{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T02:34:03Z","timestamp":1771036443724,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T00:00:00Z","timestamp":1441065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000098","name":"NIH Clinical Center","doi-asserted-by":"publisher","award":["R01-MH-073174"],"award-info":[{"award-number":["R01-MH-073174"]}],"id":[{"id":"10.13039\/100000098","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1109\/tcyb.2014.2362101","type":"journal-article","created":{"date-parts":[[2014,10,20]],"date-time":"2014-10-20T18:36:22Z","timestamp":1413830182000},"page":"1927-1941","source":"Crossref","is-referenced-by-count":45,"title":["Temporal Bayesian Fusion for Affect Sensing: Combining Video, Audio, and Lexical Modalities"],"prefix":"10.1109","volume":"45","author":[{"given":"Arman","family":"Savran","sequence":"first","affiliation":[]},{"family":"Houwei Cao","sequence":"additional","affiliation":[]},{"given":"Ani","family":"Nenkova","sequence":"additional","affiliation":[]},{"given":"Ragini","family":"Verma","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"805","DOI":"10.21437\/Interspeech.2008-246","article-title":"Balancing spoken content adaptation and unit length in the recognition of emotion and interest","author":"vlasenko","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.04.002"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref32","year":"2012","journal-title":"AVEC 2012 2nd International Audio\/Visual Emotion Challenge and Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388781"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388782"},{"key":"ref37","first-page":"195","article-title":"Desperately seeking emotions or: Actors, wizards, and human beings","author":"batliner","year":"2000","journal-title":"Proc ISCA workshop Speech Emotion"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","article-title":"Toward detecting emotions in spoken dialogs","volume":"13","author":"lee","year":"2005","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388783"},{"key":"ref40","first-page":"427","article-title":"Distribution of the estimators for autoregressive time series with a unit root","volume":"74","author":"dickey","year":"1979","journal-title":"J Amer Stat Assoc"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.11.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388776"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"805","DOI":"10.21437\/Interspeech.2005-379","article-title":"Speaker independent emotion recognition by early fusion of acoustic and linguistic features within ensembles","author":"schuller","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-009-0025-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_14"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.927269"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.37"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2007.02024.x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388780"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4018\/jse.2010101605"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/978-3-642-24571-8_53","article-title":"AVEC 2011, the audio\/visual emotion challenge","author":"schuller","year":"2011","journal-title":"Proc Int Conf Affect Comput Intell Interact"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.1"},{"key":"ref8","author":"ekman","year":"2002","journal-title":"Facial Action Coding System"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(02)00052-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.08.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2171334"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388686"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2193567"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.17"},{"key":"ref21","first-page":"268","article-title":"Robust speech recognition and understanding","author":"kim","year":"2007","journal-title":"Bimodal Emotion Recognition Using Speech and Physiological Changes"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/T-AFFC.2010.16","article-title":"Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels","volume":"2","author":"wu","year":"2011","journal-title":"IEEE Trans Affect Comput"},{"key":"ref41","author":"pitt","year":"2001","journal-title":"Sequential Monte Carlo Methods in Practice"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.07.022"},{"key":"ref26","first-page":"322","article-title":"String-based audiovisual fusion of behavioral events for the assessment of dimensional affect","author":"eyben","year":"2011","journal-title":"Proc IEEE Autom Face Gesture Recognit Workshop Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101300"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/7203181\/06930787.pdf?arnumber=6930787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,20]],"date-time":"2022-04-20T05:03:13Z","timestamp":1650430993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6930787"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9]]},"references-count":41,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2362101","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9]]}}}