{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T18:39:22Z","timestamp":1770143962971,"version":"3.49.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688348","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Annotation-Free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion"],"prefix":"10.1109","author":[{"given":"Gakusei","family":"Sato","sequence":"first","affiliation":[{"name":"Sony Computer Science Laboratories,Tokyo,Japan"}]},{"given":"Taketo","family":"Akama","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sequence-to-sequence piano transcription with transformers","volume-title":"Proceedings of ISMIR","author":"Hawthorne"},{"key":"ref2","article-title":"MT3: multi-task multitrack music transcription","volume-title":"Proceedings of ICLR","author":"Gardner"},{"key":"ref3","article-title":"Automatic piano transcription with hierarchical frequency-time transformer","volume-title":"Proceedings of ISMIR","author":"Toyama"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746549"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096688"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46282-0_20","article-title":"Escaping from the abyss of manual annotation: New methodology of building polyphonic datasets for automatic music transcription","volume-title":"Proceedings of CMMR","author":"Su"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref9","article-title":"Unaligned supervision for automatic music transcription in-the-wild","volume-title":"Proceedings of ICML","author":"Maman"},{"key":"ref10","article-title":"Sequence-to-sequence network training methods for automatic guitar transcription with tokenized outputs","volume-title":"Proceedings of ISMIR","author":"Kim"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475405"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"ref16","article-title":"Scaling polyphonic transcription with mixtures of monophonic transcriptions","volume-title":"Proceedings of ISMIR","author":"Ian"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00704"},{"key":"ref19","article-title":"A closer look at smoothness in domain adversarial training","volume-title":"Proceedings of ICML","author":"Rangwani"},{"key":"ref20","article-title":"Deep domain confusion: Maximizing for domain invariance","volume-title":"Proceedings of CVPR","author":"Tzeng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref22","article-title":"Multi-pitch estimation meets microphone mismatch: Applicability of domain adaptation","volume-title":"Proceedings of ISMIR","author":"Bittner"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3045915"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097250"},{"key":"ref25","article-title":"A universal music translation network","volume-title":"Proceedings of ICLR","author":"Mor"},{"key":"ref26","article-title":"MidiTok: A python package for MIDI file tokenization","author":"Fradet","year":"2021","journal-title":"Late-Breaking Demo of ISMIR"},{"key":"ref27","article-title":"Attention is all you need","volume-title":"Proceedings of NIPS","author":"Vaswani"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030482"},{"key":"ref29","article-title":"mir eval: A transparent implementation of common mir metrics","volume-title":"Proceedings of ISMIR","author":"Raffel"},{"key":"ref30","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"Engel","year":"2017"},{"key":"ref31","article-title":"The million song dataset","volume-title":"Proceedings of ISMIR","author":"Bertin-Mahieux"},{"key":"ref32","article-title":"Guitarset: A dataset for guitar transcription","volume-title":"Proceedings of ISMIR","author":"Xi"},{"key":"ref33","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","volume-title":"Proceedings of ICLR","author":"Hawthorne"},{"key":"ref34","article-title":"Evaluation framework for automatic singing transcription","volume-title":"Proceedings of ISMIR","author":"Molina"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/8363507"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178063"},{"key":"ref37","author":"Thickstun","year":"2016","journal-title":"Learning features of music from scratch"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688348.pdf?arnumber=10688348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:26:15Z","timestamp":1727763975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688348","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}