{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T18:06:19Z","timestamp":1762020379054,"version":"build-2065373602"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9052987","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"506-510","source":"Crossref","is-referenced-by-count":13,"title":["Improving Music Transcription by Pre-Stacking A U-Net"],"prefix":"10.1109","author":[{"given":"Fabrizio","family":"Pedersoli","sequence":"first","affiliation":[]},{"given":"George","family":"Tzanetakis","sequence":"additional","affiliation":[]},{"given":"Kwang Moo","family":"Yi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518048"},{"article-title":"A probabilistic sub-space model for multi-instrument polyphonic transcription","year":"2010","author":"grindlay","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/COMJ_a_00146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/48317"},{"key":"ref14","first-page":"175","article-title":"A classification-based polyphonic piano transcription approach using learned feature representations","author":"nam","year":"2011","journal-title":"ISMIR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540233"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/ICASSP.2011.5946322","article-title":"Polyphonic music transcription using note onset and offset detection","author":"benetos","year":"2011","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2011 IEEE International Conference on"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2007.4555594"},{"key":"ref18","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","year":"2018","journal-title":"ISMIR"},{"article-title":"Singing voice separation with deep u-net convolutional networks","year":"2017","author":"jansson","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref6","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention Springer"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"article-title":"Learning features of music from scratch","year":"2016","author":"thickstun","key":"ref7"},{"key":"ref2","first-page":"63","article-title":"Deep salience representations for f0 estimation in polyphonic music","author":"bittner","year":"2017","journal-title":"ISMIR"},{"key":"ref9","first-page":"8","article-title":"A probabilistic latent variable model for acoustic modeling","volume":"148","author":"smaragdis","year":"2006","journal-title":"Advances in Models for Acoustic Processing NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.07.001"},{"key":"ref20","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"ISMIR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Very deep convo-lutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref21"},{"journal-title":"Digital Audio Resampling Home Page Center for Compute Research in Music and Acoustics","year":"2015","author":"smith","key":"ref24"},{"article-title":"Ground-truth transcriptions of real music from force-aligned midi syntheses","year":"2003","author":"turetsky","key":"ref23"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref25"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09052987.pdf?arnumber=9052987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:16:36Z","timestamp":1656375396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9052987","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}