{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:34Z","timestamp":1740172414548,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"RGC of Hong Kong SAR","award":["PolyU 152518\/16E and PolyU 152068\/15E"],"award-info":[{"award-number":["PolyU 152518\/16E and PolyU 152068\/15E"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/taslp.2018.2791105","type":"journal-article","created":{"date-parts":[[2018,1,8]],"date-time":"2018-01-08T19:45:19Z","timestamp":1515440719000},"page":"700-712","source":"Crossref","is-referenced-by-count":6,"title":["DNN-Based Score Calibration With Multitask Learning for Noise Robust Speaker Verification"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2445-5240","authenticated-orcid":false,"given":"Zhili","family":"Tan","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\/0000-0001-6787-5555","authenticated-orcid":false,"given":"Brian Kan-Wing","family":"Mak","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.21236\/ADA613971"},{"key":"ref38","first-page":"1035","article-title":"Bottleneck features from SNR-adaptive denoising deep classifier for speaker identification-adaptive denoising deep classifier for speaker identification","author":"tan","year":"0","journal-title":"Proc Asia-Pac Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref33","first-page":"1619","article-title":"The distribution of calibrated likelihood-ratios in speaker recognition","author":"leeuwen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","first-page":"1","article-title":"Learning distributed representations of concepts","volume":"1","author":"hinton","year":"0","journal-title":"Proc 8th Annu Conf Cogn Sci Soc"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/TASLP.2015.2422573"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1023\/A:1007379606734"},{"key":"ref37","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"bengio","year":"2007","journal-title":"Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1162\/089976602760128018"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1016\/j.csl.2013.07.003"},{"key":"ref34","article-title":"The BOSARIS toolkit: Theory, algorithms and code for surviving the new DCF","volume":"abs 1304 2865","author":"br\u00fcmmer","year":"2013","journal-title":"CoRR"},{"year":"2005","author":"hirsch","article-title":"FaNT—Filtering and noise adding tool","key":"ref28"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICASSP.2014.6853884"},{"key":"ref29","first-page":"249","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"0","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICCV.2007.4409052"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TASL.2010.2064307"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TASL.2013.2279332"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.21437\/Odyssey.2016-52"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1016\/j.specom.2015.05.009"},{"key":"ref24","first-page":"317","article-title":"A unified approach for audio characterization and its application to speaker recognition","author":"ferrer","year":"0","journal-title":"Proc Odyssey"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TASLP.2016.2607343"},{"key":"ref26","first-page":"1976","article-title":"Likelihood-ratio calibration using prior-weighted proper scoring rules","author":"br\u00fcmmer","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref25","first-page":"14","article-title":"A comparison of linear and non-linear calibrations for speaker recognition","author":"br\u00fcmmer","year":"0","journal-title":"Proc Odyssey"},{"key":"ref50","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc ICML"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2012.6288859"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TASLP.2015.2442757"},{"key":"ref40","first-page":"55","article-title":"Source normalization for language-independent speaker recognition using i-vectors","author":"mandasari","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP.2016.7472742"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TASLP.2015.2499038"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TASLP.2017.2692304"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TASLP.2014.2341914"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/SLT.2016.7846260"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP.2013.6639154"},{"key":"ref18","first-page":"1037","article-title":"Modified-prior PLDA and score calibration for duration mismatch compensation in speaker recognition system","author":"hong","year":"0","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-319-43958-7_72"},{"key":"ref4","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TASL.2012.2226161"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ISCSLP.2016.7918462"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/BigMM.2015.46"},{"key":"ref8","first-page":"214","article-title":"Non-linear PLDA for i-vector speaker verification","author":"novoselov","year":"0","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/Odyssey.2016-31"},{"key":"ref49","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"0","journal-title":"Proc ICML"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2013.6638975"},{"key":"ref46","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref48","first-page":"111","article-title":"Performance analysis of various activation functions in generalized MLP architectures of neural networks","volume":"1","author":"karlik","year":"2011","journal-title":"Int J Artif Intell Expert Syst"},{"key":"ref47","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"0","journal-title":"Proc Conf Artif Intell Statist"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.21437\/Interspeech.2017-656"},{"key":"ref41","first-page":"1471","article-title":"Within-class covariance normalization for SVM-based speaker recognition","author":"hatch","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8271883\/08249870.pdf?arnumber=8249870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:18:20Z","timestamp":1642004300000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8249870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":50,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2791105","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}