{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:02:46Z","timestamp":1772553766948,"version":"3.50.1"},"reference-count":31,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447678","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12031-12035","source":"Crossref","is-referenced-by-count":10,"title":["Generalization of Self-Supervised Learning-Based Representations for Cross-Domain Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Abinay Reddy","family":"Naini","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,Department of Electrical and Computer Engineering"}]},{"given":"Mary A.","family":"Kohler","sequence":"additional","affiliation":[{"name":"North Carolina State University,Laboratory for Analytic Sciences"}]},{"given":"Elizabeth","family":"Richerson","sequence":"additional","affiliation":[{"name":"North Carolina State University,Laboratory for Analytic Sciences"}]},{"given":"Donita","family":"Robinson","sequence":"additional","affiliation":[{"name":"North Carolina State University,Laboratory for Analytic Sciences"}]},{"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,Department of Electrical and Computer Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning (ICML 2022)","volume":"162","author":"Baevski"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1034"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097135"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200910"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414035"},{"key":"ref20","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019)","author":"Devlin","year":"2019"},{"key":"ref21","first-page":"369","article-title":"Connection-ist temporal classification: labelling unsegmented sequence data with recurrent neural networks","volume-title":"International Conference on Machine Learning (ICML 2006)","author":"Graves"},{"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":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref24","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","volume-title":"Advances in neural information processing systems (NIPS 2015)","author":"Rasmusi","year":"2015"},{"issue":"59","key":"ref25","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref28","first-page":"17","article-title":"Recording audio-visual emotional databases from actors: a closer look","volume-title":"Second International Workshop on Emotion: Corpora for Research on Emotion and Affect, International conference on Language Resources and Evaluation (LREC 2008)","author":"Busso"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.010"},{"key":"ref30","volume-title":"OVAL 741-2; June 23, 1972; White House Tapes","year":"1972"},{"key":"ref31","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations","author":"Kingma"}],"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\/10447678.pdf?arnumber=10447678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:34:39Z","timestamp":1722573279000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447678","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}