{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T17:23:22Z","timestamp":1764350602994,"version":"3.37.3"},"reference-count":80,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3040797","type":"journal-article","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T20:56:11Z","timestamp":1606424171000},"page":"223509-223528","source":"Crossref","is-referenced-by-count":12,"title":["High-Fidelity Audio Generation and Representation Learning With Guided Adversarial Autoencoder"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8882-5194","authenticated-orcid":false,"given":"Kazi Nazmul","family":"Haque","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0506-2409","authenticated-orcid":false,"given":"Rajib","family":"Rana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bjorn W.","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_14"},{"key":"ref76","article-title":"Mixed precision training","author":"micikevicius","year":"2017","journal-title":"arXiv 1710 03740"},{"key":"ref77","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"2018","journal-title":"arXiv 1809 11096"},{"key":"ref39","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"latif","year":"2020","journal-title":"arXiv 2001 00378"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"ref38","article-title":"Effectiveness of self-supervised pre-training for speech recognition","author":"baevski","year":"2019","journal-title":"arXiv 1911 03912"},{"key":"ref75","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref78","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":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref30","article-title":"Learning audio representations via phase prediction","author":"de chaumont quitry","year":"2019","journal-title":"arXiv 1910 11910"},{"key":"ref37","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"arXiv 1910 05453"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref35","article-title":"Learning robust and multilingual speech representations","author":"kawakami","year":"2020","journal-title":"arXiv 2001 11128"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref60","article-title":"Unsupervised and semi-supervised learning with categorical generative adversarial networks","author":"tobias springenberg","year":"2015","journal-title":"arXiv 1511 06390"},{"key":"ref62","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","article-title":"Semi-supervised conditional GANs","author":"sricharan","year":"2017","journal-title":"arXiv 1708 05789"},{"key":"ref28","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume":"abs 1803 7728","author":"gidaris","year":"2018","journal-title":"CoRR"},{"key":"ref63","first-page":"1","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","volume":"abs 1804 3209","author":"warden","year":"2018","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1214"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref65","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"Proc Int Conf Mach Learn (PMLR)"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref66","first-page":"4352","article-title":"Adversarial generation of time-frequency features with application in audio synthesis","volume":"abs 1902 4072","author":"marafioti","year":"2019","journal-title":"CoRR"},{"key":"ref67","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local NASH equilibrium","author":"heusel","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","article-title":"A note on the inception score","author":"barratt","year":"2018","journal-title":"arXiv 1801 01973"},{"key":"ref1","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","author":"locatello","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","article-title":"Image denoising and restoration with CNN-LSTM encoder decoder with direct attention","author":"nazmul haque","year":"2018","journal-title":"arXiv 1801 05141"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01061"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00198"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref23","first-page":"1679","article-title":"Self-supervised generalisation with meta auxiliary learning","author":"liu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2019","journal-title":"arXiv 1908 08530"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1375"},{"key":"ref50","article-title":"Adversarial auto-encoders for speech based emotion recognition","author":"sahu","year":"2018","journal-title":"arXiv 1806 02146"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966273"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_8"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/978-3-319-12976-1_25","article-title":"The large time-frequency analysis toolbox 2.0","author":"pr?\u0161a","year":"2014","journal-title":"Sound Music and Motion"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref55","first-page":"1","article-title":"Adversarial feature learning","volume":"abs 1605 9782","author":"donahue","year":"2016","journal-title":"CoRR"},{"key":"ref54","article-title":"Adversarially learned inference","author":"dumoulin","year":"2016","journal-title":"arXiv 1606 00704"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref52","first-page":"1","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR"},{"key":"ref10","article-title":"GANSynth: Adversarial neural audio synthesis","author":"engel","year":"2019","journal-title":"arXiv 1902 08710"},{"key":"ref11","first-page":"1","article-title":"Adversarial audio synthesis","author":"donahue","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref40","first-page":"1","article-title":"Sequence to sequence autoencoders for unsupervised representation learning from audio","author":"amiriparian","year":"2017","journal-title":"Proc Workshop (DCASE)"},{"key":"ref12","article-title":"Adversarial generation of time-frequency features with application in audio synthesis","author":"marafioti","year":"2019","journal-title":"arXiv 1902 04072"},{"key":"ref13","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume":"abs 1809 11096","author":"brock","year":"2018","journal-title":"CoRR"},{"key":"ref14","article-title":"Guided generative adversarial neural network for representation learning and high fidelity audio generation using fewer labelled audio data","author":"nazmul haque","year":"2020","journal-title":"arXiv 2003 02836"},{"key":"ref15","article-title":"High-fidelity image generation with fewer labels","author":"lucic","year":"2019","journal-title":"arXiv 1903 02271"},{"key":"ref16","first-page":"899","article-title":"Generalized denoising auto-encoders as generative models","volume":"1","author":"bengio","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref80","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"2017","journal-title":"arXiv 1710 10196"},{"key":"ref4","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":"ref3","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume":"abs 1511 6434","author":"radford","year":"2015","journal-title":"CoRR"},{"key":"ref6","first-page":"10541","article-title":"Large scale adversarial representation learning","author":"donahue","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref8","article-title":"Adversarial autoencoders","author":"makhzani","year":"2015","journal-title":"arXiv 1511 05644"},{"key":"ref7","article-title":"InfoVAE: Information maximizing variational autoencoders","author":"zhao","year":"2017","journal-title":"arXiv 1706 02262"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-883"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268911"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952656"},{"key":"ref47","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref41","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"Learning representations of affect from speech","author":"ghosh","year":"2015","journal-title":"arXiv 1511 04747"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09272282.pdf?arnumber=9272282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:13Z","timestamp":1639770913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9272282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3040797","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}