{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:14:12Z","timestamp":1784056452828,"version":"3.55.0"},"reference-count":238,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"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":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2023,4,1]]},"DOI":"10.1109\/taffc.2021.3114365","type":"journal-article","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T16:21:35Z","timestamp":1632241295000},"page":"1634-1654","source":"Crossref","is-referenced-by-count":122,"title":["Survey of Deep Representation Learning for Speech Emotion Recognition"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5662-4777","authenticated-orcid":false,"given":"Siddique","family":"Latif","sequence":"first","affiliation":[{"name":"University of Southern Queensland (USQ), Springfield, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0506-2409","authenticated-orcid":false,"given":"Rajib","family":"Rana","sequence":"additional","affiliation":[{"name":"University of Southern Queensland (USQ), Springfield, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3417-2834","authenticated-orcid":false,"given":"Sara","family":"Khalifa","sequence":"additional","affiliation":[{"name":"Distributed Sensing Systems Group, Data61–CSIRO, Pullenvale, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7517-0782","authenticated-orcid":false,"given":"Raja","family":"Jurdak","sequence":"additional","affiliation":[{"name":"Distributed Systems and Applied Data Sciences, Queensland University of Technology, Brisbane, Queensland, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9466-2475","authenticated-orcid":false,"given":"Junaid","family":"Qadir","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, College of Engineering, Qatar University, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[{"name":"GLAM – The Group on Language, Audio, and Music, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","first-page":"3","article-title":"Autoencoders, minimum description length and helmholtz free energy","author":"hinton","year":"1994","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref207","first-page":"34","article-title":"Databases of emotional speech","author":"campbell","year":"2000","journal-title":"Proc ISCA Tut Res Workshop (ITRW)Speech Emotion"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-325"},{"key":"ref59","author":"ng","year":"0"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2541318"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICET.2017.8281753"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013215010749"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-014-0047-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(97)80111-2"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/ICDH.2014.57"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917620"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/MTS.2019.2930273"},{"key":"ref209","article-title":"Multitask learning in connectionist speech recognition","author":"lu","year":"2004","journal-title":"Proc Australian Int Conf Speech Sci Technol"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6307"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2020.3006860"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref45","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","volume":"2","author":"lecun","year":"1989","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref48","first-page":"255","article-title":"Convolutional networks for images, speech, and time series","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref216","article-title":"Adversarial machine learning and speech emotion recognition: Utilizing generative adversarial networks for robustness","author":"latif","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref217","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"International Conference on Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"ref41","author":"hebb","year":"1949","journal-title":"The Organization of Behavior A Neuropsychological Theory"},{"key":"ref215","first-page":"341","article-title":"Federated learning for speech emotion recognition applications","author":"latif","year":"2020","journal-title":"Proc 19th ACM\/IEEE Int Conf Process Sensor Netw"},{"key":"ref44","first-page":"2377","article-title":"Training very deep networks","volume":"2","author":"srivastava","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2230222"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2415"},{"key":"ref49","first-page":"3920","article-title":"Direct modeling of speech emotion from raw speech","author":"latif","year":"2019","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/7437860"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref3","author":"konar","year":"2014","journal-title":"Emotion Recognition A Pattern Analysis Approach"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/749604"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2769"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462685"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00399"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops50388.2021.9473669"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054087"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.01.008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300014980"},{"key":"ref37","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref31","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017467"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref39","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref38","first-page":"1137","article-title":"Efficient learning of sparse representations with an energy-based model","author":"poultney","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1111\/j.1745-3984.2003.tb01108.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925513"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1255"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-917"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"roweis","year":"2000","journal-title":"Science"},{"key":"ref27","author":"lee","year":"2004","journal-title":"Feature Mapping Using PCA Locally Linear Embedding and Isometric Feature Mapping for EEG-Based Brain Computer Interface"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854169"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2293"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_12"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00071"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-692"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470393"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7919019"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273628"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-739"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853745"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1353"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953131"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366340"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3190"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.004"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref89","first-page":"223","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"2014","journal-title":"Proc Fifteenth Annu Conf Int Speech Commun Assoc"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref86","first-page":"5089","article-title":"End-to-end speech emotion recognition using deep neural networks","author":"tzirakis","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683293"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.01.011"},{"key":"ref138","article-title":"Deep representation learning for improving speech emotion recognition","volume":"2020","author":"latif","year":"2020","journal-title":"Doctoral Consortium Interspeech"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1625"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0644-8"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref82","first-page":"3501","article-title":"EMOVO corpus: An Italian emotional speech database","author":"costantini","year":"2014","journal-title":"Proc Int Conf Lang Resou Eval"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.58"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"ref84","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","author":"zadeh","year":"2018","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref142","first-page":"469","article-title":"Phone recognition with the mean-covariance restricted Boltzmann machine","author":"dahl","year":"2010","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-812"},{"key":"ref140","article-title":"Learning representations of affect from speech","author":"ghosh","year":"2105"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1400323"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2983669"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952656"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1175-x"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref107","first-page":"312","article-title":"The INTERSPEECH 2009 emotion challenge","author":"bjorn","year":"2009","journal-title":"Proc Annu Conf Int Speech Commun Assoc Conf"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref75","first-page":"19","article-title":"Expression and the nature of emotion","volume":"3","author":"ekman","year":"1984","journal-title":"Approaches to Emotion"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3194"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2093"},{"key":"ref71","article-title":"Recent advances in autoencoder-based representation learning","volume":"abs 1812 5069","author":"tschannen","year":"2018","journal-title":"CoRR"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2464"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref70","first-page":"2649","article-title":"Disentangling by factorising","author":"kim","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"ref233","article-title":"Multi-task learning for speech recognition: An overview","author":"pironkov","year":"2016","journal-title":"Proc 29th Eur Symp Artif Neural Netw Comput Intell Mach Learn"},{"key":"ref73","first-page":"109","article-title":"A state of the art review on emotional speech databases","author":"ververidis","year":"2003","journal-title":"Proc 1st Richmedia Conf"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","article-title":"Toward detecting emotions in spoken dialogs","volume":"13","author":"lee","year":"2005","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2512598"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2821192"},{"key":"ref68","first-page":"1","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"},{"key":"ref117","article-title":"Does visual self-supervision improve learning of speech representations for emotion recognition","author":"shukla","year":"2021","journal-title":"IEEE Trans Affect Comput"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12047"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015885"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3026823"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-2585-3_15"},{"key":"ref236","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","author":"van seijen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-256"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref237","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Int Conf Learn Representations"},{"key":"ref66","first-page":"226","article-title":"Deep generative stochastic networks trainable by backprop","author":"bengio","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461750"},{"key":"ref234","article-title":"Disentangling the independently controllable factors of variation by interacting with the world","volume":"abs 1802 9484","author":"thomas","year":"0","journal-title":"CoRR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/S0364-0213(85)80012-4"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2672753"},{"key":"ref235","first-page":"2170","article-title":"DeepMDP: Learning continuous latent space models for representation learning","author":"gelada","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref60","article-title":"K-sparse autoencoders","author":"makhzani","year":"2013"},{"key":"ref122","first-page":"1491","article-title":"Fast human detection using a cascade of histograms of oriented gradients","author":"zhu","year":"2006","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461058"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2355"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273592"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1494"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2684799"},{"key":"ref173","first-page":"53","article-title":"Multi-task representation learning","author":"bouguelia","year":"2017","journal-title":"Proc 30th Annu Workshop Swedish Artif Intell Soc"},{"key":"ref174","first-page":"1113","article-title":"Towards speech emotion recognition “in the wild","author":"kim","year":"2017","journal-title":"Proc Annu Conf Int Speech Commun Assoc Situated Interact"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref179","article-title":"ALBERT: A Lite BERT for self-supervised learning of language representations","volume":"abs 1909 11942","author":"lan","year":"2019","journal-title":"CoRR"},{"key":"ref180","article-title":"VQ-WAV2VEC: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"CoRR"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053415"},{"key":"ref188","article-title":"A survey on deep reinforcement learning for audio-based applications","author":"latif","year":"2021"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326775"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383618"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref183","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref148","article-title":"Semi-supervised learning literature survey","author":"zhu","year":"2005"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref146","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref147","article-title":"Cross corpus speech emotion classification-an effective transfer learning technique","author":"latif","year":"2018"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00464"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3000751"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2998118"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1883"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682823"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470363"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2759338"},{"key":"ref159","author":"thrun","year":"2012","journal-title":"Learning to Learn"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1421"},{"key":"ref158","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","author":"bengio","year":"2012","journal-title":"Proc ICML Workshop Unsupervised Transfer Learn"},{"key":"ref166","first-page":"28","article-title":"Releasing a thoroughly annotated and processed spontaneous emotional database: The FAU Aibo emotion corpus","author":"batliner","year":"2008","journal-title":"Proc Satell Workshop LREC"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916092"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362058"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683299"},{"key":"ref162","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2972926"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854517"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"ref15","first-page":"5223","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Int Conf Learn Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICICCT.2017.7975169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2017.05.001"},{"key":"ref17","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"Int Conf Learn Representations"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Proces Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1168654"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-014-9239-3"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.111.2.256"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(90)90006-R"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683648"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2561"},{"key":"ref197","first-page":"1513","article-title":"Unlabeled data: Now it helps, now it doesn’t","volume":"21","author":"singh","year":"2008","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8452-2"},{"key":"ref195","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","author":"locatello","year":"2019","journal-title":"Proc IEEE Intern Conf on Machine Learning"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.45"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0617-4_16"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953232"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10138707\/09543566.pdf?arnumber=9543566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T14:09:57Z","timestamp":1687183797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9543566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":238,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2021.3114365","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.16689484.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.16689484","asserted-by":"object"}],"is-supplemented-by":[{"id-type":"doi","id":"10.36227\/techrxiv.16689484","asserted-by":"object"}]},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,1]]}}}