{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:05:04Z","timestamp":1783101904918,"version":"3.54.6"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1504622"],"award-info":[{"award-number":["U1504622"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3550007","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:51:27Z","timestamp":1741629087000},"page":"1181-1185","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Alignment and Time Aggregation Network for Speech-Visual Emotion Recognition"],"prefix":"10.1109","volume":"32","author":[{"given":"Lile","family":"Wu","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Northwest A&F University, Xianyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zutian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Henan Electric Power Survey & Design Institute, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1414-0496","authenticated-orcid":false,"given":"Guanghui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3200060"},{"issue":"2","key":"ref4","article-title":"Speech emotion recognition model based on attention CNN Bi-GRU fusing visual information","volume":"30","author":"Hu","year":"2022","journal-title":"Eng. Lett."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104676"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3304128"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ATSIP55956.2022.9805959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CEECT55960.2022.10030478"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3150097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICoDT255437.2022.9787437"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126070"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06388-6_18"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120138"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57653.2023.10152451"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.065"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114170"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3055755"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03407-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3279689"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3324294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3258900"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2020.06.008"},{"key":"ref28","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref29","article-title":"Spatio-temporal transformer for dynamic facial expression recognition in the wild","author":"Ma","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/00273171.2018.1439722"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2961089"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2553038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10919089.pdf?arnumber=10919089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T19:18:21Z","timestamp":1742843901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10919089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3550007","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}