{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T04:51:21Z","timestamp":1767847881799,"version":"3.49.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T00:00:00Z","timestamp":1477958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001868","name":"National Science Council of Taiwan","doi-asserted-by":"publisher","award":["MOST102-2221-E-001-004-MY3"],"award-info":[{"award-number":["MOST102-2221-E-001-004-MY3"]}],"id":[{"id":"10.13039\/501100001868","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Academia Sinica Career Development Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1109\/taslp.2016.2598323","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T18:11:15Z","timestamp":1470334275000},"page":"2158-2170","source":"Crossref","is-referenced-by-count":15,"title":["Monaural Music Source Separation Using Convolutional Sparse Coding"],"prefix":"10.1109","volume":"24","author":[{"given":"Ping-Keng","family":"Jao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brendt","family":"Wohlberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2466447"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854953"},{"key":"ref71","first-page":"625","article-title":"State of the art report: Audio-based music structure analysis","author":"paulus","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2208663"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2433061"},{"key":"ref74","first-page":"1065","article-title":"A survey of convolutive blind source separation methods","author":"pedersen","year":"2007","journal-title":"Springer Handbook of Speech Processing"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637745"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532675"},{"key":"ref38","first-page":"559","article-title":"A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals","author":"bosch","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref78","first-page":"708","article-title":"Electric guitar playing technique detection in real-world recordings based on F0 sequence pattern recognition","author":"chen","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref79","year":"2011"},{"key":"ref33","first-page":"337","article-title":"Separation of vocals from polyphonic audio recordings","author":"vembu","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref32","first-page":"133","article-title":"Instrument equalizer for query-by-example retrieval: Improving sound source separation based on integrated harmonic and inharmonic models","author":"itoyama","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref31","first-page":"314","article-title":"Remixing stereo music with score-informed source separation","author":"woodruff","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285484"},{"key":"ref37","first-page":"327","article-title":"Musical instrument recognition in polyphonic audio using source-filter model for sound separation","author":"heittola","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2514845"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959531"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2362006"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2042530"},{"key":"ref61","article-title":"Fast signal reconstruction from magnitude STFT spectrogram based on spectrogram consistency","author":"roux","year":"2010","journal-title":"Proc 13th Int Conf Digital Audio Effects"},{"key":"ref63","first-page":"101","article-title":"Multiresolution STFT phase estimation with frame-wise posterior window length decision","author":"gnann","year":"0","journal-title":"Proc Int Conf Digit Audio Effects"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2442411"},{"key":"ref64","article-title":"Phase-based informed source separation for active listening of music","author":"sturmel","year":"2012","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191398"},{"key":"ref65","first-page":"730","article-title":"Coding time-varying signals using sparse, shift-invariant representations","volume":"11","author":"lewicki","year":"1999","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860346"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034186"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2005.06.007"},{"key":"ref68","article-title":"Shift invariant sparse coding of image and music data","author":"m\u00f8rup","year":"2008"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827596304010"},{"key":"ref2","first-page":"509","article-title":"Shifted 2D nonnegative tensor factorisation","author":"fitzgerald","year":"0","journal-title":"Proc IET Irish Signals Syst Conf"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854992"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539958"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.57"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2495260"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177967"},{"key":"ref25","article-title":"Fast convolutional sparse coding (FCSC)","author":"kong","year":"2014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2296076"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346542"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109379"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495699"},{"key":"ref57","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"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2450494"},{"key":"ref55","article-title":"Pitch-informed solo and accompaniment separation","author":"cer\u00f3n","year":"2014"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1109\/TASL.2009.2020886","article-title":"Monaural musical sound separation based on pitch and common amplitude modulation","volume":"17","author":"li","year":"2009","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637775"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946389"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471637"},{"key":"ref11","article-title":"A probabilistic latent variable model for acoustic modeling","author":"smaragdis","year":"0","journal-title":"Proc Workshop Adv Models Acoust Process NIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2297715"},{"key":"ref13","first-page":"369","article-title":"Beyond NMF: Time-domain audio source separation without phase reconstruction","author":"yoshii","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853676"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177937"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref81","article-title":"SParse Optimization Research COde (SPORCO)","author":"wohlberg","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20132"},{"key":"ref84","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1007\/978-3-540-30110-3_63","article-title":"Non-negative matrix factor deconvolution; extraction of multiple sound sources from monophonic inputs","author":"smaragdis","year":"2004","journal-title":"Independent Component Analysis and Blind Signal Separation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20124"},{"key":"ref83","article-title":"BSS_Eval: A toolbox for performance measurement in (blind) source separation","year":"2010"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1201\/b17758","author":"rish","year":"2014","journal-title":"Sparse modeling theory algorithms and applications"},{"key":"ref80","first-page":"229","article-title":"RWC music database: Music genre database and musical instrument sound database","volume":"3","author":"goto","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref4","first-page":"17","article-title":"Investigating single-channel audio source separation methods based on non-negative matrix factorization","author":"wang","year":"0","journal-title":"Proc ICA Res Netw Int Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/11679363_87"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref85","first-page":"19","article-title":"Multiple-instrument polyphonic music transcription using a convolutive probabilistic model","author":"benetos","year":"0","journal-title":"Proc Sound and Music Computing Conf"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960364"},{"key":"ref86","article-title":"On the use of masking filters in sound source separation","author":"fitzgerald","year":"2012","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172425"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637776"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324332"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855053"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287834"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159701"},{"key":"ref48","first-page":"277","article-title":"Score-informed leading voice separation from monaural audio","author":"joder","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289134"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.914120"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637607"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0258-3"},{"key":"ref43","first-page":"601","article-title":"Predominant fundamental frequency estimation vs singing voice separation for the automatic transcription of accompanied flamenco singing","author":"g\u00f3mez","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7542618\/07533514.pdf?arnumber=7533514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:09Z","timestamp":1642003389000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7533514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":88,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2598323","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11]]}}}