{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:21:55Z","timestamp":1774455715692,"version":"3.50.1"},"reference-count":66,"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\/501100008114","name":"Research Foundation of Nanjing Institute of Technology","doi-asserted-by":"publisher","award":["CKJB202107"],"award-info":[{"award-number":["CKJB202107"]}],"id":[{"id":"10.13039\/501100008114","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008114","name":"Research Foundation of Nanjing Institute of Technology","doi-asserted-by":"publisher","award":["3544113221109"],"award-info":[{"award-number":["3544113221109"]}],"id":[{"id":"10.13039\/501100008114","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008114","name":"Research Foundation of Nanjing Institute of Technology","doi-asserted-by":"publisher","award":["3612407223538"],"award-info":[{"award-number":["3612407223538"]}],"id":[{"id":"10.13039\/501100008114","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008114","name":"Research Foundation of Nanjing Institute of Technology","doi-asserted-by":"publisher","award":["3612407222302"],"award-info":[{"award-number":["3612407222302"]}],"id":[{"id":"10.13039\/501100008114","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.2024.3490186","type":"journal-article","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T17:25:30Z","timestamp":1730481930000},"page":"161500-161518","source":"Crossref","is-referenced-by-count":3,"title":["GFRN-SEA: Global-Aware Feature Representation Network for Speech Emotion Analysis"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2292-410X","authenticated-orcid":false,"given":"Lei","family":"Pan","sequence":"first","affiliation":[{"name":"School of Computer Engineering, Nanjing Institute of Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Nanjing Institute of Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-57"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094673"},{"key":"ref7","article-title":"Multi-modal emotion recognition on IEMOCAP dataset using deep learning","author":"Tripathi","year":"2018","journal-title":"arXiv:1804.05788"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053727"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.12.246"},{"key":"ref15","first-page":"21","article-title":"CNN+LSTM architecture for speech emotion recognition with data augmentation","volume-title":"Proc. Workshop Speech, Music Mind (SMM)","author":"Etienne"},{"key":"ref16","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Baevski"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3304"},{"key":"ref22","first-page":"3569","article-title":"Learning alignment for multimodal emotion recognition from speech","volume-title":"Proc. Interspeech","author":"Xu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1190"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054229"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413635"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446769"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747517"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096966"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109752"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118943"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13725-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659587"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref41","volume-title":"Surrey audio-visual expressed emotion (savee) database","author":"Jackson","year":"2014"},{"key":"ref42","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3326071"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1649"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.07.005"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106547"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235194"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-523"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.017"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/320"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067460"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1650"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053561"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-158"},{"key":"ref60","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3277291"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2014-39"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref66","first-page":"1268","article-title":"RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification","volume-title":"Proc. Interspeech","author":"Jung"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10741263.pdf?arnumber=10741263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T03:49:05Z","timestamp":1732679345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10741263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3490186","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}