{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:17:50Z","timestamp":1790961470697,"version":"4.1.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2021R1A6A1A03043144"],"award-info":[{"award-number":["2021R1A6A1A03043144"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3225684","type":"journal-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:23:06Z","timestamp":1669854186000},"page":"125538-125551","source":"Crossref","is-referenced-by-count":59,"title":["Deep Learning-Based Speech Emotion Recognition Using Multi-Level Fusion of Concurrent Features"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6722-2578","authenticated-orcid":false,"given":"Samuel","family":"Kakuba","sequence":"first","affiliation":[{"name":"Graduate School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7100-8665","authenticated-orcid":false,"given":"Alwin","family":"Poulose","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Michigan, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7769-0236","authenticated-orcid":false,"given":"Dong Seog","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Kyungpook National University, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Multi-modal emotion recognition on IEMOCAP dataset using deep learning","author":"tripathi","year":"2018","journal-title":"arXiv 1804 05788"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/app11177962"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1577"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.02.006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2974804.2974814"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092735"},{"key":"ref10","first-page":"1419","article-title":"Residual bidirectional LSTM with multi-head attention for speech emotion recognition","author":"kakuba","year":"2022","journal-title":"Proc Korea Commun Assoc Summer General Academic Conf"},{"key":"ref40","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11091328"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC47524.2020.9031207"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s22051937"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.057"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.072"},{"key":"ref18","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047395"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107316"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/1754073910380974"},{"key":"ref27","article-title":"Bimodal speech emotion recognition using pre-trained language models","author":"heusser","year":"2019","journal-title":"arXiv 1912 02610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3119-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037496"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2788081"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-019-00524-z"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11091409"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/h0030377"},{"key":"ref20","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref22","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-917"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s21227530"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3156"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09966603.pdf?arnumber=9966603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:33:34Z","timestamp":1672083214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9966603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3225684","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}