{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T20:54:14Z","timestamp":1782766454257,"version":"3.54.5"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:00:00Z","timestamp":1635120000000},"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":[[2021,10,25]]},"DOI":"10.1109\/mlsp52302.2021.9596406","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T22:53:58Z","timestamp":1637016838000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Deep Variational Generative Models for Audio-Visual Speech Separation"],"prefix":"10.1109","author":[{"given":"Viet-Nhat","family":"Nguyen","sequence":"first","affiliation":[{"name":"RobotLearn Team at Inria Grenoble Rhône-Alpes,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mostafa","family":"Sadeghi","sequence":"additional","affiliation":[{"name":"RobotLearn Team at Inria Grenoble Rhône-Alpes,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"Università degli Studi di Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[{"name":"RobotLearn Team at Inria Grenoble Rhône-Alpes,France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053730"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3066038"},{"key":"ref14","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref17","author":"abdelaziz","year":"2017","journal-title":"Ntcd-timit"},{"key":"ref18","author":"thiemann","year":"2013","journal-title":"DEMAND a collection of multi-channel recordings of acoustic noise in diverse environments"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref4","first-page":"1245","article-title":"A new independent component analysis for speech recognition and separation","volume":"14","author":"chien","year":"2006","journal-title":"IEEE\/ACM TASLP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73031-8_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref2","first-page":"535","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2000","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"}],"event":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Gold Coast, Australia","start":{"date-parts":[[2021,10,25]]},"end":{"date-parts":[[2021,10,28]]}},"container-title":["2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9596063\/9596068\/09596406.pdf?arnumber=9596406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:30:13Z","timestamp":1659483013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9596406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,25]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/mlsp52302.2021.9596406","relation":{},"subject":[],"published":{"date-parts":[[2021,10,25]]}}}