{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:15:36Z","timestamp":1766067336782,"version":"3.37.3"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001359","name":"Singapore International","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015671","name":"Agency for Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015671","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Technology and Research (A*STAR)","doi-asserted-by":"publisher","award":["SING-2018-02-0204"],"award-info":[{"award-number":["SING-2018-02-0204"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009122","name":"MOE Tier 2","doi-asserted-by":"publisher","award":["MOE2018-T2-2-161,SRG ISTD 2017 129"],"award-info":[{"award-number":["MOE2018-T2-2-161,SRG ISTD 2017 129"]}],"id":[{"id":"10.13039\/100009122","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412155","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"9091-9098","source":"Crossref","is-referenced-by-count":16,"title":["The Effect of Spectrogram Reconstruction on Automatic Music Transcription: An Alternative Approach to Improve Transcription Accuracy"],"prefix":"10.1109","author":[{"given":"Kin Wai","family":"Cheuk","sequence":"first","affiliation":[{"name":"Institute of High Performance Computing, Agency for Science, Technology and Research"}]},{"given":"Yin-Jvun","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London"}]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London"}]},{"given":"Dorien","family":"Herremans","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing, Agency for Science, Technology and Research"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/IJCNN48605.2020.9207605"},{"key":"ref38","article-title":"Mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"ISMIR"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.24963\/ijcai.2019\/652"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1121\/1.4790351"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ASPAA.2003.1285860"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/TASL.2009.2034186"},{"key":"ref37","first-page":"315","article-title":"Evaluation of multiple-f0 estimation and tracking systems","author":"bay","year":"2009","journal-title":"ISMIR"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref35","article-title":"nnaudio: An on-the-fly gpu audio to spectrogram conversion toolbox using 1d convolution neural networks","author":"cheuk","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"On the potential of simple framewise approaches to piano transcription","author":"kelz","year":"2016","journal-title":"ISMIR"},{"key":"ref10","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"ICML"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/ICASSP.2018.8461660"},{"key":"ref11","article-title":"Striving for simplicity: The all convolutional net","author":"springenberg","year":"2014","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TASLP.2016.2533858"},{"year":"2018","author":"ullrich","journal-title":"Music transcription with convolutional sequence-to-sequence models","key":"ref13"},{"key":"ref14","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","year":"2017","journal-title":"ISMIR"},{"key":"ref15","first-page":"670","article-title":"Adversarial learning for improved onsets and frames music transcription","author":"kim","year":"0","journal-title":"International Society forMusic Information Retrieval Conference"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2019.8683582"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/TASL.2006.885248"},{"key":"ref18","first-page":"1538","article-title":"Unsupervised transcription of piano music","author":"berg-kirkpatrick","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"183","article-title":"Deep unsupervised drum transcription","author":"choi","year":"2019","journal-title":"ISMIR 4–8 2019"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICASSP40776.2020.9052987"},{"key":"ref4","first-page":"731","article-title":"A holistic approach to polyphonic music transcription with neural networks","author":"roman","year":"0","journal-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference ISMIR 2019 Delft The Netherlands November 4–8 2019"},{"key":"ref27","article-title":"Learning features of music from scratch","volume":"abs 1611 9827","author":"thickstun","year":"2016","journal-title":"ArXiv"},{"key":"ref3","first-page":"34","article-title":"An end-to-end framework for audio-to-score music transcription on monophonic excerpts","author":"roman","year":"2018","journal-title":"ISMIR"},{"key":"ref6","article-title":"Pop music transformer: Generating music with rhythm and harmony","author":"huang","year":"2020","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP.2012.6287832"},{"year":"2010","author":"cuthbert","journal-title":"music21 A toolkit for computer-aided musicology and symbolic music data","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1155\/2007\/48317"},{"year":"2015","author":"magalhaes","journal-title":"Chordify Three years after the launch","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/WASPAA.2017.8170013"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ASPAA.2007.4393050"},{"year":"2004","author":"cemgil","journal-title":"Bayesian music transcription","key":"ref1"},{"key":"ref20","article-title":"Blending acoustic and language model predictions for automatic music transcription","author":"ycart","year":"2019","journal-title":"ISMIR"},{"year":"2010","author":"emiya","journal-title":"MAPS-A Piano Database for Multipitch Estimation and Automatic Transcription of Music","key":"ref22"},{"key":"ref21","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP.2018.8461686"},{"key":"ref41","article-title":"A study on lstm networks for polyphonic music sequence modelling","author":"ycart","year":"2017","journal-title":"ISMIR"},{"key":"ref23","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref26","article-title":"Deep complex networks","author":"trabelsi","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref25","first-page":"175","article-title":"A classification-based polyphonic piano transcription approach using learned feature representations","author":"nam","year":"2011","journal-title":"ISMIR"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412155.pdf?arnumber=9412155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:09:05Z","timestamp":1659485345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412155","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}