{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T08:02:10Z","timestamp":1778313730228,"version":"3.51.4"},"reference-count":46,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"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.2021.3121991","type":"journal-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T20:52:27Z","timestamp":1635281547000},"page":"3707-3717","source":"Crossref","is-referenced-by-count":87,"title":["High-Resolution Piano Transcription With Pedals by Regressing Onset and Offset Times"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2864-0475","authenticated-orcid":false,"given":"Qiuqiang","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bochen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuchen","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683505"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683582"},{"key":"ref32","article-title":"The role of timing and intensity in the production and perception of melody in expressive piano performance","author":"goebl","year":"2003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.1376133"},{"key":"ref30","first-page":"286","article-title":"Convolutional neural networks for real-time beat tracking: A dancing robot application","author":"gkiokas","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref37","first-page":"193","article-title":"The interpretation of midi velocity","author":"dannenberg","year":"0","journal-title":"Proc Int Comput Music Conf"},{"key":"ref36","first-page":"417","article-title":"Boundary detection in music structure analysis using convolutional neural networks","author":"ullrich","year":"0","journal-title":"Int Soc Music Inf Retr (ISMIR)"},{"key":"ref35","first-page":"63","article-title":"Deep salience representations for F0 estimation in polyphonic music","author":"bittner","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MELCON.2000.879982"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref11","article-title":"A discriminative model for polyphonic piano transcription","volume":"2007","author":"poliner","year":"2007","journal-title":"EURASIP J Adv Signal Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872609"},{"key":"ref14","first-page":"318","article-title":"Polyphonic music transcription by non-negative sparse coding of power spectra","author":"abdallah","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref15","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":"ref16","first-page":"584","article-title":"An attack\/decay model for piano transcription","author":"cheng","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref17","first-page":"1538","article-title":"Unsupervised transcription of piano music","author":"berg-kirkpatrick","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827507"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324332"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0258-3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/10.0001468"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref27","article-title":"SoftLoc: Robust temporal localization under label misalignment","author":"schroeter","year":"0","journal-title":"Proc Open Rev Int Conf Learn Representations"},{"key":"ref6","first-page":"417","article-title":"A multi-pass algorithm for accurate audio-to-score alignment","author":"niedermayer","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2611938"},{"key":"ref29","article-title":"Modeling music: Studies of music transcription, music perception and music production","author":"elowsson","year":"2018"},{"key":"ref8","first-page":"153","article-title":"Using musical knowledge to extract expressive performance information from audio recordings","author":"scheirer","year":"0","journal-title":"Proc Int Joint Conf Artif Intell Workshop Comput Auditory Scene Anal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159701"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref1","article-title":"Automatic transcription of piano music","author":"raphael","year":"0","journal-title":"Trans Int Soc Music Inf Retrieval"},{"key":"ref9","first-page":"31","article-title":"On the computer recognition of solo piano music","author":"dixon","year":"0","journal-title":"Proc Australas Comput Music Conf"},{"key":"ref46","first-page":"367","article-title":"mir_eval: A transparent implementation of common MIR metrics","author":"raffel","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"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 Soc Music Inf Retrieval"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287832"},{"key":"ref42","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00023"},{"key":"ref41","first-page":"670","article-title":"Adversarial learning for improved onsets and frames music transcription","author":"kim","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref23","first-page":"475","article-title":"On the potential of simple framewise approaches to piano transcription","author":"kelz","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref44","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref26","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"hawthorne","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"50","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","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\/9289074\/09585550.pdf?arnumber=9585550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:53Z","timestamp":1652194433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9585550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3121991","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}