{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:46:50Z","timestamp":1784216810473,"version":"3.55.0"},"reference-count":71,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62220106008"],"award-info":[{"award-number":["62220106008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2063"],"award-info":[{"award-number":["U20B2063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306067"],"award-info":[{"award-number":["62306067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2024NSFSC1463"],"award-info":[{"award-number":["2024NSFSC1463"]}]},{"name":"Sichuan Province Innovative Talent Funding Project for Postdoctoral Fellows"},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M720660"],"award-info":[{"award-number":["2022M720660"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3410133","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T17:56:11Z","timestamp":1717610171000},"page":"10623-10636","source":"Crossref","is-referenced-by-count":12,"title":["Improving Pre-Trained Model-Based Speech Emotion Recognition From a Low-Level Speech Feature Perspective"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5765-2128","authenticated-orcid":false,"given":"Ke","family":"Liu","sequence":"first","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-1742","authenticated-orcid":false,"given":"Jiwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-778X","authenticated-orcid":false,"given":"Jie","family":"Zou","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5397-9115","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388152"},{"key":"ref2","first-page":"44","article-title":"Learning discriminative features using center loss and reconstruction as regularizer for speech emotion recognition","volume-title":"Proc. Workshop Artif. Intell. Affect. Comput.","author":"Tripathi","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095588"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3366404"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20724"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2947155"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3243521"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947358"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157485"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746289"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859862"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.4400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5408"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3278184"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3211197"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3280222"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475451"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3297410"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889523"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.312"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6122"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133196"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3282092"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref39","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01106"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2014.09.032"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688036"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1649"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414540"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2730187"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1132"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.09.002"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICTer48817.2019.9023737"},{"key":"ref57","article-title":"Towards adversarial learning of speaker-invariant representation for speech emotion recognition","author":"Tu","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-3068"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054580"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-285"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/1945630"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2927384"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/app11219897"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/e24081025"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref68","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","volume":"2009","author":"Haq","year":"2009","journal-title":"AVSP"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref71","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10549860.pdf?arnumber=10549860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:25:22Z","timestamp":1732667122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3410133","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}