{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:09:20Z","timestamp":1774127360615,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI Grant","award":["16K00297"],"award-info":[{"award-number":["16K00297"]}]},{"name":"Research Foundation of Education Bureau of Hunan Province, China","award":["18A414"],"award-info":[{"award-number":["18A414"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2967791","type":"journal-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T12:32:14Z","timestamp":1579609934000},"page":"16560-16572","source":"Crossref","is-referenced-by-count":73,"title":["Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1020-7796","authenticated-orcid":false,"given":"Zhichao","family":"Peng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8958-0341","authenticated-orcid":false,"given":"Xingfeng","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1525-9395","authenticated-orcid":false,"given":"Zhi","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6605-2052","authenticated-orcid":false,"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9237-4821","authenticated-orcid":false,"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-6754","authenticated-orcid":false,"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.21437\/Interspeech.2017-917","article-title":"Attentive convolutional neural network based speech emotion recognition: A study on the impact of input features, signal length, and acted speech","author":"neumann","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref32","first-page":"1537","article-title":"High-level feature representation using recurrent neural network for speech emotion recognition","author":"lee","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-448"},{"key":"ref37","first-page":"1","article-title":"The Interspeech 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism","author":"schuller","year":"2013","journal-title":"Proc 14th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref36","article-title":"The interspeech 2009 emotion challenge","author":"schuller","year":"2009","journal-title":"Proc 10th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486564"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.1992.0070"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.874669"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.1600720"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.2228539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.420345"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.389861"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcn.2011.11.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1250\/ast.39.379"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2684186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.06.032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2456420"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1250\/ast.39.234"},{"key":"ref7","first-page":"262","article-title":"Modulation spectral features for predicting vocal emotion recognition by simulated cochlear implants","author":"zhu","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703305013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.428100"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-692"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.408825"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2512598"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1477"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2018.03.044"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727636"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273628"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08963694.pdf?arnumber=8963694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T19:16:22Z","timestamp":1643310982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8963694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2967791","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}