400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2019,3,2]],"date-time":"2019-03-02T00:00:00Z","timestamp":1551484800000},"content-version":"am","delay-in-days":366,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N 000141010375"],"award-info":[{"award-number":["N 000141010375"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of the Franklin Institute"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1016\/j.jfranklin.2017.04.013","type":"journal-article","created":{"date-parts":[[2017,4,17]],"date-time":"2017-04-17T22:15:27Z","timestamp":1492467327000},"page":"1638-1662","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical linear dynamical systems for unsupervised musical note recognition"],"prefix":"10.1016","volume":"355","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1393-4614","authenticated-orcid":false,"given":"Goktug T.","family":"Cinar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9701-8087","authenticated-orcid":false,"given":"Pedro M.N.","family":"Sequeira","sequence":"additional","affiliation":[]},{"given":"Jose C.","family":"Principe","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"year":"1993","series-title":"Listening: an introduction to the perception of auditory events","author":"Handel","key":"10.1016\/j.jfranklin.2017.04.013_bib0001"},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0002","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1109\/TASL.2009.2036306","article-title":"Modeling music as a dynamic texture","volume":"18","author":"Barrington","year":"2010","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"5","key":"10.1016\/j.jfranklin.2017.04.013_bib0003","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1162\/neco.1995.7.5.889","article-title":"The Helmholtz machine","volume":"7","author":"Dayan","year":"1995","journal-title":"Neural Comput."},{"issue":"1456","key":"10.1016\/j.jfranklin.2017.04.013_bib0004","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1098\/rstb.2005.1622","article-title":"A theory of cortical responses","volume":"360","author":"Friston","year":"2005","journal-title":"Philos. Trans. R. Soc. B: Biol. Sci."},{"issue":"4","key":"10.1016\/j.jfranklin.2017.04.013_bib0005","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1162\/neco.1997.9.4.721","article-title":"Dynamic model of visual recognition predicts neural response properties in the visual cortex","volume":"9","author":"Rao","year":"1997","journal-title":"Neural Comput."},{"issue":"5","key":"10.1016\/j.jfranklin.2017.04.013_bib0006","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1109\/TPAMI.2007.70738","article-title":"Modeling, clustering, and segmenting video with mixtures of dynamic textures","volume":"30","author":"Chan","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0007","series-title":"Natural Image Statistics","volume":"39","author":"Hyv\u00e4rinen","year":"2009"},{"issue":"5","key":"10.1016\/j.jfranklin.2017.04.013_bib0008","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1109\/TASL.2010.2090148","article-title":"Time series models for semantic music annotation","volume":"19","author":"Coviello","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"10.1016\/j.jfranklin.2017.04.013_bib0009","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1109\/34.506410","article-title":"Using generative models for handwritten digit recognition","volume":"18","author":"Revow","year":"1996","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"10.1016\/j.jfranklin.2017.04.013_bib0010","doi-asserted-by":"crossref","first-page":"1862","DOI":"10.1109\/TPAMI.2009.110","article-title":"Layered dynamic textures","volume":"31","author":"Chan","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0011","series-title":"Proceedings of the International Society for Music Information Retrieval","first-page":"747","article-title":"Modeling dynamic patterns for emotional content in music","author":"Vaizman","year":"2011"},{"issue":"8","key":"10.1016\/j.jfranklin.2017.04.013_bib0012","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":"Hopfield","year":"1982","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"7","key":"10.1016\/j.jfranklin.2017.04.013_bib0013","doi-asserted-by":"crossref","first-page":"1896","DOI":"10.1073\/pnas.84.7.1896","article-title":"Neural computation by concentrating information in time","volume":"84","author":"Tank","year":"1987","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0014","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/78.80888","article-title":"Connected-digit speaker-dependent speech recognition using a neural network with time-delayed connections","volume":"39","author":"Unnikrishnan","year":"1991","journal-title":"IEEE Trans. Signal Process."},{"issue":"11","key":"10.1016\/j.jfranklin.2017.04.013_bib0015","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1016\/j.patcog.2005.01.025","article-title":"Clustering of time series data: a survey","volume":"38","author":"Warren Liao","year":"2005","journal-title":"Pattern Recogn."},{"year":"2015","series-title":"Self-organized computational perception in the time frequency domain","author":"Cinar","key":"10.1016\/j.jfranklin.2017.04.013_bib0016"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0017","doi-asserted-by":"crossref","unstructured":"G.T. Cinar, J.C. Principe, Clustering of time series using a hierarchical linear dynamical system, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2014, pp. 6741\u20136745.","DOI":"10.1109\/ICASSP.2014.6854905"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0018","series-title":"Proceedings of the 2014 IEEE International Joint Conference on Neural Networks (IJCNN)","first-page":"2464","article-title":"Hierarchical linear dynamical systems: a new model for clustering of time series","author":"Cinar","year":"2014"},{"issue":"1","key":"10.1016\/j.jfranklin.2017.04.013_bib0019","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"J. Basic Eng."},{"year":"2000","series-title":"Nonlinear estimation and modeling of noisy time-series by dual Kalman filtering methods","author":"Nelson","key":"10.1016\/j.jfranklin.2017.04.013_bib0020"},{"issue":"2","key":"10.1016\/j.jfranklin.2017.04.013_bib0021","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TAC.1980.1102269","article-title":"A new form of the extended Kalman filter for parameter estimation in linear systems with correlated noise","volume":"25","author":"Panuska","year":"1980","journal-title":"IEEE Trans. Autom. Control"},{"year":"1975","series-title":"Applied Optimal Control: Optimization, Estimation, and Control","author":"Bryson","key":"10.1016\/j.jfranklin.2017.04.013_bib0022"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0023","first-page":"505","article-title":"Distance metric learning with application to clustering with side-information","volume":"15","author":"Xing","year":"2003","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0024","doi-asserted-by":"crossref","DOI":"10.1162\/COMJ_a_00375","article-title":"A study of musical pitch distance using a self-organized hierarchical linear dynamical system on acoustic signals","volume":"40","author":"Cinar","year":"2016","journal-title":"Comput. Music J."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0025","first-page":"849","article-title":"On spectral clustering: analysis and an algorithm","volume":"2","author":"Ng","year":"2002","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"9","key":"10.1016\/j.jfranklin.2017.04.013_bib0026","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/5.58325","article-title":"The self-organizing map","volume":"78","author":"Kohonen","year":"1990","journal-title":"Proc. IEEE"},{"issue":"12","key":"10.1016\/j.jfranklin.2017.04.013_bib0027","doi-asserted-by":"crossref","first-page":"5020","DOI":"10.1109\/TIP.2014.2361210","article-title":"Multi-feature based surround inhibition improves contour detection in natural images","volume":"23","author":"Yang","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0028","first-page":"1289","article-title":"Learning efficient auditory codes using spikes predicts cochlear filters","volume":"17","author":"Smith","year":"2005","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7079","key":"10.1016\/j.jfranklin.2017.04.013_bib0029","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1038\/nature04485","article-title":"Efficient auditory coding","volume":"439","author":"Smith","year":"2006","journal-title":"Nature"},{"issue":"1-2","key":"10.1016\/j.jfranklin.2017.04.013_bib0030","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/0378-5955(90)90170-T","article-title":"Derivation of auditory filter shapes from notched-noise data","volume":"47","author":"Glasberg","year":"1990","journal-title":"Hear. Res."},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0031","doi-asserted-by":"crossref","first-page":"750","DOI":"10.1121\/1.389861","article-title":"Suggested formulae for calculating auditory-filter bandwidths and excitation patterns","volume":"74","author":"Moore","year":"1983","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0032","unstructured":"U.o. I. E. M. Studios, Musical instrument samples, 1997, (http:\/\/theremin.music.uiowa.edu\/). (accessed 24-04-12)."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0033","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1121\/1.1458024","article-title":"YIN, a fundamental frequency estimator for speech and music","volume":"111","author":"De Cheveign\u00e9","year":"2002","journal-title":"J. Acoust. Soc. Am."},{"year":"2007","series-title":"SWIPE: a sawtooth waveform inspired pitch estimator for speech and music","author":"Camacho","key":"10.1016\/j.jfranklin.2017.04.013_bib0034"},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0035","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1109\/TASL.2009.2034186","article-title":"Adaptive harmonic spectral decomposition for multiple pitch estimation","volume":"18","author":"Vincent","year":"2010","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"10.1016\/j.jfranklin.2017.04.013_bib0036","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/89.876309","article-title":"A computationally efficient multipitch analysis model","volume":"8","author":"Tolonen","year":"2000","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0037","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP","first-page":"105","article-title":"Multiple fundamental frequency estimation using gaussian smoothness","author":"Pertusa","year":"2008"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0038","series-title":"Proceedings of the International Society for Music Information Retrieval","first-page":"216","article-title":"Multiple fundamental frequency estimation by summing harmonic amplitudes.","author":"Klapuri","year":"2006"},{"issue":"6","key":"10.1016\/j.jfranklin.2017.04.013_bib0039","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.1109\/TASL.2006.872609","article-title":"Automatic piano transcription using frequency and time-domain information","volume":"14","author":"Bello","year":"2006","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"10.1016\/j.jfranklin.2017.04.013_bib0040","doi-asserted-by":"crossref","first-page":"2498","DOI":"10.1121\/1.2168548","article-title":"Bayesian analysis of polyphonic western tonal music","volume":"119","author":"Davy","year":"2006","journal-title":"J. Acoust. Soc. Am."},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0041","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1109\/TMM.2004.827507","article-title":"A connectionist approach to automatic transcription of polyphonic piano music","volume":"6","author":"Marolt","year":"2004","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"10.1016\/j.jfranklin.2017.04.013_bib0042","first-page":"154","article-title":"A discriminative model for polyphonic piano transcription","volume":"2007","author":"Poliner","year":"2007","journal-title":"EURASIP J. Appl. Signal Process."},{"issue":"3","key":"10.1016\/j.jfranklin.2017.04.013_bib0043","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1007\/s00221-012-3102-z","article-title":"Reduced surround inhibition in musicians","volume":"219","author":"Shin","year":"2012","journal-title":"Exp. Brain Res."},{"issue":"31","key":"10.1016\/j.jfranklin.2017.04.013_bib0044","doi-asserted-by":"crossref","first-page":"10470","DOI":"10.1523\/JNEUROSCI.0047-12.2012","article-title":"Population-wide bias of surround suppression in auditory spatial receptive fields of the owl\u2019s midbrain","volume":"32","author":"Wang","year":"2012","journal-title":"J. Neurosci."},{"issue":"11","key":"10.1016\/j.jfranklin.2017.04.013_bib0045","doi-asserted-by":"crossref","first-page":"2830","DOI":"10.1523\/JNEUROSCI.04-11-02830.1984","article-title":"Specificity of intrinsic connections in primate primary visual cortex","volume":"4","author":"Livingstone","year":"1984","journal-title":"J. Neurosci."},{"issue":"5-6","key":"10.1016\/j.jfranklin.2017.04.013_bib0046","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1007\/s00422-007-0182-0","article-title":"Motion detection, noise reduction, texture suppression, and contour enhancement by spatiotemporal gabor filters with surround inhibition","volume":"97","author":"Petkov","year":"2007","journal-title":"Biol. Cybern."},{"issue":"5","key":"10.1016\/j.jfranklin.2017.04.013_sbref0045","doi-asserted-by":"crossref","first-page":"1622","DOI":"10.1121\/1.392800","article-title":"Speech processing in the auditory system II: lateral inhibition and the central processing of speech evoked activity in the auditory nerve","volume":"78","author":"Shamma","year":"1985","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0048","article-title":"Deep predictive coding networks","author":"Chalasani","year":"2013","journal-title":"arXiv preprint arXiv:1301.3541"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0049","series-title":"Proceedings of the 1998 IEEE International Joint Conference on Neural Networks World Congress on Computational Intelligence","first-page":"69","article-title":"The application of dynamic neural networks to the estimation of feedgas vehicle emissions","volume":"vol.\u00a01","author":"Jesion","year":"1998"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0050","doi-asserted-by":"crossref","unstructured":"H.-G. Zimmermann, R. Grothmann, A.M. Sch\u00e4fer, C. Tietz, H. Georg, Modeling large dynamical systems with dynamical consistent neural networks, New Directions in Statistical Signal Processing (2007) 203.","DOI":"10.7551\/mitpress\/4977.003.0010"},{"issue":"9","key":"10.1016\/j.jfranklin.2017.04.013_bib0051","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.1162\/089976602320263980","article-title":"Learning nonregular languages: a comparison of simple recurrent networks and LSTM","volume":"14","author":"Schmidhuber","year":"2002","journal-title":"Neural Comput."},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0052","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2009","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"Yang","year":"2009"},{"year":"2003","series-title":"The Handbook of Brain Theory and Neural Networks","author":"Arbib","key":"10.1016\/j.jfranklin.2017.04.013_bib0053"},{"key":"10.1016\/j.jfranklin.2017.04.013_bib0054","first-page":"1064","article-title":"Sparse coding in the primate cortex","volume":"1","author":"F\u00f6ldi\u00e1k","year":"1995","journal-title":"Handb. Brain Theory Neural Netw."},{"issue":"9","key":"10.1016\/j.jfranklin.2017.04.013_bib0055","doi-asserted-by":"crossref","first-page":"3844","DOI":"10.1523\/JNEUROSCI.2753-12.2013","article-title":"The sparseness of mixed selectivity neurons controls the generalization\u2013discrimination trade-off","volume":"33","author":"Barak","year":"2013","journal-title":"The Journal of Neuroscience"}],"container-title":["Journal of the Franklin Institute"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0016003217301862?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0016003217301862?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T09:16:01Z","timestamp":1758014161000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0016003217301862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["S0016003217301862"],"URL":"https:\/\/doi.org\/10.1016\/j.jfranklin.2017.04.013","relation":{},"ISSN":["0016-0032"],"issn-type":[{"type":"print","value":"0016-0032"}],"subject":[],"published":{"date-parts":[[2018,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical linear dynamical systems for unsupervised musical note recognition","name":"articletitle","label":"Article Title"},{"value":"Journal of the Franklin Institute","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jfranklin.2017.04.013","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2017 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}