{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:58:04Z","timestamp":1780394284826,"version":"3.54.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010693","name":"Telekom Malaysia Research and Development","doi-asserted-by":"publisher","award":["RDTC\/221064"],"award-info":[{"award-number":["RDTC\/221064"]}],"id":[{"id":"10.13039\/501100010693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010693","name":"Telekom Malaysia Research and Development","doi-asserted-by":"publisher","award":["RDTC\/231075"],"award-info":[{"award-number":["RDTC\/231075"]}],"id":[{"id":"10.13039\/501100010693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023674","name":"Deanship of Scientific Research at King Khalid University, Saudi Arabia","doi-asserted-by":"publisher","award":["RGP2\/332\/44"],"award-info":[{"award-number":["RGP2\/332\/44"]}],"id":[{"id":"10.13039\/501100023674","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3360483","type":"journal-article","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T18:37:31Z","timestamp":1706726251000},"page":"18237-18250","source":"Crossref","is-referenced-by-count":22,"title":["MaxMViT-MLP: Multiaxis and Multiscale Vision Transformers Fusion Network for Speech Emotion Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9732-0067","authenticated-orcid":false,"given":"Kah Liang","family":"Ong","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3679-8977","authenticated-orcid":false,"given":"Chin Poo","family":"Lee","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8346-6345","authenticated-orcid":false,"given":"Heng Siong","family":"Lim","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Technology, Multimedia University, Melaka, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1929-7978","authenticated-orcid":false,"given":"Kian Ming","family":"Lim","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1052-2657","authenticated-orcid":false,"given":"Ali","family":"Alqahtani","sequence":"additional","affiliation":[{"name":"Department of Computer Science, King Khalid University, Abha, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412360"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSECS52883.2021.00130"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SWC50871.2021.00030"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SCC53769.2021.9768372"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9615958"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106547"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3163856"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05936-0_31"},{"key":"ref11","first-page":"1419","article-title":"Residual bidirectional LSTM with multi-head attention for speech emotion recognition","volume-title":"Proc. Korea Commun. Assoc. Summer Gen. Acad. Conf.","author":"Kakuba"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103712"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909528"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14051-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IHCSP56702.2023.10127148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109444"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app13074124"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3282092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019","journal-title":"arXiv:1910.05453"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v13i4.pp4020-4028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.11.005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref28","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Dai"},{"key":"ref29","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10418124.pdf?arnumber=10418124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T05:45:33Z","timestamp":1707457533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3360483","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}