{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T06:01:26Z","timestamp":1770530486013,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["DFG-MU 2686\/11-1"],"award-info":[{"award-number":["DFG-MU 2686\/11-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["MU 2686\/12-1"],"award-info":[{"award-number":["MU 2686\/12-1"]}],"id":[{"id":"10.13039\/501100001659","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":[[2021]]},"DOI":"10.1109\/taslp.2021.3110137","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T20:21:17Z","timestamp":1631132477000},"page":"2957-2971","source":"Crossref","is-referenced-by-count":14,"title":["CTC-Based Learning of Chroma Features for Score\u2013Audio Music Retrieval"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1383-4541","authenticated-orcid":false,"given":"Frank","family":"Zalkow","sequence":"first","affiliation":[{"name":"International Audio Laboratories Erlangen, a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-7524","authenticated-orcid":false,"given":"Meinard","family":"Muller","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen, a joint institution of the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany"}]}],"member":"263","reference":[{"key":"ref39","first-page":"34","article-title":"An end-to-end framework for audio-to-score music transcription on monophonic excerpts","author":"rom\u00e1n","year":"2018","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2021.1873393"},{"key":"ref33","first-page":"636","article-title":"Deep-rhythm for global tempo estimation in music","author":"aarabi","year":"2019","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref32","first-page":"135","article-title":"Frame-level instrument recognition by timbre and pitch","author":"hung","year":"2018","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref31","first-page":"302","article-title":"Multiple F0 estimation in vocal ensembles using convolutional neural networks","author":"cuesta","year":"2020","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462420"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.77"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/app8040606"},{"key":"ref35","first-page":"472","article-title":"End-to-end optical music recognition using neural networks","author":"calvo-zaragoza","year":"2017","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902741"},{"key":"ref28","first-page":"403","article-title":"Moving beyond feature design: Deep architectures and automatic feature learning in music informatics","author":"humphrey","year":"2012","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/376929.376978"},{"key":"ref29","first-page":"188","article-title":"Structured training for large-vocabulary chord recognition","author":"mcfee","year":"2017","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref2","article-title":"Polyphonic score retrieval using polyphonic audio","author":"pickens","year":"2002","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5"},{"key":"ref20","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","author":"bittner","year":"2014","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref22","first-page":"184","article-title":"Using weakly aligned score-audio pairs to train deep chroma models for cross-modal music retrieval","author":"zalkow","year":"2020","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.68"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2875349"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2868887"},{"key":"ref50","first-page":"67","article-title":"Melody extraction based on a source-filter model using pitch contour selection","author":"bosch","year":"2016","journal-title":"Proc 13th Sound Music Comput Conf"},{"key":"ref51","article-title":"Melody extraction for MIREX 2016","author":"bosch","year":"0","journal-title":"Music Inf Retrieval Eval eXchange (MIREX) System Abstr"},{"key":"ref58","first-page":"25","article-title":"Data usage in MIR: History & future recommendations","author":"chen","year":"2019","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5220\/0007456306910698"},{"key":"ref56","first-page":"54","article-title":"20 years of automatic chord recognition from audio","author":"pauwels","year":"2019","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2016.1182191"},{"key":"ref53","author":"benward","year":"2009","journal-title":"Music in Theory and Practice"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref11","first-page":"37","article-title":"Feature learning for chord recognition: The deep chroma extractor","author":"korzeniowski","year":"2016","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683470"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738895"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/app10010019"},{"key":"ref14","first-page":"107","article-title":"Cover detection using dominant melody embeddings","author":"doras","year":"2019","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053793"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2879399"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952145"},{"key":"ref18","first-page":"82","article-title":"Main melody estimation with source-filter NMF and CRNN","author":"basaran","year":"2018","journal-title":"Proc 19th Int Soc Music Inf Retrieval Conf"},{"key":"ref19","first-page":"673","article-title":"Four timely insights on automatic chord estimation","author":"humphrey","year":"2015","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref4","first-page":"185","article-title":"Polyphonic audio matching and alignment for music retrieval","author":"hu","year":"2003","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683609"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471681"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840597"},{"key":"ref7","article-title":"Tonal description of music audio signals","author":"g\u00f3mez","year":"2006"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref9","first-page":"63","article-title":"Deep salience representations for F0 tracking in polyphonic music","author":"bittner","year":"2017","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref46","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"0","journal-title":"ICML Workshop Deep Learn Audio Speech Lang Process (WDLASL)"},{"key":"ref45","author":"barlow","year":"1975","journal-title":"A Dictionary of Musical Themes"},{"key":"ref48","article-title":"Transcribing real-valued sequences with deep neural network","author":"hannun","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2020-0165"},{"key":"ref42","first-page":"512","article-title":"Multilingual lyrics-to-audio alignment","author":"vaglio","year":"2020","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054567"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683024"},{"key":"ref43","first-page":"955","article-title":"Audio tagging with connectionist temporal classification model using sequentially labelled data","author":"hou","year":"2019","journal-title":"Proc Int Conf Signal Process Commun"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09531521.pdf?arnumber=9531521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T20:41:01Z","timestamp":1642192861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9531521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3110137","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}