{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:48:49Z","timestamp":1779889729275,"version":"3.53.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276098"],"award-info":[{"award-number":["62276098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Wenzhou Science and Technology Bureau","doi-asserted-by":"publisher","award":["ZS2024001"],"award-info":[{"award-number":["ZS2024001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tce.2025.3596056","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T18:06:46Z","timestamp":1754417206000},"page":"7539-7550","source":"Crossref","is-referenced-by-count":1,"title":["MSMF-MIL: Multi-Scale Mixed Feature-Based Multiple Instance Learning for Speech Emotion Recognition"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1880-8054","authenticated-orcid":false,"given":"Dongdong","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmei","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3759-2041","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3259988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3546283"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT54382.2022.10152117"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-5180-2_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3119921"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106140"},{"key":"ref7","first-page":"1","article-title":"Feature importance and model performance in deep learning for speech emotion recognition","volume-title":"Proc. 11th Int. Conf. Adv. Comput. Commun. (ICACC)","author":"Ramkrishnan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3325317"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3496909"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114683"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104277"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref13","article-title":"Cross-language speech emotion recognition using multimodal dual attention transformers","author":"Zaidi","year":"2023","journal-title":"arXiv:2306.13804"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3282092"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2524"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349497"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445740"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2024.11.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109648"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3236972"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109578"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT58233.2024.10540745"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112123"},{"key":"ref24","article-title":"Acquisition and incorporation prosody knowledge for speech systems in Indian languages","author":"Rao","year":"2005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE54056.2021.9721524"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.09.047"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18280\/ria.380318"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9615958"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112499"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223705"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPIS56952.2022.10044059"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref33","article-title":"Transfer learning from high-resource to low-resource language improves speech affect recognition classification accuracy","author":"Durrani","year":"2021","journal-title":"arXiv:2103.11764"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00303-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119633"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3325037"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1504\/IJWMC.2021.113221"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref39","first-page":"1","article-title":"Support vector machines for multiple-instance learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"15","author":"Andrews"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273643"},{"key":"ref41","first-page":"123","article-title":"Deterministic annealing for multiple-instance learning","volume-title":"Proc. 11th Artif. Intell. Statist.","author":"Gehler"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-023-01961-z"},{"key":"ref43","first-page":"53","article-title":"Multi instance neural networks","volume-title":"Proc. Workshop Attribute-Value Relational Learn.","author":"Ramon"},{"key":"ref44","first-page":"2127","article-title":"Attention-based deep multiple instance learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilse"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6030"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119113"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2024.104115"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09417-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1968"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1779"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413640"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/app132312587"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3360428"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1177\/01655515221137270"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638345"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638344"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11241057\/11114734.pdf?arnumber=11114734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:41:49Z","timestamp":1762972909000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11114734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":58,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3596056","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}