{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:35:24Z","timestamp":1770467724850,"version":"3.49.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3519761","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:40:41Z","timestamp":1734550841000},"page":"193101-193114","source":"Crossref","is-referenced-by-count":5,"title":["Domain Adapting Deep Reinforcement Learning for Real-World Speech Emotion Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3156-3327","authenticated-orcid":false,"given":"Thejan","family":"Rajapakshe","sequence":"first","affiliation":[{"name":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajib","family":"Rana","sequence":"additional","affiliation":[{"name":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3417-2834","authenticated-orcid":false,"given":"Sara","family":"Khalifa","sequence":"additional","affiliation":[{"name":"School of Information Systems, Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003838"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916092"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023339"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/int.22291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688269"},{"key":"ref9","article-title":"Unsupervised speech domain adaptation based on disentangled representation learning for robust speech recognition","author":"Park","year":"2019","journal-title":"arXiv:1904.06086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3237025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197465"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW59127.2023.10388120"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC51323.2021.9498861"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-148"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-022-00772-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105708"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2023.102262"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12233"},{"issue":"1","key":"ref23","doi-asserted-by":"crossref","first-page":"159","DOI":"10.12928\/telkomnika.v21i1.24261","article-title":"An evolutionary optimization method for selecting features for speech emotion recognition","volume":"21","author":"Bagadi","year":"2023","journal-title":"TELKOMNIKA (Telecommunication Comput. Electron. Control)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_17"},{"key":"ref25","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref26","first-page":"1859","article-title":"Domain adaptation for reinforcement learning on the Atari","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst., AAMAS","author":"Carr"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICOIACT.2018.8350761"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10224-2"},{"key":"ref30","article-title":"Feature learning in deep neural networks-studies on speech recognition tasks","author":"Yu","year":"2013","journal-title":"arXiv:1301.3605"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2018.8499077"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366340"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","article-title":"The arcade learning environment: An evaluation platform for general agents","volume":"47","author":"Bellemare","year":"2013","journal-title":"J. Artif. Intell. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461058"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.008"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icdew.2006.145"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.10.017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3086395"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"issue":"3","key":"ref43","doi-asserted-by":"crossref","first-page":"3355","DOI":"10.32604\/csse.2023.037373","article-title":"TC-Net: A modest & lightweight emotion recognition system using temporal convolution network","volume":"46","author":"Ishaq","year":"2023","journal-title":"Comput. Syst. Sci. Eng."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref47","first-page":"1733","article-title":"Unsupervised adversarial domain adaptation for acoustic scene classification","volume-title":"Proc. Detection Classification Acoustic Scenes Events","author":"Gharib"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178934"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418813"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1861"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178232"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925513"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548328"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1248"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref57","article-title":"Pre-training in deep reinforcement learning for automatic speech recognition","author":"Rajapakshe","year":"2019","journal-title":"arXiv:1910.11256"},{"key":"ref58","article-title":"Deep reinforcement learning with pre-training for time-efficient training of automatic speech recognition","author":"Rajapakshe","year":"2020","journal-title":"arXiv:2005.11172"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3511616.3513104"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2900768"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MEC.2011.6025669"},{"key":"ref62","first-page":"1","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Jaitly"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.122712"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2967791"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC51323.2021.9498598"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747129"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2017.8300161"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN52536.2021.9566046"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPC51351.2021.9451810"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref72","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"Latif","year":"2020","journal-title":"arXiv:2001.00378"},{"key":"ref73","volume-title":"Keras","author":"Chollet","year":"2015"},{"key":"ref74","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2015","journal-title":"arXiv:1603.04467"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.26686\/wgtn.17147651.v1"},{"key":"ref78","first-page":"1","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.2478\/amcs-2013-0060"},{"key":"ref80","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv:1701.07274"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10806705.pdf?arnumber=10806705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T06:19:35Z","timestamp":1735107575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3519761","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}