{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:47:49Z","timestamp":1784821669094,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["19H04215"],"award-info":[{"award-number":["19H04215"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3282092","type":"journal-article","created":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T17:36:19Z","timestamp":1685640979000},"page":"2193-2203","source":"Crossref","is-referenced-by-count":65,"title":["Dual-TBNet: Improving the Robustness of Speech Features via Dual-Transformer-BiLSTM for Speech Emotion Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0685-1124","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"first","affiliation":[{"name":"Faculty of Science and Engineering, Tokushima University, Tokushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6024-3598","authenticated-orcid":false,"given":"Xin","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Information Science and Intelligent Systems, Tokushima University, Tokushima, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4860-9184","authenticated-orcid":false,"given":"Fuji","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9493-x"},{"key":"ref57","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","author":"haq","year":"0","journal-title":"Proc Auditory-Vis Speech Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref15","first-page":"857","article-title":"Self-supervised learning: Generative or contrastive","volume":"35","author":"liu","year":"2023","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09693-w"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"ref58","first-page":"491","article-title":"Research on the effect of different speech segment lengths on speech emotion recognition based on LSTM","author":"liu","year":"0","journal-title":"Proc 9th Int Workshop Comput Sci Eng"},{"key":"ref53","first-page":"1","article-title":"Design of speech corpus for mandarin text to speech","author":"zhang","year":"0","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005997"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09874-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref54","first-page":"8","article-title":"The eNTERFACE'05 audio-visual emotion database","author":"martin","year":"0","journal-title":"Proceedings of the 22nd International Conference on Data Engineering Workshops"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-03948-5_28"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/app10010205"},{"key":"ref51","first-page":"491","article-title":"Research on the effect of different speech segment lengths on speech emotion recognition based on LSTM","author":"liu","year":"0","journal-title":"Proc 9th Int Workshop Comput Sci Eng"},{"key":"ref50","article-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies","author":"liu","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref45","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref44","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2010.10.028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02175-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.12324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app10082924"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2017.8217966"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103649"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref35","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3225684"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.115831"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11091328"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.12.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0219622019300052"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcs.2008.12.065"},{"key":"ref39","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app11041890"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223705"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114683"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09734-7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1121\/10.0003530"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3474198.3478152"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v11i2.pp1259-1264"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108046"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-018-0145-5"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2020-0458"},{"key":"ref28","article-title":"MLT-DNet: Speech emotion recognition using 1D dilated CNN based on multi-learning trick approach","volume":"167","author":"kwon","year":"2021","journal-title":"Expert Syst Appl"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.094"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3069818"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/s20082297"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1811"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10141880.pdf?arnumber=10141880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:23:12Z","timestamp":1688408592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10141880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3282092","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}