{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:56:44Z","timestamp":1764403004666,"version":"3.37.3"},"reference-count":60,"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":[{"name":"RGC of Hong Kong SAR","award":["PolyU 152137\/17E"],"award-info":[{"award-number":["PolyU 152137\/17E"]}]},{"name":"Taiwan MOST","award":["109-2634-F-009-024"],"award-info":[{"award-number":["109-2634-F-009-024"]}]}],"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.2020.3004760","type":"journal-article","created":{"date-parts":[[2020,6,24]],"date-time":"2020-06-24T21:16:01Z","timestamp":1593033361000},"page":"2013-2024","source":"Crossref","is-referenced-by-count":33,"title":["Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9580-2414","authenticated-orcid":false,"given":"Youzhi","family":"Tu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8854-3760","authenticated-orcid":false,"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3466-8941","authenticated-orcid":false,"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref38","article-title":"Understanding disentangling in $\\beta$-VAE","author":"burgess","year":"2017","journal-title":"Proc NIPS Workshop Learn Disentangled Representations"},{"key":"ref33","first-page":"159","article-title":"Fixing a broken ELBO","author":"alemi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","article-title":"ELBO surgery: Yet another way to carve up the variational evidence lower bound","author":"hoffman","year":"0","journal-title":"Proc NIPS Workshop Adv Approx Bayesian Inference"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2486"},{"key":"ref30","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","first-page":"1214","article-title":"VAE with a VampPrior","author":"tomczak","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015885"},{"key":"ref35","article-title":"Lagging inference networks and posterior collapse in variational autoencoders","author":"he","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","first-page":"4393","article-title":"Amortized inference regularization","author":"shu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","first-page":"21","article-title":"Power comparisons of Shapiro-Wilk, Kolmogorov-Smirnov, Lilliefors and Anderson-Darling tests","volume":"2","author":"razali","year":"2011","journal-title":"Journal of Statistical Modeling and Analytics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683245"},{"key":"ref27","first-page":"249","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-48"},{"key":"ref2","first-page":"47","article-title":"Bayesian adaptation of PLDA based speaker recognition to domains with scarce development data","author":"villalba","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854362"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168121"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682064"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683616"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2128"},{"key":"ref25","article-title":"Bayesian speaker verification with heavy tailed priors","author":"kenny","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"journal-title":"Monte Carlo Strategies in Scientific Computing","year":"2008","author":"liu","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1017\/9781108552332"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/2333709"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2307\/2334448"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref55","first-page":"2649","article-title":"Disentangling by factorising","author":"kim","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","first-page":"2525","article-title":"Structured disentangled representations","author":"esmaeili","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref53","first-page":"2615","article-title":"Isolating sources of disentanglement in variational autoencoders","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","first-page":"531","article-title":"Mutual information neural estimation","author":"belghazi","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1524"},{"key":"ref40","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682852"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-49"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2866707"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682752"},{"key":"ref16","first-page":"6839","article-title":"Multi-level deep neural network adaptation for speaker verification using MMD and consistency regularization","author":"lin","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref17","first-page":"513","article-title":"A kernel method for the two-sample-problem","author":"gretton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref4","first-page":"266","article-title":"Unsupervised clustering approaches for domain adaptation in speaker recognition systems","author":"shum","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461943"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078604"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854353"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref49","article-title":"Adversarial autoencoders","author":"makhzani","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","first-page":"1017","article-title":"Dataset-invariant covariance normalization for out-domain PLDA speaker verification","author":"rahman","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref46","first-page":"10 215","article-title":"Glow: Generative flow with invertible $1 \\times 1$ convolutions","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1548"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2168"},{"key":"ref47","first-page":"2722","article-title":"Flow++: Improving flow-based generative models with variational dequantization and architecture design","author":"ho","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Towards deeper understanding of variational autoencoding models","year":"2017","author":"zhao","key":"ref42"},{"key":"ref41","first-page":"4743","article-title":"Amortized inference regularization","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"2397","article-title":"Avoiding latent variable collapse with generative skip models","author":"dieng","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref43","first-page":"2678","article-title":"Semi-amortized variational autoencoders","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09124672.pdf?arnumber=9124672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:43Z","timestamp":1651080703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9124672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3004760","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}