{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T00:28:41Z","timestamp":1726014521204},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650087","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Improving Speech Emotion Recognition through Hierarchical Classification and Text Integration for Enhanced Emotional Analysis and Contextual Understanding"],"prefix":"10.1109","author":[{"given":"Nawal","family":"Alqurashi","sequence":"first","affiliation":[{"name":"Cardiff University,School of Computer Science and Informatics,Cardiff,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[{"name":"Cardiff University,School of Computer Science and Informatics,Cardiff,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirill","family":"Sidorov","sequence":"additional","affiliation":[{"name":"Cardiff University,School of Computer Science and Informatics,Cardiff,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.109178"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12112512"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3071503"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.076"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app13169062"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13725-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3388861"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-57"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13091-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"journal-title":"Multimodal speech emotion recognition and ambiguity resolution","year":"2019","author":"Sahu","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"journal-title":"A fine-tuned wav2vec 2.0\/Hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","year":"2021","author":"Wang","key":"ref21"},{"journal-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","year":"2020","author":"Baevski","key":"ref22"},{"key":"ref23","article-title":"embedding4bert: A python library for extracting word embeddings from pre-trained language models","author":"Chai","year":"2020","journal-title":"GitHub repository"},{"journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2466"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2019-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3201"},{"key":"ref29","first-page":"1","article-title":"Ensemble of svm trees for multimodal emotion recognition","volume-title":"Proc. IEEE Signal & Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Rozgic"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650087.pdf?arnumber=10650087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:50:40Z","timestamp":1725943840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650087","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}