{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:28:31Z","timestamp":1781087311889,"version":"3.54.1"},"reference-count":56,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFB1302402"],"award-info":[{"award-number":["2017YFB1302402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1736202"],"award-info":[{"award-number":["U1736202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GuSu Innovation Fund","award":["ZXT20200003"],"award-info":[{"award-number":["ZXT20200003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.3016498","type":"journal-article","created":{"date-parts":[[2020,8,14]],"date-time":"2020-08-14T20:41:09Z","timestamp":1597437669000},"page":"2598-2609","source":"Crossref","is-referenced-by-count":47,"title":["Data Augmentation Using Deep Generative Models for Embedding Based Speaker Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9597-9829","authenticated-orcid":false,"given":"Yexin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2352-4002","authenticated-orcid":false,"given":"Zhanghao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853695"},{"key":"ref38","first-page":"14","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"0","journal-title":"Proc Odyssey"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref37","first-page":"194","article-title":"The speaker partitioning problem","author":"br\u00fcmmer","year":"0","journal-title":"Proc Odyssey"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44415-3_47"},{"key":"ref28","article-title":"Discriminative and generative approaches for long-and short-term speaker characteristics modeling: Application to speaker verification","author":"dehak","year":"2009"},{"key":"ref27","article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","author":"kenny","year":"2005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1769"},{"key":"ref2","article-title":"Overcoming resource limitations in the processing of unlimited speech: Applications to speaker and language recognition","author":"shum","year":"2016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706575"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462624"},{"key":"ref24","article-title":"But system description to Voxceleb speaker recognition challenge 2019","author":"zeinali","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2248"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref51","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref55","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref54","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref53","article-title":"Pytorch implementation of wgan","author":"kristiadi","year":"2016"},{"key":"ref52","article-title":"How to train a gan? tips and tricks to make GANS work","author":"chintala","year":"2016"},{"key":"ref10","first-page":"237","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref11","first-page":"105","article-title":"Bottleneck features for speaker recognition","author":"yaman","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-32"},{"key":"ref12","first-page":"1327","article-title":"Tandem deep features for text-dependent speaker verification","author":"fu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-883"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-51"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICNIDC.2018.8525526"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659966"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref46","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014"},{"key":"ref45","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref47","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014"},{"key":"ref42","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref41","first-page":"260","article-title":"Unsupervised domain adaptation for i-vector speaker recognition","author":"garcia-romero","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref44","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","article-title":"Nips 2016 tutorial: Generative adversarial networks","author":"goodfellow","year":"2016"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09167416.pdf?arnumber=9167416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:24Z","timestamp":1651080684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9167416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3016498","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}