{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:27:11Z","timestamp":1784215631714,"version":"3.55.0"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/lsp.2021.3065598","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T20:48:10Z","timestamp":1615495690000},"page":"608-612","source":"Crossref","is-referenced-by-count":21,"title":["Multimodal Embeddings From Language Models for Emotion Recognition in the Wild"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1795-8330","authenticated-orcid":false,"given":"Shao-Yen","family":"Tseng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0790-7161","authenticated-orcid":false,"given":"Panayiotis","family":"Georgiou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054229"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref33","first-page":"1478","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"0","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref32","first-page":"24","article-title":"A simple but tough-to-beat baseline for sentence embeddings","author":"arora","year":"0","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref31","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref30","article-title":"Character-aware neural language models","author":"kim","year":"0","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref36","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"zadeh","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref34","first-page":"2635","article-title":"One billion word benchmark for measuring progress in statistical language modeling","author":"chelba","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref11","article-title":"Behavior gated language models","author":"kumar","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-010-9068-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1110"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2018.09.019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3242996"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3301"},{"key":"ref19","article-title":"Convolutional attention networks for multimodal emotion recognition from speech and text data","author":"lee","year":"2018","journal-title":"ACL"},{"key":"ref28","article-title":"FRAGE: Frequency-agnostic word representation","author":"gong","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240605"},{"key":"ref27","article-title":"M-BERT Injecting multimodal information in the BERT structure","author":"rahman","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref29","article-title":"Exploring the limits of language modeling","author":"j\u00f3zefowicz","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682583"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3279981.3279987"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236291"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2010.02.002"},{"key":"ref20","article-title":"S. Poria, E. Cambria, and L.-P. Morency, “Memory fusion network for multi-view sequential learning","author":"zadeh","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref24","first-page":"4171","article-title":"Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc NAACL-HLT"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref23","first-page":"2227","article-title":"Deep contextualized word representations","author":"matthew","year":"0","journal-title":"Proc NAACL-HLT"},{"key":"ref26","article-title":"Learning factorized multimodal representations","author":"tsai","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref25","article-title":"Disentangling by partitioning: A representation learning framework for multimodal sensory data","author":"hsu","year":"2018"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9325893\/09376096.pdf?arnumber=9376096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:40Z","timestamp":1652194240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/lsp.2021.3065598","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}