{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T23:03:42Z","timestamp":1793142222832,"version":"4.5.0"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"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":[[2023]]},"DOI":"10.1109\/access.2023.3325037","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:23:20Z","timestamp":1697480600000},"page":"113769-113789","source":"Crossref","is-referenced-by-count":54,"title":["Deep Learning Approaches for Bimodal Speech Emotion Recognition: Advancements, Challenges, and a Multi-Learning Model"],"prefix":"10.1109","volume":"11","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":"School of Data Science, Indian Institute of Science Education and Research Thiruvananthapuram (IISER TVM), Vithura, Thiruvananthapuram, Kerala, India"}],"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":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC47524.2020.9031207"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11091328"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.057"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref53","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-336"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11091409"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-57"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178798"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054629"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.098"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2050104.2050105"},{"key":"ref42","article-title":"Deep learning based emotion recognition system using speech features and transcriptions","author":"tripathi","year":"2019","journal-title":"arXiv 1906 05681"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107316"},{"key":"ref43","article-title":"Multimodal speech emotion recognition and ambiguity resolution","author":"sahu","year":"2019","journal-title":"arXiv 1904 06022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","author":"picard","year":"1997","journal-title":"Affective Computing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103649"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-54173-6_17"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199942237.001.0001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10799-012-0138-5"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2846596"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3126\/jiee.v3i1.34327"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1080\/03081079.2017.1291635"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2013.0446"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3054345"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-010-0001-0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2016.11.001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3225684"},{"key":"ref38","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":"ref24","doi-asserted-by":"crossref","first-page":"2236","DOI":"10.18653\/v1\/P18-1208","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"bagher zadeh","year":"2018","journal-title":"Proc 56th Annu Meeting Assoc Comput Linguistics Long Papers"},{"key":"ref23","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"poria","year":"2018","journal-title":"arXiv 1810 02508"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027600"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10101163"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2788081"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00506"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDL8258"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2022.108078"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICICT57646.2023.10134389"},{"key":"ref96","article-title":"Cross-corpus bimodal speech emotion recognition","author":"yunxiang","year":"2022","journal-title":"Authorea Preprints"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.002"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICICT57646.2023.10134211"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref98","first-page":"1","article-title":"Driver’s companion-drowsiness detection and emotion based music recommendation system","author":"pant","year":"2022","journal-title":"Proc Int Conf Comput Commun Intell Syst (ICCCIS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3156"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23851\/mjs.v28i3.48"},{"key":"ref18","author":"kesarkar","year":"2003","journal-title":"Feature Extraction for Speech Recognition"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054441"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3228649"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3219094"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688036"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2022.10.018"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc6030095"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.02.006"},{"key":"ref86","article-title":"Bimodal speech emotion recognition using pre-trained language models","author":"heusser","year":"2019","journal-title":"arXiv 1912 02610"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3390\/e25010124"},{"key":"ref88","article-title":"Multistage linguistic conditioning of convolutional layers for speech emotion recognition","author":"triantafyllopoulos","year":"2021","journal-title":"arXiv 2110 06650"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1703"},{"key":"ref82","first-page":"2020","volume":"1","author":"pichora-fuller","year":"2020","journal-title":"Toronto Emotional Speech Set (TESS)"},{"key":"ref81","author":"jackson","year":"2014","journal-title":"Surrey audio-visual expressed emotion (savee) database"},{"key":"ref84","first-page":"1793","article-title":"ASVP-ESD: A dataset and its benchmark for emotion recognition using both speech and non-speech utterances","volume":"8","author":"landry","year":"2020","journal-title":"J Glob Sci"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3151551"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967286"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref2","first-page":"38","article-title":"Enhancing health care via affective computing","volume":"5","author":"yannakakis","year":"2018","journal-title":"Malta J Health Sci"},{"key":"ref1","article-title":"A survey of speech emotion recognition in natural environment","volume":"110","author":"fahad","year":"2021","journal-title":"Digit Signal Process"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3390\/app10010205"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/app11177962"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/2974804.2974814"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICUFN57995.2023.10199790"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/s21227530"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.11"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.07.004"},{"key":"ref60","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":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223705"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/APCC55198.2022.9943771"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10286495.pdf?arnumber=10286495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T22:57:49Z","timestamp":1730329069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10286495\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3325037","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}