{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:28:48Z","timestamp":1783096128487,"version":"3.54.6"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002241","name":"JST SPRING","doi-asserted-by":"publisher","award":["JPMJSP2124"],"award-info":[{"award-number":["JPMJSP2124"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3219094","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:58:49Z","timestamp":1667527129000},"page":"115732-115743","source":"Crossref","is-referenced-by-count":33,"title":["Speech Emotion Recognition Based on Self-Attention Weight Correction for Acoustic and Text Features"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7723-3396","authenticated-orcid":false,"given":"Jennifer","family":"Santoso","sequence":"first","affiliation":[{"name":"Degree Programs in Systems and Information Engineering, University of Tsukuba, Ibaraki, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5744-8469","authenticated-orcid":false,"given":"Takeshi","family":"Yamada","sequence":"additional","affiliation":[{"name":"RevComm, Inc, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenkichi","family":"Ishizuka","sequence":"additional","affiliation":[{"name":"RevComm, Inc, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6588-9790","authenticated-orcid":false,"given":"Taiichi","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"RevComm, Inc, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoji","family":"Makino","sequence":"additional","affiliation":[{"name":"Degree Programs in Systems and Information Engineering, University of Tsukuba, Ibaraki, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc NAACL"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10403"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3307"},{"key":"ref30","article-title":"A transfer learning method for speech emotion recognition from automatic speech recognition","author":"zhou","year":"2020","journal-title":"arXiv 2008 02863"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383618"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1180"},{"key":"ref35","article-title":"On the impact of word error rate on acoustic-linguistic speech emotion recognition: An update for the deep learning era","author":"amiriparian","year":"2021","journal-title":"arXiv 2104 10121"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1149"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2312"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-609"},{"key":"ref1","first-page":"22","article-title":"Emotion in speech: Recognition and application to call centers","volume":"710","author":"petrushin","year":"1999","journal-title":"Proc ANNIE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1832"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3156"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-411"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-57"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref40","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2015.7391796"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462677"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/11550907_126"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref17","first-page":"1","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639633"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2966857"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683679"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053561"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221370"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-324"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2007.677"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"ref46","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NIPS"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref48","article-title":"Bimodal speech emotion recognition using pre-trained language models","author":"heusser","year":"2019","journal-title":"arXiv 1912 02610"},{"key":"ref47","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref44","year":"2022","journal-title":"Bert base model (uncased)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09936641.pdf?arnumber=9936641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T20:12:26Z","timestamp":1669666346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9936641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3219094","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}