{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:42:23Z","timestamp":1784212943535,"version":"3.55.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746598","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6897-6901","source":"Crossref","is-referenced-by-count":65,"title":["Key-Sparse Transformer for Multimodal Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Weidong","family":"Chen","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Xing","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangmin","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jichen","family":"Yang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxin","family":"Pang","sequence":"additional","affiliation":[{"name":"UBTECH Robotics Corp,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3026823"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref13","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref15","first-page":"3507","article-title":"Multi-modal transformer fusion for continuous emotion recognition","author":"huang","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2067"},{"key":"ref18","first-page":"374","article-title":"A Multi-Scale Fusion Frame-work for Bimodal Speech Emotion Recognition","author":"chen","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"ref4","article-title":"What makes multimodal learning better than single (provably)","author":"huang","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"ref6","first-page":"4243","article-title":"Multimodal Emotion Recognition Using Cross-Modal Attention and 1D Convolutional Neural Networks","author":"krishna","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref8","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414705"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DSR.2011.6026823"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref9","article-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"liu","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414542"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746598.pdf?arnumber=9746598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:51Z","timestamp":1660594311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746598","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}