{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:47:25Z","timestamp":1776883645145,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687971","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"39-46","source":"Crossref","is-referenced-by-count":6,"title":["Beyond Isolated Utterances: Conversational Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Raghavendra","family":"Pappagari","sequence":"first","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Zelasko","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laureano","family":"Moro-Velazquez","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Center for Language and Speech Processing, Johns Hopkins University,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.370"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/752"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.08.018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-009-0032-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2710"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-336"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0956797610372634"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24736"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2466"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1180"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2007.03.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-011-9125-1"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref21","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2638"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8721.ep10770953"},{"key":"ref25","article-title":"Transformers with convolutional context for asr","author":"mohamed","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687971.pdf?arnumber=9687971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:18Z","timestamp":1652733678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687971\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687971","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}