{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:15:53Z","timestamp":1766067353256,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414585","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"206-210","source":"Crossref","is-referenced-by-count":5,"title":["Multichannel-based Learning for Audio Object Extraction"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Arteaga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jordi","family":"Pons","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Unsupervised sound separation using mixtures of mixtures","author":"wisdom","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","author":"locatello","year":"2019","journal-title":"ICML"},{"key":"ref12","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"2019","journal-title":"ICLRE"},{"key":"ref13","article-title":"Amplitude panning and the interior pan","volume":"143","author":"thomas","year":"2017","journal-title":"Audio Engineering Society Convention"},{"key":"ref14","article-title":"Multi-task self-supervised learning for robust speech recognition","author":"ravanelli","year":"2020","journal-title":"ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref16","article-title":"Singing voice separation with deep u-net convolutional networks","author":"jansson","year":"2017","journal-title":"ISMIR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref18","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"ISMIR"},{"key":"ref19","article-title":"Music source separation in the waveform domain","author":"d\u00e9fossez","year":"2020","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854167"},{"key":"ref5","article-title":"The flexible audio source separation toolbox version 2.0","author":"sala\u00fcn","year":"2014","journal-title":"ICASSP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054721"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref20","article-title":"Freesound datasets: a platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"ISMIR"},{"article-title":"FSD50k: an open dataset of human-labeled sound events","year":"2020","author":"fonseca","key":"ref22"},{"key":"ref21","article-title":"General-purpose tagging of Freesound audio with audioset labels: Task description, dataset, and baseline","author":"fonseca","year":"2018","journal-title":"Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414585.pdf?arnumber=9414585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:57Z","timestamp":1652182857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414585","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}