{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T08:57:28Z","timestamp":1765961848863,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Government","award":["RS-2023-NR077289","RS-2024-00358448"],"award-info":[{"award-number":["RS-2023-NR077289","RS-2024-00358448"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3507568","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:44:02Z","timestamp":1732736642000},"page":"5106-5116","source":"Crossref","is-referenced-by-count":3,"title":["Towards Efficient and Real-Time Piano Transcription Using Neural Autoregressive Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8510-872X","authenticated-orcid":false,"given":"Taegyun","family":"Kwon","sequence":"first","affiliation":[{"name":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3655-1181","authenticated-orcid":false,"given":"Dasaem","family":"Jeong","sequence":"additional","affiliation":[{"name":"Sogang University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-2119","authenticated-orcid":false,"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"article-title":"MAPS-A piano database for multipitch estimation and automatic transcription of music","year":"2010","author":"Emiya","key":"ref2"},{"key":"ref3","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hawthorne","year":"2019"},{"key":"ref4","first-page":"50","article-title":"Onsets and frames: Dual-objective piano transcription","volume-title":"Proc. 19th Int. Soc. Music Inf. Retrieval Conf.","author":"Hawthorne","year":"2018"},{"key":"ref5","first-page":"670","article-title":"Adversarial learning for improved onsets and frames music transcription","volume-title":"Proc. 20th Int. Soc. Music Inf. Retrieval Conf.","author":"Kim","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683582"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.03.010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0169411"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2019.00075"},{"key":"ref11","first-page":"475","article-title":"On the potential of simple framewise approaches to piano transcription","volume-title":"Proc. 17th Int. Soc. Music Inf. Retrieval Conf.","author":"Kelz","year":"2016"},{"key":"ref12","first-page":"454","article-title":"Polyphonic piano transcription using autoregressive multi-state note model","volume-title":"Proc. 21th Int. Soc. Music Inf. Retrieval Conf.","author":"Kwon","year":"2020"},{"key":"ref13","first-page":"4","article-title":"Real-time automatic piano music transcription system","volume-title":"Proc. Late Breaking Demo 21st Int. Soc. Music Inf. Retrieval Conf.","author":"Jeong","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app8030470"},{"key":"ref15","first-page":"1881","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","volume-title":"Proc. 29th Int. Conf. Mach. Learn.","author":"Boulanger-Lewandowski","year":"2012"},{"key":"ref16","first-page":"454","article-title":"Blending acoustic and language model predictions for automatic music transcription","volume-title":"Proc. 20th Int. Soc. Music Inf. Retrieval Conf.","author":"Ycart","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034186"},{"key":"ref18","first-page":"175","article-title":"A classification-based polyphonic piano transcription approach using learned feature representations","volume-title":"Proc. 12th Int. Soc. Music Inf. Retrieval Conf.","author":"Nam","year":"2011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/48317"},{"key":"ref20","first-page":"20583","article-title":"Skipping the frame-level: Event-based piano transcription with neural semi-CRFs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yan","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/app7090901"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030482"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070851"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638244"},{"key":"ref25","first-page":"2021","article-title":"Sequence-to-sequence piano transcription with transformers","volume-title":"Proc. 22th Int. Soc. Music Inf. Retrieval Conf.","author":"Hawthorne"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref27","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"article-title":"The vienna 4x22 piano corpus","year":"1999","author":"Goebl","key":"ref30"},{"key":"ref31","article-title":"Saarland music data (SMD)","volume-title":"Proc. Late-Breaking Demo Session 12th Int. Conf. Music Inf. Retrieval","author":"Mller","year":"2011"},{"key":"ref32","first-page":"367","article-title":"MIR_EVAL: A transparent implementation of common MIR metrics","volume-title":"Proc. 15th Int. Soc. Music Inf. Retrieval Conf.","author":"Raffel","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref34","first-page":"18795","article-title":"Adabelief optimizer: Adapting stepsizes by the belief in observed gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhuang","year":"2020"},{"key":"ref35","first-page":"315","article-title":"Evaluation of real-time audio-to-score alignment","volume-title":"Proc. Int. Conf. Music Inf. Retrieval","author":"Cont","year":"2007"},{"key":"ref36","article-title":"Analysis and correction of maps dataset","volume-title":"Proc. 22nd Int. Conf. Digit. Audio Effects","author":"Gong","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0087357"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475405"},{"key":"ref40","first-page":"183","article-title":"Deep unsupervised drum transcription","volume-title":"Proc. 20th Int. Soc. Music Inf. Retrieval Conf.","author":"Choi","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982285"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10769033.pdf?arnumber=10769033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T22:10:42Z","timestamp":1733955042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3507568","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}