{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:20:13Z","timestamp":1776889213796,"version":"3.51.2"},"reference-count":92,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100012774","name":"Innovationsfonden","doi-asserted-by":"publisher","award":["9065-00046"],"award-info":[{"award-number":["9065-00046"]}],"id":[{"id":"10.13039\/100012774","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3321975","type":"journal-article","created":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T17:59:39Z","timestamp":1698256779000},"page":"164-177","source":"Crossref","is-referenced-by-count":8,"title":["A Two-Stage Deep Representation Learning-Based Speech Enhancement Method Using Variational Autoencoder and Adversarial Training"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7120-5842","authenticated-orcid":false,"given":"Yang","family":"Xiang","sequence":"first","affiliation":[{"name":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6278-9353","authenticated-orcid":false,"given":"Jesper Lisby","family":"H\u00f8jvang","sequence":"additional","affiliation":[{"name":"Capturi A\/S, Aarhus, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Morten H\u00f8jfeldt","family":"Rasmussen","sequence":"additional","affiliation":[{"name":"Capturi A\/S, Aarhus, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3586-7969","authenticated-orcid":false,"given":"Mads Gr\u00e6sb\u00f8ll","family":"Christensen","sequence":"additional","affiliation":[{"name":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1047"},{"key":"ref57","first-page":"359","article-title":"A deep representation learning speech enhancement method using $\\beta$-vae","author":"xiang","year":"0","journal-title":"Proc 30th Eur Signal Process Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref56","article-title":"Understanding disentangling in $\\beta$-VAE","author":"burgess","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref59","first-page":"271","article-title":"f-GAN: Training generative neural samplers using variational divergence minimization","volume":"29","author":"nowozin","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414620"},{"key":"ref58","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747036"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553039"},{"key":"ref55","first-page":"1","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872128"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"ref92","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput - Assist Interv"},{"key":"ref51","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021"},{"key":"ref50","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014"},{"key":"ref91","first-page":"1","article-title":"Phase-aware speech enhancement with deep complex U-Net","author":"choi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref90","article-title":"Deep complex networks","author":"trabelsi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054254"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414363"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683704"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref86","first-page":"6493","article-title":"DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","author":"reddy","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2940662"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-343"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632676"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414060"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471709"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2505416"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-220"},{"key":"ref3","article-title":"Impact of digital surge during COVID-19 pandemic: A viewpoint on research and practice","volume":"55","author":"pandey","year":"2020","journal-title":"Int J Inf Manage"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.818031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref82","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref81","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref83","first-page":"626","article-title":"SDR–half-baked or well done?","author":"le roux","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596320"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_8"},{"key":"ref34","first-page":"1876","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3087"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/e24040456"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/9781108779302"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref30","first-page":"1","article-title":"ReduNet: A white-box deep network from the principle of maximizing rate reduction","volume":"23","author":"chan","year":"2022","journal-title":"J Mach Learn Res"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268911"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref71","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"ref72","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref67","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053630350"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038111"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2997118"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414062"},{"key":"ref66","first-page":"ii\/53?ii\/56","article-title":"A family of mlp based nonlinear spectral estimators for noise reduction","volume":"2","author":"xie","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref65","article-title":"Networks for speech enhancement","volume":"139","author":"wan","year":"1999","journal-title":"Handbook of Neural Networks for Speech Processing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/2331216518770964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.5119226"},{"key":"ref60","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","first-page":"52","article-title":"IntroVAE: Introspective variational autoencoders for photographic image synthesis","author":"huang","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00088"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10296040.pdf?arnumber=10296040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:33:10Z","timestamp":1700508790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10296040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3321975","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}