{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:30Z","timestamp":1776890070438,"version":"3.51.2"},"reference-count":43,"publisher":"Ubiquity Press, Ltd.","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,17]]},"DOI":"10.5334\/tismir.172","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T10:21:12Z","timestamp":1713349272000},"page":"44-62","source":"Crossref","is-referenced-by-count":8,"title":["The Sound Demixing Challenge 2023 \u2013 Cinematic Demixing Track"],"prefix":"10.5334","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3158-4945","authenticated-orcid":false,"given":"Stefan","family":"Uhlich","sequence":"first","affiliation":[]},{"given":"Giorgio","family":"Fabbro","sequence":"additional","affiliation":[]},{"given":"Masato","family":"Hirano","sequence":"additional","affiliation":[]},{"given":"Shusuke","family":"Takahashi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8597-6795","authenticated-orcid":false,"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3451-171X","authenticated-orcid":false,"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[]},{"given":"Dipam","family":"Chakraborty","sequence":"additional","affiliation":[]},{"given":"Sharada","family":"Mohanty","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7447-3885","authenticated-orcid":false,"given":"Yi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Rongzhi","family":"Gu","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":[]},{"given":"Mikhail","family":"Sukhovei","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":"key20240417110056_B1","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/ASPAA.2003.1285818","volume-title":"2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No. 03TH8684)","year":"2003"},{"key":"key20240417110056_B2","article-title":"aubio\/aubio: 0.4.9","year":"2019"},{"key":"key20240417110056_B3","first-page":"246","article-title":"Deep attractor network for single-microphone speaker separation","year":"2017"},{"key":"key20240417110056_B4","article-title":"FMA: A dataset for music analysis","year":"2016","journal-title":"arXiv preprint arXiv:1612.01840"},{"key":"key20240417110056_B5","first-page":"9271","article-title":"ICASSP 2022 Deep Noise Suppression Challenge","year":"2022"},{"issue":"1","key":"key20240417110056_B6","doi-asserted-by":"crossref","first-page":"63","DOI":"10.5334\/tismir.171","article-title":"The Sound Demixing Challenge 2023 \u2013 Music Demixing Track","volume":"7","year":"2024","journal-title":"Transactions of the International Society for Music Information Retrieval"},{"key":"key20240417110056_B7","first-page":"829","article-title":"FSD50K: An open dataset of humanlabeled sound events","volume":"30","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"key20240417110056_B8","first-page":"869","article-title":"Dialogue enhancement of stereo sound","year":"2015"},{"key":"key20240417110056_B9","first-page":"3734","article-title":"Deep neural networks for single channel source separation","year":"2014"},{"key":"key20240417110056_B10","first-page":"31","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","year":"2016"},{"key":"key20240417110056_B11","first-page":"57","article-title":"Singing-voice separation from monaural recordings using robust principal component analysis","year":"2012"},{"key":"key20240417110056_B12","unstructured":"International Telecommunications Union (2015). ITUR BS.1770-4: Algorithms to measure audio programme loudness and true-peak audio level. https:\/\/www.itu.int\/rec\/R-REC-BS.1770."},{"key":"key20240417110056_B13","article-title":"Kuielab-mdx-net: A two-stream neural network for music demixing","year":"2021","journal-title":"arXiv preprint arXiv:2111.12203"},{"key":"key20240417110056_B14","article-title":"Adam: A method for stochastic optimization","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"key20240417110056_B15","first-page":"626","article-title":"SDR \u2013 Half-baked or well done?","year":"2019"},{"key":"key20240417110056_B16","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"},{"key":"key20240417110056_B17","article-title":"Automatic music mixing with deep learning and out-of-domain data","year":"2022"},{"key":"key20240417110056_B18","unstructured":"Masri, P. (1996). Computer Modelling of Sound for Transformation and Synthesis of Musical Signals. PhD thesis, University of Bristol."},{"key":"key20240417110056_B19","first-page":"18","article-title":"Music Demixing Challenge 2021","volume":"1","year":"2022","journal-title":"Frontiers in Signal Processing"},{"key":"key20240417110056_B20","first-page":"5206","article-title":"Librispeech: An ASR corpus based on public domain audio books","year":"2015"},{"issue":"7\/8","key":"key20240417110056_B21","doi-asserted-by":"crossref","first-page":"510","DOI":"10.17743\/jaes.2019.0032","article-title":"Source separation for enabling dialogue enhancement in object-based broadcast with MPEG-H","volume":"67","year":"2019","journal-title":"Journal of the Audio Engineering Society"},{"key":"key20240417110056_B22","first-page":"31","article-title":"Tackling the cocktail fork problem for separation and transcription of real-world soundtracks","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"key20240417110056_B23","first-page":"526","article-title":"The cocktail fork problem: Three-stem audio separation for real-world soundtracks","year":"2022"},{"key":"key20240417110056_B24","article-title":"MUSDB18-HQ \u2013 an uncompressed version of MUSDB18","year":"2019"},{"key":"key20240417110056_B25","article-title":"Hybrid transformers for music source separation","year":"2023"},{"key":"key20240417110056_B26","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":"key20240417110056_B27","first-page":"51","article-title":"All for one and one for all: Improving music separation by bridging networks","year":"2021"},{"key":"key20240417110056_B28","article-title":"Benchmarks and leaderboards for sound demixing tasks","year":"2023","journal-title":"arXiv preprint arXiv:2305.07489"},{"key":"key20240417110056_B29","unstructured":"Sound Effects Wiki (2024). Godzilla roar. https:\/\/soundeffects.fandom.com\/wiki\/Godzilla_Roar [Accessed: 2024-01-15]."},{"key":"key20240417110056_B30","volume-title":"Audio Engineering Society Convention 150","year":"2021"},{"key":"key20240417110056_B31","first-page":"293","article-title":"The 2018 Signal Separation Evaluation Campaign","year":"2018"},{"issue":"41","key":"key20240417110056_B32","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":"key20240417110056_B33","article-title":"Dialog+ in broadcasting: First field tests using deep-learning-based dialogue enhancement","year":"2021","journal-title":"arXiv preprint arXiv:2112.09494"},{"key":"key20240417110056_B34","first-page":"441","article-title":"Stereo panning features for classifying recording production style","year":"2007"},{"key":"key20240417110056_B35","volume-title":"Audio Engineering Society Convention 125","year":"2008"},{"key":"key20240417110056_B36","first-page":"2135","article-title":"Deep neural network based instrument extraction from music","year":"2015"},{"key":"key20240417110056_B37","first-page":"261","article-title":"Improving music source separation based on deep neural networks through data augmentation and network blending","year":"2017"},{"key":"key20240417110056_B38","first-page":"552","article-title":"First stereo audio source separation evaluation campaign: Data, algorithms and results","year":"2007"},{"key":"key20240417110056_B39","article-title":"A generalized bandsplit neural network for cinematic audio source separation","year":"2023","journal-title":"IEEE Open Journal of Signal Processing"},{"key":"key20240417110056_B40","first-page":"900","article-title":"Differentiable consistency constraints for improved deep speech enhancement","year":"2019"},{"key":"key20240417110056_B41","first-page":"241","article-title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","year":"2017"},{"key":"key20240417110056_B42","article-title":"TSpeech-AI system description to the 5th Deep Noise Suppression (DNS) Challenge","year":"2023"},{"key":"key20240417110056_B43","article-title":"High fidelity speech enhancement with band-split RNN","year":"2022","journal-title":"arXiv preprint arXiv:2212.00406"}],"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\/172\/661fc9bdf1264.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T08:00:44Z","timestamp":1761552044000},"score":1,"resource":{"primary":{"URL":"https:\/\/transactions.ismir.net\/articles\/10.5334\/tismir.172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,4,17]]}},"alternative-id":["10.5334\/tismir.172"],"URL":"https:\/\/doi.org\/10.5334\/tismir.172","relation":{},"ISSN":["2514-3298"],"issn-type":[{"value":"2514-3298","type":"print"}],"subject":[],"published":{"date-parts":[[2024]]}}}