{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:32:00Z","timestamp":1776889920490,"version":"3.51.2"},"reference-count":69,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014462","name":"Mitsubishi Electric Research Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014462","id-type":"DOI","asserted-by":"publisher"}]}],"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.2023.3290428","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T17:30:33Z","timestamp":1689269433000},"page":"2592-2605","source":"Crossref","is-referenced-by-count":10,"title":["Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-5752","authenticated-orcid":false,"given":"Darius","family":"Petermann","sequence":"first","affiliation":[{"name":"Department of Intelligent Systems Engineering, Indiana University Bloomington, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8597-6795","authenticated-orcid":false,"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4446-001X","authenticated-orcid":false,"given":"Aswin Shanmugam","family":"Subramanian","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4204-9430","authenticated-orcid":false,"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3451-171X","authenticated-orcid":false,"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746005"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5594\/J11396"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2210"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref52","first-page":"316","article-title":"FMA: A dataset for music analysis","author":"defferrard","year":"0","journal-title":"Proc ISMIR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3013105"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1728"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053921"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3088949"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414254"},{"key":"ref48","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref42","first-page":"9880","article-title":"Perceptual evaluation of source separation for remixing music","author":"wierstorf","year":"0","journal-title":"Proc Audio Eng Soc Conv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2022.808594"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414044"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"ref7","article-title":"Open-unmix - a reference implementation for music source separation","volume":"4","author":"st\u00f6ter","year":"2019","journal-title":"Open Source Software"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref4","article-title":"SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition","author":"drude","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref6","article-title":"The MUSDB18 corpus for music separation","author":"rafii","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref40","first-page":"381","article-title":"A unified model for zero-shot music source separation, transcription and synthesis","author":"lin","year":"0","journal-title":"Proc ISMIR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746347"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746077"},{"key":"ref36","first-page":"205","article-title":"Improving sound event detection in domestic environments using sound separation","author":"turpault","year":"0","journal-title":"Proc DCASE"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632756"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3126931"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-302"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040522"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054567"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937250"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683800"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2757"},{"key":"ref69","first-page":"575","article-title":"Towards robust music source separation on loud commercial music","author":"jeon","year":"0","journal-title":"Proc ISMIR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054340"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336885"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413678"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref21","first-page":"314","article-title":"Remixing stereo music with score-informed source separation","author":"woodruff","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.14311\/1251"},{"key":"ref27","first-page":"748","article-title":"Multitask learning for instrument activation aware music source separation","author":"hung","year":"0","journal-title":"Proc ISMIR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414445"},{"key":"ref60","first-page":"337","article-title":"Perceptual quality assessment for digital audio: PEAQ-the new ITU standard for objective measurement of the perceived audio quality","author":"colomes","year":"0","journal-title":"Proc AES 17th Int Conf High Qual Audio Coding"},{"key":"ref62","article-title":"P862.2: Wideband extension to recommendation P.862 for the assessment of wideband telephone networks and speech codecs","year":"2007"},{"key":"ref61","article-title":"An examination and interpretation of ITU-R BS. 1387: Perceptual evaluation of audio quality","author":"kabal","year":"2002"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10183662.pdf?arnumber=10183662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T17:35:53Z","timestamp":1691516153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10183662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3290428","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}