{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:19:17Z","timestamp":1775578757730,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"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":[[2024,9,22]]},"DOI":"10.1109\/mlsp58920.2024.10734819","type":"proceedings-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:31:55Z","timestamp":1730745115000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["YourMT3+: Multi-Instrument Music Transcription with Enhanced Transformer Architectures and Cross-Dataset STEM Augmentation"],"prefix":"10.1109","author":[{"given":"Sungkyun","family":"Chang","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}]},{"given":"Holger","family":"Kirchhoff","sequence":"additional","affiliation":[{"name":"Huawei"}]},{"given":"Simon","family":"Dixon","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4361.001.0001"},{"key":"ref3","first-page":"114","article-title":"Song2quartet: A system for generating string quartet cover songs from polyphonic audio of popular music","author":"Percival","year":"2015","journal-title":"ISMIR"},{"key":"ref4","article-title":"MT3: Multi-task multitrack music transcription","author":"Gardner","year":"2021","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096688"},{"key":"ref6","article-title":"YourMT3: a toolkit for training multi-task and multi-track music transcription model for everyone","author":"Chang","year":"2022","journal-title":"in DMRN+17"},{"key":"ref7","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"287","article-title":"RWC music database: Popular, classical and jazz music databases","volume":"2","author":"Goto","year":"2002","journal-title":"ISMIR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475405"},{"key":"ref11","article-title":"Unaligned supervision for automatic music transcription in the wild","author":"Maman","year":"2022","journal-title":"ICML"},{"key":"ref12","first-page":"50","article-title":"Onsets and frames: Dual-obiective Piano transcription","author":"Hawthorne","year":"2018","journal-title":"ISMIR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"},{"issue":"1","key":"ref15","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref16","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref18","article-title":"Learning features of music from scratch","author":"Thickstun","year":"2016","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414601"},{"key":"ref20","volume-title":"MIREX Singing Transcription from Polyphonic Music","year":"2020"},{"key":"ref21","article-title":"Mir_eval: A transparent implementation of common mir metrics","author":"Raffel","year":"2014","journal-title":"ISMIR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3363646"},{"key":"ref24","article-title":"Automatic piano transcription with hierarchical frequency-time transformer","author":"Toyama","year":"2023","journal-title":"ISMIR"},{"key":"ref25","article-title":"Deep audio-visual singing voice transcription based on self-supervised learning models","volume":"abs\/2304.12082","author":"Gu","year":"2023","journal-title":"ArXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2830113"},{"key":"ref27","article-title":"Guitarset: A dataset for guitar transcription","author":"Xi","year":"2018","journal-title":"ISMIR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref29","article-title":"Cutting music source separation some Slakh","author":"Manilow","year":"2019","journal-title":"IEEE WAS- PAA"},{"key":"ref30","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","author":"Shazeer","year":"2018","journal-title":"ICML"},{"key":"ref31","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.11"},{"key":"ref33","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"Hawthorne","year":"2018","journal-title":"ICLR"}],"event":{"name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"London, United Kingdom","start":{"date-parts":[[2024,9,22]]},"end":{"date-parts":[[2024,9,25]]}},"container-title":["2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10734669\/10734712\/10734819.pdf?arnumber=10734819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T03:58:27Z","timestamp":1732679907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10734819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/mlsp58920.2024.10734819","relation":{},"subject":[],"published":{"date-parts":[[2024,9,22]]}}}