{"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":1790961470330,"version":"4.1.0"},"reference-count":44,"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\/501100014188","name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education","doi-asserted-by":"publisher","award":["2021R1A6A1A03043144"],"award-info":[{"award-number":["2021R1A6A1A03043144"]}],"id":[{"id":"10.13039\/501100014188","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.2022.3223705","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:11:43Z","timestamp":1669065103000},"page":"122302-122313","source":"Crossref","is-referenced-by-count":56,"title":["Attention-Based Multi-Learning Approach for Speech Emotion Recognition With Dilated Convolution"],"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05936-0_31"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app12189188"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037496"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref37","article-title":"Multi-window data augmentation approach for speech emotion recognition","author":"padi","year":"2020","journal-title":"arXiv 2010 09895"},{"key":"ref36","first-page":"867","article-title":"Speech emotion recognition—A deep learning approach","author":"asiya","year":"2021","journal-title":"Proc 5th Int Conf I-SMAC (IoT Social Mobile Analytics Cloud) (I-SMAC)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3163856"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017462"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/s22062378"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9050713"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2019EDL8019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047395"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC47524.2020.9031207"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3143803"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11030496"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2133","DOI":"10.3390\/math8122133","article-title":"CLSTM: Deep feature-based speech emotion recognition using the hierarchical ConvLSTM network","volume":"8","author":"kwon","year":"2020","journal-title":"Mathematics"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2022.108078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3119-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-019-00524-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3056421"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.882699"},{"key":"ref9","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 Gen Academic Conf"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06007-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929257"},{"key":"ref21","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref24","article-title":"MLT-DNet: Speech emotion recognition using 1D dilated CNN based on multi-learning trick approach","volume":"167","author":"kwon","year":"2021","journal-title":"Expert Syst Appl"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s20216008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00208-5"},{"key":"ref44","author":"jackson","year":"2014","journal-title":"Surrey audio-visual expressed emotion (savee) database"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682154"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s21227530"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09956836.pdf?arnumber=9956836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:53:26Z","timestamp":1671479606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3223705","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}