{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:29:26Z","timestamp":1776882566842,"version":"3.51.2"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ANR ML3RI","award":["ANR-19-CE33-0008-01"],"award-info":[{"award-number":["ANR-19-CE33-0008-01"]}]},{"name":"ANR-3IA MIAI","award":["ANR-19-P3IA-0003"],"award-info":[{"award-number":["ANR-19-P3IA-0003"]}]},{"name":"H2020 SPRING","award":["GA 871245"],"award-info":[{"award-number":["GA 871245"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tsp.2021.3066038","type":"journal-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T19:34:51Z","timestamp":1616009691000},"page":"1899-1909","source":"Crossref","is-referenced-by-count":23,"title":["Mixture of Inference Networks for VAE-Based Audio-Visual Speech Enhancement"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0272-8017","authenticated-orcid":false,"given":"Mostafa","family":"Sadeghi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-1084","authenticated-orcid":false,"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"TIMIT acoustic phonetic continuous speech corpus","volume":"33","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref33","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref32","article-title":"Switching variational auto-encoders for noise-agnostic audio-visual speech enhancement","author":"sadeghi","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053730"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref37","first-page":"3752","article-title":"NTCD-TIMIT: A. new database and baseline for noise-robust audio-visual speech recognition","author":"abdelaziz","year":"0","journal-title":"Proc Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2679692"},{"key":"ref40","article-title":"Dynamical variational autoencoders: A comprehensive review","author":"girin","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74494-8_52"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946317"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2498101"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref16","first-page":"1","article-title":"A variance modeling framework based on variational autoencoders for speech enhancement","author":"leglaive","year":"0","journal-title":"Proc IEEE Int Workshop Mach Learn Signal Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659591"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1398"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682546"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/PROC.1979.11540","article-title":"enhancement and bandwidth compression of noisy speech","volume":"67","author":"lim","year":"1979","journal-title":"Proceedings of the IEEE"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.1358887"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref8","first-page":"4029","article-title":"Speech denoising using nonnegative matrix factorization with priors","author":"wilson","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937218"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1002\/9781119279860","author":"vincent","year":"2018","journal-title":"Audio Source Separation and Speech Enhancement"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01217"},{"key":"ref22","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref21","article-title":"Deep variational generative models for audio-visual speech separation","author":"nhat nguyen","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029977"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref23","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206274"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2953020"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/9307529\/09380713.pdf?arnumber=9380713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T09:20:23Z","timestamp":1698052823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9380713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/tsp.2021.3066038","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}