{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:57:14Z","timestamp":1781110634206,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NIH","award":["1R01MH122367-01"],"award-info":[{"award-number":["1R01MH122367-01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/taffc.2025.3629970","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:44Z","timestamp":1762455224000},"page":"656-669","source":"Crossref","is-referenced-by-count":4,"title":["Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition With Text Description of the Environment"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1175-1577","authenticated-orcid":false,"given":"Seong-Gyun","family":"Leem","sequence":"first","affiliation":[{"name":"Meta Reality Labs, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4405-9031","authenticated-orcid":false,"given":"Daniel","family":"Fulford","sequence":"additional","affiliation":[{"name":"Occupational Therapy and Psychological and Brain Sciences, Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6613-8668","authenticated-orcid":false,"given":"Jukka-Pekka","family":"Onnela","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0446-4000","authenticated-orcid":false,"given":"David","family":"Gard","sequence":"additional","affiliation":[{"name":"Psychology Department, San Francisco State University, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4075-4072","authenticated-orcid":false,"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"Wav2Vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Proc. Adv. in Neural Inf. Process. Syst. (NeurIPS 2020)","volume":"33","author":"Baevski","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2444"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-311"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388175"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3056421"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2020.11.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3105939"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-819"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-921"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-01571-2_27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2006-150"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747705"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACII52823.2021.9597437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1438"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096968"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097135"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1034"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML 2021)","volume":"139","author":"Radford","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1591"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1832"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.2994107"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3340603"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-35"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1248"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1226"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-469"},{"key":"ref37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2217"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref42","article-title":"The MSP-Podcast corpus","author":"Busso","year":"2025"},{"key":"ref43","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"Proc. Int. Soc. Music Inf. Retrieval (ISMIR 2017)","author":"Fonseca","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref47","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.2478\/pralin-2018-0002"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-519"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-117"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA49011.2020.00096"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11418735\/11230645.pdf?arnumber=11230645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:38Z","timestamp":1772571218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":59,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3629970","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}