{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:18:44Z","timestamp":1761848324277,"version":"build-2065373602"},"reference-count":78,"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":[{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial National Science Foundation of China and National Science Foundation of China","doi-asserted-by":"publisher","award":["LZ20F020002","LQ21F020002","61976149"],"award-info":[{"award-number":["LZ20F020002","LQ21F020002","61976149"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018552","name":"Science and Technology Plan Project of Taizhou","doi-asserted-by":"publisher","award":["1803gy08"],"award-info":[{"award-number":["1803gy08"]}],"id":[{"id":"10.13039\/501100018552","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Outstanding Youth Project of Taizhou University","award":["2018JQ003"],"award-info":[{"award-number":["2018JQ003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3038493","type":"journal-article","created":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T16:44:15Z","timestamp":1605631455000},"page":"215851-215862","source":"Crossref","is-referenced-by-count":4,"title":["Speech Emotion Recognition by Combining a Unified First-Order Attention Network With Data Balance"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1532-9741","authenticated-orcid":false,"given":"Gang","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8184-5088","authenticated-orcid":false,"given":"Shiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tao","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4708-4171","authenticated-orcid":false,"given":"Xiaoming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Information Processing, Taizhou University, Taizhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00089"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2553038"},{"key":"ref70","first-page":"1","article-title":"The INTERSPEECH 2010 paralinguistic challenge","author":"schuller","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023339"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.012"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.06.003"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019296"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914193"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2969032"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461299"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00154"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00746"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275184"},{"key":"ref36","article-title":"Syntax-directed attention for neural machine translation","author":"chen","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5120\/16891-6927"},{"key":"ref62","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2947464"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738859"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470342"},{"key":"ref27","first-page":"194","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Proc 13th Annu Conf Int Speech Commun Assoc"},{"key":"ref65","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"jialin pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"ref68","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref69","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref22","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0644-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2009.09.009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.010"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/EMEIT.2011.6023178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref40","first-page":"810","article-title":"Data augmentation for low resource languages","author":"ragni","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref12","first-page":"1","article-title":"Emotion recognition in spontaneous speech using GMMs","author":"neiberg","year":"2006","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.03.006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018628609742"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2925934"},{"key":"ref19","first-page":"1","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"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.10.043"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2016.10.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SAI.2017.8252104"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2633383"},{"key":"ref8","first-page":"183","article-title":"Voice quality features for speech emotion recognition","volume":"10","author":"idris","year":"2015","journal-title":"J Inf Assurance Secur"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIECS.2009.5362730"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.11.028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366937"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349350"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref47","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":"ref42","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv 1412 5567"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372913"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2935128"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09261367.pdf?arnumber=9261367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:03:32Z","timestamp":1761847412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9261367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3038493","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}