{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T08:18:12Z","timestamp":1776154692714,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Scientific Research Staring Foundation of Hangzhou Institute for Advanced Study","award":["2024HIAS-C2001"],"award-info":[{"award-number":["2024HIAS-C2001"]}]},{"name":"National Key R&D Program of China","award":["2019YFE0105400"],"award-info":[{"award-number":["2019YFE0105400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/taffc.2024.3481253","type":"journal-article","created":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T17:24:11Z","timestamp":1729013051000},"page":"915-932","source":"Crossref","is-referenced-by-count":3,"title":["A Residual Multi-Scale Convolutional Neural Network With Transformers for Speech Emotion Recognition"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1851-6075","authenticated-orcid":false,"given":"Tianhao","family":"Yan","sequence":"first","affiliation":[{"name":"Research Center for Data Hub and Security, Zhejiang Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3586-9286","authenticated-orcid":false,"given":"Hao","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1843-3632","authenticated-orcid":false,"given":"Emilia","family":"Parada-Cabaleiro","sequence":"additional","affiliation":[{"name":"Institute of Computational Perception, Johannes Kepler University Linz, Linz, Austria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3279-7125","authenticated-orcid":false,"given":"Taihao","family":"Li","sequence":"additional","affiliation":[{"name":"Hangzhou Institute for Advanced Study, UCAS, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Augsburg, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597419"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3119921"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107172"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10329-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v11i2.pp1259-1264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-021-09647-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref11","article-title":"Bag-of-words representations for computer audition","author":"Schmitt","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-4625-6_24"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_34"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104277"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659587"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747517"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3135152"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0281079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3083821"},{"key":"ref24","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"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA50338.2020.9295032"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2694"},{"key":"ref29","first-page":"325","article-title":"Deep multilayer perceptrons for dimensional speech emotion recognition","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Atmaja"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413910"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2023.1072479"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/sym14071428"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747754"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2947464"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12378-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3512353.3512380"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414314"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133195"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref46","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"Latif","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref49","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107340"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3173128"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2016.1154108"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.109178"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3028109"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11018643\/10716771.pdf?arnumber=10716771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:53:39Z","timestamp":1748667219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10716771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":61,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3481253","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}