{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:57:06Z","timestamp":1781110626995,"version":"3.54.1"},"reference-count":24,"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\/icassp49357.2023.10097135","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":11,"title":["Adapting a Self-Supervised Speech Representation for Noisy Speech Emotion Recognition by Using Contrastive Teacher-Student Learning"],"prefix":"10.1109","author":[{"given":"Seong-Gyun","family":"Leem","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Fulford","sequence":"additional","affiliation":[{"name":"Boston University,Occupational Therapy and Psychological & Brain Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jukka-Pekka","family":"Onnela","sequence":"additional","affiliation":[{"name":"Harvard University,Harvard T.H. Chan School of Public Health,Department of Biostatistics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Gard","sequence":"additional","affiliation":[{"name":"San Francisco State University,Psychology Department"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747705"},{"key":"ref24","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"Emotion recognition in the noise applying large acoustic feature sets","author":"schuller","year":"2006","journal-title":"ISCA Speech Prosody"},{"key":"ref23","first-page":"1","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref20","first-page":"1","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597437"},{"key":"ref22","first-page":"1","article-title":"A fine-tuned Wav2vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"wang","year":"2021"},{"key":"ref10","first-page":"1","article-title":"Dynamic layer customization for noise robust speech emotion recognition in heterogeneous condition training","author":"wilf","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref1","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 (NeurIPS 2020)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1494"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053581"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1438"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","first-page":"1","article-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","author":"wagner","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2217"}],"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\/10097135.pdf?arnumber=10097135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:26Z","timestamp":1700506826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097135\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097135","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}