{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T12:27:55Z","timestamp":1765369675507,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9207605","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-6","source":"Crossref","is-referenced-by-count":14,"title":["The Impact of Audio Input Representations on Neural Network based Music Transcription"],"prefix":"10.1109","author":[{"given":"Kin Wai","family":"Cheuk","sequence":"first","affiliation":[]},{"given":"Kat","family":"Agres","sequence":"additional","affiliation":[]},{"given":"Dorien","family":"Herremans","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Deep complex networks","year":"2017","author":"trabelsi","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/app7090901"},{"key":"ref11","article-title":"Onsets and frames: Dual-objective piano transcription","author":"hawthorne","year":"2017","journal-title":"ISMIR"},{"article-title":"Maps-a piano database for multipitch estimation and automatic transcription of music","year":"2010","author":"emiya","key":"ref12"},{"key":"ref13","article-title":"Mel frequency cepstral coefficients for music modeling","author":"logan","year":"2000","journal-title":"ISMIR"},{"key":"ref14","article-title":"On the potential of simple framewise approaches to piano transcription","author":"kelz","year":"2016","journal-title":"ISMIR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923806"},{"article-title":"nnaudio: An on-the-fly gpu audio to spectrogram conversion toolbox using 1D convolution neural networks","year":"2019","author":"cheuk","key":"ref16"},{"key":"ref17","article-title":"nnaudio: A pytorch audio processing tool using 1D convolution neural networks","author":"cheuk","year":"2019","journal-title":"Proc ISMIR–Late Breaking Demo"},{"article-title":"Learning features of music from scratch","year":"2016","author":"thickstun","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461660"},{"key":"ref4","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/19.769633"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0258-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2007.4393050"},{"year":"0","key":"ref29","article-title":"Melodyne"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/48317"},{"key":"ref8","first-page":"2241","article-title":"Invariances and data augmentation for supervised music transcription","author":"thickstun","year":"2017","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287832"},{"journal-title":"Introduction to Braille Music Transcription","year":"2006","author":"klapuri","key":"ref2"},{"key":"ref9","article-title":"Deep complex networks","author":"trabelsi","year":"2017","journal-title":"ArXiv"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758101"},{"key":"ref22","first-page":"175","article-title":"The htk book","volume":"3","author":"young","year":"2002","journal-title":"Cambridge University Engineering Department"},{"journal-title":"Speech Communication Human and Machine","year":"1987","author":"o\u2019shaughnessy","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1978.1170547"},{"key":"ref26","article-title":"Mir_eval: A transparent implementation of common mir metrics","author":"raffel","year":"2014","journal-title":"ISMIR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.404385"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09207605.pdf?arnumber=9207605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:50:33Z","timestamp":1656453033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9207605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9207605","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}