{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:14:24Z","timestamp":1776975264587,"version":"3.51.4"},"reference-count":19,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095777","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":26,"title":["Multiple Acoustic Features Speech Emotion Recognition Using Cross-Attention Transformer"],"prefix":"10.1109","author":[{"given":"Yurun","family":"He","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/s20226688"},{"key":"ref11","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3131"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747517"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"114177","DOI":"10.1016\/j.eswa.2020.114177","article-title":"Mlt-dnet: Speech emotion recognition using 1d dilated cnn based on multi-learning trick approach","volume":"167","author":"kwon","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"ref8","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref9","first-page":"2578","article-title":"Self-attention for speech emotion recognition","author":"tarantino","year":"2019","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref3","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-336"}],"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\/10095777.pdf?arnumber=10095777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:07Z","timestamp":1700506627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095777","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}