{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:33:21Z","timestamp":1776882801643,"version":"3.51.2"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832296","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"510-517","source":"Crossref","is-referenced-by-count":15,"title":["Open-Emotion: A Reproducible EMO-Superb For Speech Emotion Recognition Systems"],"prefix":"10.1109","author":[{"given":"Haibin","family":"Wu","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Huang-Cheng","family":"Chou","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Taiwan"}]},{"given":"Kai-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Lucas","family":"Goncalves","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,USA"}]},{"given":"Jiawei","family":"Du","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Chi-Chun","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Taiwan"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096808"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273633"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273615"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388175"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref20","first-page":"1298","article-title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Baevski"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref22","article-title":"vqwav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019","journal-title":"arXiv preprint arXiv:1910.05453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref25","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018","journal-title":"arXiv preprint arXiv:1807.03748"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3225198"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1702247114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/1948550610393987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11041"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.11.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3411290"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.308"},{"key":"ref33","article-title":"Macro f1 and macro f1","author":"Opitz","year":"2019","journal-title":"arXiv preprint arXiv:1911.03347"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2019-3"},{"key":"ref36","article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022770"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1113"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1073"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-788"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746990"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023428"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832296.pdf?arnumber=10832296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:25Z","timestamp":1737100225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832296","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}