{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:04:22Z","timestamp":1740103462081,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L233032,L223033"],"award-info":[{"award-number":["L233032,L223033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471012"],"award-info":[{"award-number":["62471012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800413","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"398-402","source":"Crossref","is-referenced-by-count":0,"title":["Speech Emotion Recognition Based on Shallow Structure of Wav2vec 2.0 and Attention Mechanism"],"prefix":"10.1109","author":[{"given":"Yumei","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maoshen","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichen","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Engineering, Yanbian University,Yanji"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3119921"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HSI.2018.8431232"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app10134653"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2961089"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3096037"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3141237"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123383"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367262"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114683"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12040839"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app13074124"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3259988"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.2002-557"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3869-3"},{"key":"ref19","article-title":"Multimodal emotion recognition from raw audio with sinc-convolution","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114683"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3282092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3304516"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1840"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388152"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023428"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800413.pdf?arnumber=10800413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:28:44Z","timestamp":1736969324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800413","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}