{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T19:05:00Z","timestamp":1771614300383,"version":"3.50.1"},"reference-count":47,"publisher":"Ubiquity Press, Ltd.","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,18]]},"DOI":"10.5334\/tismir.171","type":"journal-article","created":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T08:21:21Z","timestamp":1713428481000},"page":"63-84","source":"Crossref","is-referenced-by-count":19,"title":["The Sound Demixing Challenge 2023 \u2013 Music Demixing Track"],"prefix":"10.5334","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6302-9033","authenticated-orcid":false,"given":"Giorgio","family":"Fabbro","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3158-4945","authenticated-orcid":false,"given":"Stefan","family":"Uhlich","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3059-929X","authenticated-orcid":false,"given":"Chieh-Hsin","family":"Lai","sequence":"additional","affiliation":[]},{"given":"Woosung","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Mart\u00ednez-Ram\u00edrez","sequence":"additional","affiliation":[]},{"given":"Weihsiang","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Igor","family":"Gadelha","sequence":"additional","affiliation":[]},{"given":"Geraldo","family":"Ramos","sequence":"additional","affiliation":[]},{"given":"Eddie","family":"Hsu","sequence":"additional","affiliation":[]},{"given":"Hugo","family":"Rodrigues","sequence":"additional","affiliation":[]},{"given":"Fabian-Robert","family":"St\u00f6ter","sequence":"additional","affiliation":[]},{"given":"Alexandre","family":"D\u00e9fossez","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Dipam","family":"Chakraborty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4578-0170","authenticated-orcid":false,"given":"Sharada","family":"Mohanty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0312-452X","authenticated-orcid":false,"given":"Roman","family":"Solovyev","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5585-014X","authenticated-orcid":false,"given":"Alexander","family":"Stempkovskiy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3940-8639","authenticated-orcid":false,"given":"Tatiana","family":"Habruseva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3960-5627","authenticated-orcid":false,"given":"Nabarun","family":"Goswami","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3712-3691","authenticated-orcid":false,"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[]},{"given":"Minseok","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2740-2006","authenticated-orcid":false,"given":"Jun","family":"Hyung Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5208-9447","authenticated-orcid":false,"given":"Yuanliang","family":"Dong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9055-061X","authenticated-orcid":false,"given":"Xinran","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5530-8744","authenticated-orcid":false,"given":"Jiafeng","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6806-6140","authenticated-orcid":false,"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[]}],"member":"3285","reference":[{"key":"key20240418092809_B1","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","year":"2014"},{"key":"key20240418092809_B2","first-page":"72","article-title":"A consolidated view of loss functions for supervised deep learningbased speech enhancement","year":"2020"},{"key":"key20240418092809_B3","article-title":"Learning with instance-dependent label noise: A sample sieve approach","year":"2020","journal-title":"arXiv preprint arXiv:2010.02347"},{"key":"key20240418092809_B4","first-page":"192","article-title":"Investigating U-Nets with various intermediate blocks for spectrogram-based singing voice separation","year":"2020"},{"key":"key20240418092809_B5","article-title":"Hybrid spectrogram and waveform source separation","year":"2021"},{"key":"key20240418092809_B6","first-page":"220","article-title":"Leveraging hierarchical structures for fewshot musical instrument recognition","year":"2021"},{"key":"key20240418092809_B7","first-page":"31","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"key20240418092809_B8","first-page":"8340","article-title":"The many faces of robustness: A critical analysis of out-of-distribution generalization","year":"2021"},{"issue":"50","key":"key20240418092809_B9","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.21105\/joss.02154","article-title":"Spleeter: A fast and efficient music source separation tool with pre-trained models","volume":"5","year":"2020","journal-title":"Journal of Open Source Software"},{"key":"key20240418092809_B10","first-page":"569","volume-title":"Advances in Neural Information Processing Systems 19 (NIPS-06)","year":"2007"},{"key":"key20240418092809_B11","first-page":"abs\/1503.02531","article-title":"Distilling the knowledge in a neural network","year":"2015","journal-title":"ArXiv"},{"key":"key20240418092809_B12","first-page":"abs\/2004.14589","article-title":"Improved natural language generation via loss truncation","year":"2020","journal-title":"ArXiv"},{"key":"key20240418092809_B13","article-title":"KUIELab-MDX-Net: A two-stream neural network for music demixing","year":"2021"},{"key":"key20240418092809_B14","first-page":"arXiv:2306.09382","article-title":"Sound Demixing Challenge 2023 \u2013 Music Demixing Track technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"key20240418092809_B15","doi-asserted-by":"crossref","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","article-title":"PANNs: Large-scale pretrained audio neural networks for audio pattern recognition","volume":"28","year":"2020","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"key20240418092809_B16","article-title":"Self-refining of pseudo labels for music source separation with noisy labeled data","year":"2023","journal-title":"arXiv preprint arXiv:2307.12576"},{"key":"key20240418092809_B17","article-title":"Robust subspace recovery layer for unsupervised anomaly detection","year":"2019","journal-title":"arXiv preprint arXiv:1904.00152"},{"key":"key20240418092809_B18","first-page":"3538","article-title":"Robust variational autoencoding with Wasserstein penalty for novelty detection","year":"2023"},{"key":"key20240418092809_B19","article-title":"Dividemix: Learning with noisy labels as semi-supervised learning","year":"2020","journal-title":"arXiv preprint arXiv:2002.07394"},{"key":"key20240418092809_B20","article-title":"Channelwise subband input for better voice and accompaniment separation on high resolution music","year":"2020","journal-title":"Interspeech"},{"key":"key20240418092809_B21","first-page":"323","volume-title":"Latent Variable Analysis and Signal Separation","year":"2017"},{"key":"key20240418092809_B22","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.1109\/TASLP.2023.3271145","article-title":"Music source separation with band-split RNN","volume":"31","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"key20240418092809_B23","first-page":"351","article-title":"Deep neural network for musical instrument recognition using MFCCs","volume":"25","year":"2021","journal-title":"Computacion y Sistemas"},{"key":"key20240418092809_B24","article-title":"Hierarchical musical instrument separation","year":"2020"},{"key":"key20240418092809_B25","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/WASPAA.2019.8937170","volume-title":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","year":"2019"},{"key":"key20240418092809_B26","first-page":"18","article-title":"Music Demixing Challenge 2021","volume":"1","year":"2022","journal-title":"Frontiers in Signal Processing"},{"key":"key20240418092809_B27","first-page":"7850","article-title":"Outlier-robust optimal transport","year":"2021"},{"key":"key20240418092809_B28","first-page":"387","volume-title":"Latent Variable Analysis and Signal Separation","year":"2015"},{"key":"key20240418092809_B29","first-page":"619","article-title":"MoisesDB: A dataset for source separation beyond 4-stems","year":"2023"},{"key":"key20240418092809_B30","article-title":"The cocktail fork problem: Threestem audio separation for real-world soundtracks","year":"2022"},{"key":"key20240418092809_B31","article-title":"Freischutz Digital: Demos of audio-related contributions","year":"2015"},{"key":"key20240418092809_B32","article-title":"The MUSDB18 corpus for music separation","year":"2017"},{"key":"key20240418092809_B33","article-title":"Hybrid transformers for music source separation","year":"2023"},{"key":"key20240418092809_B34","article-title":"The whole is greater than the sum of its parts: Improving DNNbased music source separation","year":"2023","journal-title":"arXiv preprint arXiv:2305.07855"},{"key":"key20240418092809_B35","first-page":"51","article-title":"All for one and one for all: Improving music separation by bridging networks","year":"2021"},{"key":"key20240418092809_B36","article-title":"Benchmarks and leaderboards for sound demixing tasks","year":"2023","journal-title":"arXiv preprint arXiv:2305.07489"},{"key":"key20240418092809_B37","first-page":"293","volume-title":"Latent Variable Analysis and Signal Separation","year":"2018"},{"issue":"41","key":"key20240418092809_B38","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.21105\/joss.01667","article-title":"Open-unmix \u2013 A reference implementation for music source separation","volume":"4","year":"2019","journal-title":"Journal of Open Source Software"},{"key":"key20240418092809_B39","first-page":"30","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"key20240418092809_B40","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1109\/TASLP.2021.3069302","article-title":"Objective measures of perceptual audio quality reviewed: An evaluation of their application domain dependence","volume":"29","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"key20240418092809_B41","doi-asserted-by":"crossref","first-page":"44","DOI":"10.5334\/tismir.172","article-title":"The Sound Demixing Challenge 2023 \u2013 Cinematic Demixing Track","volume":"7","year":"2024","journal-title":"Transactions of the International Society for Music Information Retrieval"},{"key":"key20240418092809_B42","first-page":"261","article-title":"Improving music source separation based on deep neural networks through data augmentation and network blending","year":"2017"},{"key":"key20240418092809_B43","article-title":"Promix: Combating label noise via maximizing clean sample utility","year":"2022","journal-title":"arXiv preprint arXiv:2207.10276"},{"key":"key20240418092809_B44","first-page":"31","article-title":"Semi-supervised singing voice separation with noisy self-training","year":"2021"},{"key":"key20240418092809_B45","first-page":"900","article-title":"Differentiable consistency constraints for improved deep speech enhancement","year":"2019"},{"key":"key20240418092809_B46","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume":"33","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"key20240418092809_B47","first-page":"749","article-title":"Road extraction by deep residual U-Net","volume":"15","year":"2017","journal-title":"IEEE Geoscience and Remote Sensing Letters"}],"container-title":["Transactions of the International Society for Music Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/storage.googleapis.com\/jnl-up-j-tismir-files\/journals\/1\/articles\/171\/66210ffd7fc02.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T08:00:45Z","timestamp":1761552045000},"score":1,"resource":{"primary":{"URL":"https:\/\/transactions.ismir.net\/articles\/10.5334\/tismir.171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,4,18]]}},"alternative-id":["10.5334\/tismir.171"],"URL":"https:\/\/doi.org\/10.5334\/tismir.171","relation":{},"ISSN":["2514-3298"],"issn-type":[{"value":"2514-3298","type":"print"}],"subject":[],"published":{"date-parts":[[2024]]}}}