{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:08:48Z","timestamp":1784563728260,"version":"3.55.0"},"reference-count":35,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747723","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6917-6921","source":"Crossref","is-referenced-by-count":26,"title":["Multimodal Transformer with Learnable Frontend and Self Attention for Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Soumya","family":"Dutta","sequence":"first","affiliation":[{"name":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/703"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2018.2882362"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3304"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref19","article-title":"LEAF: A learnable frontend for audio classification","author":"zeghidour","year":"2021"},{"key":"ref28","article-title":"Multi-modal emotion recognition on iemocap dataset using deep learning","author":"tripathi","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34584-5_37"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref3","author":"scherer","year":"2003","journal-title":"Vocal Expression of Emotion"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054709"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15184-2_9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85099-1_8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531741"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459377"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632708"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDECOM.2011.5738536"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-324"},{"key":"ref26","article-title":"Advances in pretraining distributed word representations","author":"mikolov","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"}],"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\/09747723.pdf?arnumber=9747723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:10:32Z","timestamp":1661199032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747723","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}