{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:45:31Z","timestamp":1777938331784,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746950","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"736-740","source":"Crossref","is-referenced-by-count":14,"title":["An End-to-End Deep Learning Framework For Multiple Audio Source Separation And Localization"],"prefix":"10.1109","author":[{"given":"Yu","family":"Chen","sequence":"first","affiliation":[{"name":"University of Michigan,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Michigan,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Michigan,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hun-Seok","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Michigan,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053921"},{"key":"ref14","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"arXiv preprint arXiv 1806 03185"},{"key":"ref15","first-page":"626","article-title":"Sdr–half-baked or well done?","author":"le roux","year":"2019","journal-title":"ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref17","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SAM.2018.8448644"},{"key":"ref19","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2851147"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/APS.2005.1552745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461267"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s18103418"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1248813"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054090"},{"key":"ref20","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020","journal-title":"arXiv preprint arXiv 2005 11084"},{"key":"ref22","article-title":"Towards principled methods for training generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"ICLRE"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054172"},{"key":"ref24","first-page":"182","article-title":"Av16. 3: An audio-visual corpus for speaker localization and tracking","author":"lathoud","year":"2004","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.4740503"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746950.pdf?arnumber=9746950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T17:54:15Z","timestamp":1729101255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746950","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}