{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T21:54:51Z","timestamp":1772574891764,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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 Trans. Affective Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/taffc.2025.3647876","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T18:46:19Z","timestamp":1766601979000},"page":"1134-1146","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing Multimodal Unlabeled Data for Enhanced Speech Emotion Recognition"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9613-1002","authenticated-orcid":false,"given":"Lucas","family":"Goncalves","sequence":"first","affiliation":[{"name":"Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4075-4072","authenticated-orcid":false,"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3083821"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461866"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1972"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925524"},{"key":"ref8","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447678"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref18","first-page":"566","article-title":"Leveraging pre-trained language model for speech sentiment analysis","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Shon","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3188390"},{"key":"ref22","first-page":"258","article-title":"XLM-T: Multilingual language models in twitter for sentiment analysis and beyond","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Barbieri","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref24","article-title":"The MSP-Podcast corpus","author":"Busso","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414035"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472670"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747705"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289072"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2466"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2217"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref41","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","volume-title":"Proc. 2021 IEEE\/CVF Int. Conf. Comput. Vis.","author":"Caron","year":"2021"},{"key":"ref42","article-title":"EMO-SUPERB: An in-depth look at speech emotion recognition","author":"Wu","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747754"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614110"},{"key":"ref46","first-page":"519","article-title":"Speech emotion recognition using speech feature and word embedding","author":"Atmaja","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683190"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096138"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428219"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3433386"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747157"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216993"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2025.3530274"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5492"},{"issue":"10","key":"ref57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/e25101440","article-title":"A survey of deep learning-based multimodal emotion recognition: Speech, text, and face","volume":"25","author":"Lian","year":"2023","journal-title":"Entropy"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.16"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0203-6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3062406"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref66","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref67","first-page":"549","article-title":"Interplay between linguistic and affective goals in facial expression during emotional utterances","volume-title":"Proc. 7th Int. Seminar Speech Production","author":"Busso","year":"2006"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191330"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.905145"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref72","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall","year":"2018"},{"key":"ref73","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Chen","year":"2018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2407898"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-60278-1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-280"},{"key":"ref78","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3187336"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2123"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1248"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2023.200266"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11418735\/11314580.pdf?arnumber=11314580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:35Z","timestamp":1772571215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11314580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":82,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3647876","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}