{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:41:31Z","timestamp":1774366891278,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009148","name":"Queen Mary University of London","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009148","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096885","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":18,"title":["Cross-Modal Fusion Techniques for Utterance-Level Emotion Recognition from Text and Speech"],"prefix":"10.1109","author":[{"given":"Jiachen","family":"Luo","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,UK"}]},{"given":"Huy","family":"Phan","sequence":"additional","affiliation":[{"name":"Amazon Alexa,Cambridge,MA,USA"}]},{"given":"Joshua","family":"Reiss","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,UK"}]}],"member":"263","reference":[{"key":"ref13","first-page":"4243","article-title":"Multimodal Emotion Recognition Using Cross-Modal Attention and 1D Convolutional Neural Net-works","author":"krishna","year":"2020","journal-title":"InterSpeech"},{"key":"ref12","article-title":"EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa","author":"kim","year":"2021","journal-title":"ArXiv"},{"key":"ref15","first-page":"527","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"soujanya","year":"0","journal-title":"Proceedings annual meeting of the Association for Computational Linguistics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.009"},{"key":"ref31","first-page":"1","article-title":"SMIN: Semi-supervised Multi-modal Interaction Network for Conversational Emotion Recognition","author":"zheng","year":"2022","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref30","article-title":"Attention Is All You Need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-018-0505-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1280"},{"key":"ref2","article-title":"Cross-Modal BERT for Text-Audio Sentiment Analysis","author":"yang","year":"0","journal-title":"Paper presented at Proceedings of the 28th ACM International Conference on Multimedia"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.12.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"ref16","first-page":"6818","article-title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","author":"navonil","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"168865","DOI":"10.1109\/ACCESS.2020.3023871","article-title":"Cross-subject multimodal emotion recognition based on hybrid fusion","volume":"8","author":"yucel","year":"2020","journal-title":"IEEE Access"},{"key":"ref23","first-page":"1","article-title":"Deep learning based multimodal emotion recognition using model-level fusion of audio-visual modalities","volume":"244","author":"asif","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2020.00009"},{"key":"ref25","first-page":"2122","article-title":"Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos","volume":"1","author":"devamanyu","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s21144913"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref27","article-title":"COSMIC: Common Sense knowledge for eMotion Identification in Conversations","author":"ghosal","year":"2020","journal-title":"Findings of the Association for Computational Linguistics (EMNLP Findings)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413144"},{"key":"ref7","first-page":"6309","article-title":"Speech Emotion Recognition Using Quaternion Convolutional Neural Networks","author":"aneesh","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref9","first-page":"7697","article-title":"SERAB: A Multi-Lingual Benchmark for Speech Emotion Recognition","author":"neil","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096885.pdf?arnumber=10096885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:23Z","timestamp":1700507303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096885","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}