{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:19:39Z","timestamp":1784391579121,"version":"3.55.0"},"reference-count":29,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3587607","type":"journal-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:23Z","timestamp":1752103223000},"page":"121351-121361","source":"Crossref","is-referenced-by-count":5,"title":["A Lightweight Tri-Stream Feature Fusion Network for Speech Emotion Recognition"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0389-7138","authenticated-orcid":false,"given":"Ronghe","family":"Cao","sequence":"first","affiliation":[{"name":"School of Electronic Information Engineering, Jiangxi University of Engineering, Xinyu, Jiangxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Jiangxi University of Engineering, Xinyu, Jiangxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9256-8043","authenticated-orcid":false,"given":"Xiaolong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Ürümqi, Xinjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Jiangxi University of Engineering, Xinyu, Jiangxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiling","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Politics and Economics, Guizhou Minzu University, Guiyang, Guizhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407571"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14328-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922691"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16736-5"},{"issue":"10","key":"ref14","first-page":"3749","article-title":"Multi-channel autoencoder for speech emotion recognition","volume":"18","author":"Zong","year":"2018","journal-title":"Sensors"},{"key":"ref15","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref16","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","author":"Baevski","year":"2020","journal-title":"arXiv:2005.05122"},{"key":"ref17","first-page":"1234","article-title":"Swin transformer for speech emotion recognition","volume":"30","author":"Hao","year":"2022","journal-title":"IEEE Trans. Audio, Speech, Language Process."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3250840"},{"key":"ref19","article-title":"Speech emotion recognition using multi-stream feature fusion","volume-title":"Proc. Interspeech","author":"Kili\u00e7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref22","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","volume-title":"Proc. Int. Conf. Auditory-Visual Speech Process. (AVSP)","author":"Haq"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414248"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193151"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14577-w"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11075664.pdf?arnumber=11075664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:47:12Z","timestamp":1752860832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11075664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3587607","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}