{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:23:24Z","timestamp":1783556604839,"version":"3.55.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019117","name":"Vector Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019117","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448505","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11976-11980","source":"Crossref","is-referenced-by-count":7,"title":["Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations"],"prefix":"10.1109","author":[{"given":"Debaditya","family":"Shome","sequence":"first","affiliation":[{"name":"Queen’s University,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[{"name":"Queen’s University,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1832"},{"key":"ref8","author":"Wang","year":"2021","journal-title":"A fine-tuned Wav2Vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref11","author":"Heusser","year":"2019","journal-title":"Bimodal speech emotion recognition using pre-trained language models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2023.1072479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096112"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref15","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3243596"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094895"},{"key":"ref18","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746679"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414540"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120586"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448505.pdf?arnumber=10448505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:57Z","timestamp":1722660897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448505","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}