{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:16:54Z","timestamp":1759133814838,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008902","name":"LANL","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008902","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007000","name":"LDRD","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/taslp.2016.2598305","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T18:11:15Z","timestamp":1470334275000},"page":"2218-2230","source":"Crossref","is-referenced-by-count":23,"title":["Context-Dependent Piano Music Transcription With Convolutional Sparse Coding"],"prefix":"10.1109","volume":"24","author":[{"given":"Andrea","family":"Cogliati","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brendt","family":"Wohlberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.852985"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.1999.810864"},{"key":"ref33","first-page":"318","article-title":"Polyphonic music transcription by non-negative sparse coding of power spectra","author":"abdallah","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/COMJ_a_00146"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2162395"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/89.876309"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.400725"},{"key":"ref35","first-page":"3112","article-title":"Polyphonic piano transcription using non-negative matrix factorisation with group sparsity","author":"o\u2019hanlon","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref34","first-page":"441","article-title":"Structured sparsity for automatic music transcription","author":"o\u2019hanlon","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.57"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177967"},{"journal-title":"MATLAB Library SParse Optimization Research COde (SPORCO) version 0 0 2","year":"2015","author":"wohlberg","key":"ref61"},{"article-title":"BW3—MSSIPLCA_fast_NoteTracking2","year":"2013","author":"benetos","key":"ref63"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"journal-title":"Signal Processing Methods for Music Transcription","year":"2006","author":"davy","key":"ref64"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158804"},{"article-title":"RIR Generator","year":"2003","author":"habets","key":"ref65"},{"key":"ref29","article-title":"A probabilistic latent variable model for acoustic modeling","author":"smaragdis","year":"0","journal-title":"Proc Workshop Adv Models Acoust Process Neural Inform Process Syst"},{"key":"ref2","first-page":"32","article-title":"On the transcription of musical sound by computer","volume":"1","author":"moorer","year":"1977","journal-title":"Comput Music J"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0258-3"},{"key":"ref20","first-page":"175","article-title":"A classification-based polyphonic piano transcription approach using learned feature representations","author":"nam","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref22","first-page":"1159","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287832"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.07.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2042119"},{"key":"ref50","first-page":"1538","article-title":"Unsupervised transcription of piano music","author":"berg-kirkpatrick","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178033"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854992"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"ref56","first-page":"149","article-title":"Shift-invariance sparse coding for audio classification","author":"grosse","year":"2007","journal-title":"UAI 2007 Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860346"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2495260"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827596304010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/ji-3-2.1946.0074"},{"year":"2015","key":"ref11","article-title":"MIREX2015 Results"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.2168548"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324332"},{"key":"ref13","article-title":"Automatic transcription of piano music","author":"raphael","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.815516"},{"key":"ref15","first-page":"iii-225","article-title":"Multiple fundamental frequency estimation of polyphonic music signals","volume":"3","author":"yeh","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref16","article-title":"Multiple fundamental frequency extraction for MIREX 2012","author":"dressler","year":"0","journal-title":"Proc Music Information Retrieval Evaluation eXchange"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/48317"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517557"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.912998"},{"key":"ref4","first-page":"315","article-title":"Evaluation of multiple-F0 estimation and tracking systems","author":"bay","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref3","first-page":"24","article-title":"Automatic music transcription","volume":"1","author":"piszczalski","year":"1977","journal-title":"Comput Music J"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0003-682X(90)90043-T"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4808.001.0001","author":"cook","year":"1999","journal-title":"Music Cognition and Computerized Sound"},{"key":"ref8","first-page":"361","article-title":"Local group delay based vibrato and tremolo suppression for onset detection","author":"b\u00f6ck","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851998"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885248"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MELECON.2002.1014600"},{"key":"ref45","first-page":"181","article-title":"Note-level music transcription by maximum likelihood sampling","author":"duan","year":"0","journal-title":"Proc Int Symp Musical Inform Retrieval"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2009.03.024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2442411"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872609"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/comj.2008.32.3.72"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2005.06.007"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/6570655\/7571201\/7533446-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7571201\/07533446.pdf?arnumber=7533446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:54:23Z","timestamp":1649444063000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7533446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":65,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2598305","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}