{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:02:46Z","timestamp":1772553766863,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096138","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Learning Cross-Modal Audiovisual Representations with Ladder Networks for Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Lucas","family":"Goncalves","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1175-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1438"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470363"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref23","first-page":"2368","article-title":"Deconstructing the ladder network architecture","author":"pezeshki","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS 2017)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref29","first-page":"1459","article-title":"OpenSMILE: the Munich versatile and fast open-source audio feature extractor","author":"eyben","year":"2010","journal-title":"ACM International Conference on Multimedia (MM 2010)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref7","first-page":"549","article-title":"Interplay between linguistic and affective goals in facial expression during emotional utterances","author":"busso","year":"2006","journal-title":"7th International Seminar on Speech Production (ISSP 2006)"},{"key":"ref9","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","volume":"1","author":"zadeh","year":"2018","journal-title":"ACM Association for Computational Linguistics (ACL 2004)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747157"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216993"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096138.pdf?arnumber=10096138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:50Z","timestamp":1699902050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096138","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}