{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:43:00Z","timestamp":1771915380279,"version":"3.50.1"},"reference-count":197,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Eastern Mediterranean University, through the C T\u00dcR\u00dc B\u0130L\u0130MSEL ARA\u015eTIRMA PROJELER\u0130 (BAP-C) Project","award":["BAP-C-02-18-0001"],"award-info":[{"award-number":["BAP-C-02-18-0001"]}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2018\/26455-8"],"award-info":[{"award-number":["2018\/26455-8"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2020\/01928-0"],"award-info":[{"award-number":["2020\/01928-0"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2018\/12579-7"],"award-info":[{"award-number":["2018\/12579-7"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2019\/07665-4"],"award-info":[{"award-number":["2019\/07665-4"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3042328","type":"journal-article","created":{"date-parts":[[2020,12,3]],"date-time":"2020-12-03T20:48:57Z","timestamp":1607028537000},"page":"218499-218529","source":"Crossref","is-referenced-by-count":31,"title":["Generative Adversarial Networks in Human Emotion Synthesis: A Review"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3120-5370","authenticated-orcid":false,"given":"Noushin","family":"Hajarolasvadi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7107-0888","authenticated-orcid":false,"given":"Miguel Arjona","family":"Ramirez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6599-2344","authenticated-orcid":false,"given":"Wesley","family":"Beccaro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6933-6659","authenticated-orcid":false,"given":"Hasan","family":"Demirel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref170","year":"2001","journal-title":"Perceptual Evaluation of Speech Quality (PESQ) An Objective Method for End to-End Speech Quality Assessment of Narrow-Band Telephone Networks and Speech Codecs"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref171","article-title":"GANSynth: Adversarial neural audio synthesis","author":"engel","year":"2019","journal-title":"arXiv 1902 08710"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref173","article-title":"End-to-end speech-driven facial animation with temporal GANs","author":"vougioukas","year":"2018","journal-title":"arXiv 1805 09313"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461852"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref39","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref38","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682970"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/618"},{"key":"ref30","article-title":"MojiTalk: Generating emotional responses at scale","author":"zhou","year":"2017","journal-title":"arXiv 1711 04090"},{"key":"ref37","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"jimenez rezende","year":"2014","journal-title":"arXiv 1401 4082"},{"key":"ref36","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref185","first-page":"2018","article-title":"Stabilizing training of generative adversarial networks through regularization","author":"roth","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref184","first-page":"6886","article-title":"CMCGAN: A uniform framework for cross-modal visual-audio mutual generation","author":"hao","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486594"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref189","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"arXiv 1611 01144"},{"key":"ref188","article-title":"GANS for sequences of discrete elements with the gumbel-softmax distribution","author":"kusner","year":"2016","journal-title":"arXiv 1611 04051"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00888"},{"key":"ref186","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"2018","journal-title":"arXiv 1801 04406"},{"key":"ref28","article-title":"Variational autoencoders for learning latent representations of speech emotion: A preliminary study","author":"latif","year":"2017","journal-title":"arXiv 1712 08708"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.369"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2916092"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0022-1031(81)90037-8"},{"key":"ref22","first-page":"1","article-title":"ExprGAN: Facial expression editing with controllable expression intensity","author":"ding","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/h0024648"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref25","article-title":"CAKE: Compact and accurate K-dimensional representation of emotion","author":"kervadec","year":"2018","journal-title":"arXiv 1807 11215"},{"key":"ref50","article-title":"Unsupervised and semi-supervised learning with categorical generative adversarial networks","author":"tobias springenberg","year":"2015","journal-title":"arXiv 1511 06390"},{"key":"ref51","article-title":"BEGAN: Boundary equilibrium generative adversarial networks","author":"berthelot","year":"2017","journal-title":"arXiv 1703 10717"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref150","article-title":"Improved speech enhancement with the Wave-U-Net","author":"macartney","year":"2018","journal-title":"arXiv 1811 11307"},{"key":"ref152","article-title":"ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion","author":"kameoka","year":"2018","journal-title":"arXiv 1811 01609"},{"key":"ref151","article-title":"ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","author":"kameoka","year":"2018","journal-title":"arXiv 1808 05092"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"key":"ref149","article-title":"WaveCycleGAN2: Time-domain neural post-filter for speech waveform generation","author":"tanaka","year":"2019","journal-title":"arXiv 1904 02892"},{"key":"ref59","first-page":"271","article-title":"F-GAN: Training generative neural samplers using variational divergence minimization","author":"nowozin","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SmartWorld.2018.00113"},{"key":"ref56","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref55","article-title":"CapsuleGAN: Generative adversarial capsule network","author":"jaiswal","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref54","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","volume":"70","author":"odena","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref52","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","article-title":"Stabilizing adversarial nets with prediction methods","author":"yadav","year":"2017","journal-title":"arXiv 1705 07364"},{"key":"ref167","article-title":"MelNet: A generative model for audio in the frequency domain","author":"vasquez","year":"2019","journal-title":"arXiv 1906 01083"},{"key":"ref166","article-title":"ET-GAN: Cross-language emotion transfer based on cycle-consistent generative adversarial networks","author":"jia","year":"2019","journal-title":"arXiv 1905 11173"},{"key":"ref165","article-title":"BAGAN: Data augmentation with balancing GAN","author":"mariani","year":"2018","journal-title":"arXiv 1803 09655"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-34"},{"key":"ref163","article-title":"Attacking speaker recognition with deep generative models","author":"cai","year":"2018","journal-title":"arXiv 1801 02384"},{"key":"ref162","first-page":"29","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"hirsch","year":"2000","journal-title":"Proc ISCA Tutorial and Research Workshop on Automatic Speech Recognition Challenges for the New Millennium"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref160","first-page":"223","article-title":"The CMU arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc 5th ISCA Workshop Speech Synth"},{"key":"ref4","article-title":"A review on generative adversarial networks: Algorithms, theory, and applications","author":"gui","year":"2020","journal-title":"arXiv 2001 06937"},{"key":"ref3","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510583"},{"key":"ref8","article-title":"Comparative study on generative adversarial networks","author":"hitawala","year":"2018","journal-title":"arXiv 1801 04271"},{"key":"ref159","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20912-4_24"},{"key":"ref49","article-title":"CGANs with projection discriminator","author":"miyato","year":"2018","journal-title":"arXiv 1802 05637"},{"key":"ref157","first-page":"159","author":"schuller","year":"1988","journal-title":"Emotion Affect and Personality in Speech and Language Processing"},{"key":"ref9","article-title":"Generative adversarial networks in computer vision: A survey and taxonomy","author":"wang","year":"2019","journal-title":"arXiv 1906 01529"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref46","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv 1511 06434"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref48","first-page":"5767","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"arXiv 1802 05957"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.202"},{"key":"ref41","first-page":"1486","article-title":"Deep generative image models using a Laplacian pyramid of adversarial networks","author":"denton","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref43","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"2017","journal-title":"arXiv 1710 10196"},{"key":"ref73","author":"ekman","year":"1978","journal-title":"Facial Action Coding System"},{"key":"ref72","first-page":"421","article-title":"Generating facial expressions with deep belief nets","author":"susskind","year":"2008","journal-title":"Affective Computing Emotion Modelling Synthesis and Recognition"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref70","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"arXiv 1605 05396"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref77","first-page":"211","article-title":"A 3D facial expression database for facial behavior research","author":"yin","year":"2006","journal-title":"Proc 7th Int Conf Autom Face Gesture Recognit"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1080\/02699930903485076"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref60","article-title":"Energy-based generative adversarial network","author":"zhao","year":"2016","journal-title":"arXiv 1609 03126"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1819"},{"key":"ref61","article-title":"Adversarial feature learning","author":"donahue","year":"2016","journal-title":"arXiv 1605 09782"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref65","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"boesen lindbo larsen","year":"2015","journal-title":"arXiv 1512 09300"},{"key":"ref66","article-title":"Adversarially learned inference","author":"dumoulin","year":"2016","journal-title":"arXiv 1606 00704"},{"key":"ref67","first-page":"700","article-title":"Unsupervised image-to-image translation networks","author":"liu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref69","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","volume":"70","author":"kim","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01100"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054071"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.141"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.267"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00537"},{"key":"ref94","article-title":"MeshGAN: Non-linear 3D morphable models of faces","author":"cheng","year":"2019","journal-title":"arXiv 1903 10384"},{"key":"ref190","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"2016","journal-title":"arXiv 1611 00712"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00741"},{"key":"ref191","first-page":"2513","article-title":"Fisher GAN","author":"mroueh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref92","first-page":"2","volume":"91","author":"lundqvist","year":"1998","journal-title":"The Karolinska Directed Emotional Faces (KDEF)"},{"key":"ref192","article-title":"Sobolev GAN","author":"mroueh","year":"2017","journal-title":"arXiv 1711 04894"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107111"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521424"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240612"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_18"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.624"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00035"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref84","first-page":"14","article-title":"The Japanese female facial expression (JAFFE) database","author":"lyons","year":"1998","journal-title":"Proc 3rd Int Conf Autom Face Gesture Recognit"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"ref80","article-title":"EmotioNet challenge: Recognition of facial expressions of emotion in the wild","author":"fabian benitez-quiroz","year":"2017","journal-title":"arXiv 1703 01210"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-6655-0"},{"key":"ref85","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","author":"huang","year":"2007"},{"key":"ref86","article-title":"Learning to augment expressions for few-shot fine-grained facial expression recognition","author":"wang","year":"2020","journal-title":"arXiv 2001 06144"},{"key":"ref87","first-page":"1","article-title":"The mug facial expression database","author":"aifanti","year":"2010","journal-title":"Proc 8th Int Workshop Image Analy Multimedia Interactive Services (WIAMIS)"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.280"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00259"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2018.6576"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093557"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803764"},{"key":"ref124","first-page":"196","article-title":"Bringing portraits to life","volume":"36","author":"elor","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3422852.3423483"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"ref130","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350937"},{"key":"ref134","article-title":"A survey on face data augmentation","author":"wang","year":"2019","journal-title":"arXiv 1904 11685"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref132","article-title":"MetaPix: Few-shot video retargeting","author":"lee","year":"2019","journal-title":"arXiv 1910 04742"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.009"},{"key":"ref135","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref138","article-title":"Adversarial machine learning and speech emotion recognition: Utilizing generative adversarial networks for robustness","author":"latif","year":"2018","journal-title":"arXiv 1811 11402"},{"key":"ref137","article-title":"Generating images with recurrent adversarial networks","author":"jiwoong im","year":"2016","journal-title":"arXiv 1602 05110"},{"key":"ref139","article-title":"Nonparallel emotional speech conversion","author":"gao","year":"2018","journal-title":"arXiv 1811 01174"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706651"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1883"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2561"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310398"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3355397"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756560"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00092"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916751"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756558"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00046"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93040-4_28"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3390\/sym10090414"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964955"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531363"},{"key":"ref110","article-title":"FaceFeat-GAN: A two-stage approach for identity-preserving face synthesis","author":"shen","year":"2018","journal-title":"arXiv 1812 01288"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3301282"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref12","article-title":"An introduction to image synthesis with generative adversarial nets","author":"huang","year":"2018","journal-title":"arXiv 1803 04469"},{"key":"ref13","article-title":"The GAN landscape: Losses, architectures, regularization, and normalization","author":"kurach","year":"2018","journal-title":"arXiv 1807 04720"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101552"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2019918334"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/TST.2017.8195348"},{"key":"ref118","article-title":"Deep identity-aware transfer of facial attributes","author":"li","year":"2016","journal-title":"arXiv 1610 05586"},{"key":"ref17","article-title":"A survey and taxonomy of adversarial neural networks for Text-to-Image synthesis","author":"agnese","year":"2019","journal-title":"arXiv 1910 09399"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.578"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2017.01.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.54.3.414"},{"key":"ref119","article-title":"Invertible conditional GANs for image editing","author":"perarnau","year":"2016","journal-title":"arXiv 1611 06355"},{"key":"ref114","first-page":"1431","article-title":"Learning to disentangle factors of variation with manifold interaction","author":"reed","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref113","article-title":"Semantic facial expression editing using autoencoded flow","author":"yeh","year":"2016","journal-title":"arXiv 1611 09961"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273626"},{"key":"ref115","article-title":"Discovering hidden factors of variation in deep networks","author":"cheung","year":"2014","journal-title":"arXiv 1412 6583"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00202"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275043"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09279199.pdf?arnumber=9279199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:22Z","timestamp":1639770922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9279199\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":197,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3042328","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}