{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:40:31Z","timestamp":1779385231808,"version":"3.53.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3252272","type":"journal-article","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T18:24:43Z","timestamp":1677867883000},"page":"1276-1289","source":"Crossref","is-referenced-by-count":29,"title":["Unsupervised Music Source Separation Using Differentiable Parametric Source Models"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8397-7914","authenticated-orcid":false,"given":"Kilian","family":"Schulze-Forster","sequence":"first","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-0010","authenticated-orcid":false,"given":"Ga\u00ebl","family":"Richard","sequence":"additional","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liam","family":"Kelley","sequence":"additional","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8739-4510","authenticated-orcid":false,"given":"Clement S. J.","family":"Doire","sequence":"additional","affiliation":[{"name":"Sonos Inc., Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9630-6877","authenticated-orcid":false,"given":"Roland","family":"Badeau","sequence":"additional","affiliation":[{"name":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2874719"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207052"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref4","article-title":"D3Net: Densely connected multidilated densenet for music source separation","author":"Takahashi","year":"2020"},{"key":"ref5","article-title":"Demucs: Deep extractor for music sources with extra unlabeled data remixed","author":"Dfossez","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref7","article-title":"Analysis of intonation in unison choir singing","volume-title":"Proc. Int. Conf. Music Percep. Cogn.","author":"Cuesta","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287834"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158801"},{"key":"ref12","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wisdom","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632714"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3115"},{"key":"ref15","article-title":"Bootstrapping unsupervised deep music separation from primitive auditory grouping principles","volume-title":"Proc. Workshop Self-Supervision Audio Speech 37th Int. Conf. Mach. Learn.","author":"Seetharaman","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3218802"},{"key":"ref17","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engel","year":"2019"},{"key":"ref18","first-page":"302","article-title":"Multiple f0 estimation in vocal ensembles using convolutional neural networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Cuesta","year":"2020"},{"key":"ref19","first-page":"552","article-title":"Multi-pitch detection and voice assignment for a cappella recordings of multiple singers","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Schramm","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref23","first-page":"733","article-title":"Deep learning based source separation applied to choir ensembles","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Petermann","year":"2020"},{"key":"ref24","first-page":"231","article-title":"Score-informed source separation of choral music","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Gover","year":"2020"},{"key":"ref25","first-page":"159","article-title":"Conditioned-U-Net: Introducing a control mechanism in the U-Net for multiple source separations","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Meseguer-Brocal","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3037487"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413358"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683520"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683201"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683704"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016905"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3005031"},{"key":"ref34","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. Symp. Oper. Syst. Des. Implementation","author":"Abadi","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.08.010"},{"key":"ref38","first-page":"327","article-title":"Musical instrument recognition in polyphonic audio using source-filter model for sound separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Heittola","year":"2009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/3680788"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.1993.379970"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(96)00038-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"key":"ref43","article-title":"Self-supervised pitch detection by inverse audio synthesis","volume-title":"in Proc. Workshop Self-Supervision Audio Speech Int. Conf. Mach. Learn.","author":"Engel","year":"2020"},{"key":"ref44","volume-title":"The Art of Electronics","author":"Horowitz","year":"2002"},{"key":"ref45","first-page":"216","article-title":"Multiple fundamental frequency estimation by summing harmonic amplitudes","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Klapuri","year":"2006"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3007794"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31807-1_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2015.1136650"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/w14-4012"},{"key":"ref50","article-title":"Layer normalization","author":"Ba","year":"2016"},{"issue":"1","key":"ref51","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"30","author":"Maas","year":"2013"},{"key":"ref52","volume-title":"Spectral Audio Signal Processing: Frequency Sampling Method","author":"Smith","year":"2011"},{"key":"ref53","volume-title":"Spectral Audio Signal Processing: Generalized Window Method","author":"Smith","year":"2011"},{"key":"ref54","volume-title":"Theory and Applications of Digital Speech Processing","author":"Rabiner","year":"2010"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/sapm1946251261"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2307\/1401322"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1121\/1.1995189"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/0471668850"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172448"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164983"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.09.003"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1121\/1.398894"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_28"},{"key":"ref66","volume-title":"The Basic Practice of Statistics","volume":"2","author":"Moore","year":"2007"},{"key":"ref67","first-page":"279","article-title":"Robust tests for equality of variances","volume-title":"Contributions Probability Statist. Essays Honor Harold Hotelling","author":"Levene","year":"1961"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2307\/2332510"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref70","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10058592.pdf?arnumber=10058592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T07:08:33Z","timestamp":1710400113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10058592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3252272","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}