{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:44:03Z","timestamp":1781585043426,"version":"3.54.5"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DFG's Reinhart Koselleck","award":["442218748"],"award-info":[{"award-number":["442218748"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3263585","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T17:39:53Z","timestamp":1680284393000},"page":"10745-10759","source":"Crossref","is-referenced-by-count":319,"title":["Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap"],"prefix":"10.1109","volume":"45","author":[{"given":"Johannes","family":"Wagner","sequence":"first","affiliation":[{"name":"audEERING GmbH, Gilching, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8338-617X","authenticated-orcid":false,"given":"Andreas","family":"Triantafyllopoulos","sequence":"additional","affiliation":[{"name":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hagen","family":"Wierstorf","sequence":"additional","affiliation":[{"name":"audEERING GmbH, Gilching, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7453-5612","authenticated-orcid":false,"given":"Maximilian","family":"Schmitt","sequence":"additional","affiliation":[{"name":"audEERING GmbH, Gilching, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2689-0545","authenticated-orcid":false,"given":"Felix","family":"Burkhardt","sequence":"additional","affiliation":[{"name":"audEERING GmbH, Gilching, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Eyben","sequence":"additional","affiliation":[{"name":"audEERING GmbH, Gilching, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"audEERING GmbH, Gilching, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3106619"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3021015"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054709"},{"key":"ref15","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aao6760"},{"key":"ref14","article-title":"On the opportunities and risks of foundation models","author":"bommasani","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref53","article-title":"The measure and mismeasure of fairness: A critical review of fair machine learning","author":"corbett-davies","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"ref55","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1658"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/e21080741"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref19","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","author":"baevski","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-104"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2317187"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7554349"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2962027"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3306"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414896"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1149"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref9","article-title":"Multistage linguistic conditioning of convolutional layers for speech emotion recognition","author":"triantafyllopoulos","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(77)90037-X"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref40","article-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"babu","year":"2021"},{"key":"ref35","article-title":"AequeVox: Automated fairness testing of speech recognition systems","author":"rajan","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1708"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref30","article-title":"Representation learning through cross-modal conditional teacher-student training for speech emotion recognition","author":"srinivasan","year":"2021"},{"key":"ref33","article-title":"Best practices for noise-based augmentation to improve the performance of emotion recognition ”in the wild","author":"jaiswal","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413910"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref24","article-title":"The role of phonetic units in speech emotion recognition","author":"yuan","year":"2021"},{"key":"ref23","article-title":"Using large pre-trained models with cross-modal attention for multi-modal emotion recognition","author":"krishna","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73706-5_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref20","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":"ref64","first-page":"201","article-title":"Why does unsupervised pre-training help deep learning?","author":"erhan","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6221127"},{"key":"ref66","article-title":"Poor man's BERT: Smaller and faster transformer models","author":"sajjad","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021. 3114365"},{"key":"ref65","first-page":"512","article-title":"What is being transferred in transfer learning?","author":"neyshabur","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688036"},{"key":"ref27","article-title":"Exploring wav2vec 2.0 fine-tuning for improved speech emotion recognition","author":"chen","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"ref62","article-title":"Underspecification presents challenges for credibility in modern machine learning","author":"d\u2019amour","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3187336"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10089511.pdf?arnumber=10089511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:58:13Z","timestamp":1693245493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3263585","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}