{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T21:33:57Z","timestamp":1769549637502,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317325","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1013-1018","source":"Crossref","is-referenced-by-count":3,"title":["Speech Emotion Recognition by Late Fusion of Linguistic and Acoustic Features using Deep Learning Models"],"prefix":"10.1109","author":[{"given":"Kiyohide","family":"Sato","sequence":"first","affiliation":[{"name":"Yamagata University,Graduate School of Science and Engineering,Yonezawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keita","family":"Kishi","sequence":"additional","affiliation":[{"name":"Yamagata University,Graduate School of Science and Engineering,Yonezawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuo","family":"Kosaka","sequence":"additional","affiliation":[{"name":"Yamagata University,Graduate School of Science and Engineering,Yonezawa,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref2","first-page":"725","article-title":"Speech Emotion Recognition with Fusion of Acoustic and Linguistic-Feature-Based Decisions","volume-title":"Proc. of APSIPA ASC2021","author":"Nagase"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-118"},{"key":"ref4","first-page":"700","article-title":"Hierarchical Prosody Analysis Improves Categorical and Dimensional Emotion Recognition","volume-title":"Proc. of APSIPA ASC2021","author":"Li"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/a13030070"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1723"},{"key":"ref8","first-page":"371","article-title":"Language Model Adaptation for Emotional Speech Recognition using Tweet data","volume-title":"Proc. of APSIPA ASC2020","author":"Saeki"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747460"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE53005.2021.9621810"},{"key":"ref13","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proc. of NAACL2019","author":"Devlin"},{"issue":"11","key":"ref14","first-page":"2418","article-title":"Evaluation of task adaptation using N-gram count mixture","volume":"J83-D-II","author":"Ito","year":"2000","journal-title":"IEICE Trans"},{"key":"ref16","first-page":"1459","article-title":"openSMILE - The Munich Versatile and Fast Open-Source Audio Feature Extractor","volume-title":"Proc. of the 9th ACM international conference on Multimedia","author":"Eyben"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918977"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1199"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1180"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054621"},{"key":"ref21","article-title":"wav2vec 2.0:A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,10,31]]},"end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317325.pdf?arnumber=10317325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:52:25Z","timestamp":1709405545000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317325","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}