{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T14:42:53Z","timestamp":1721832173872},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["309629"],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1016\/j.csl.2019.101024","type":"journal-article","created":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T23:17:10Z","timestamp":1570144630000},"page":"101024","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":8,"special_numbering":"C","title":["Voice biometrics security: Extrapolating false alarm rate via hierarchical Bayesian modeling of speaker verification scores"],"prefix":"10.1016","volume":"60","author":[{"given":"Alexey","family":"Sholokhov","sequence":"first","affiliation":[]},{"given":"Tomi","family":"Kinnunen","sequence":"additional","affiliation":[]},{"given":"Ville","family":"Vestman","sequence":"additional","affiliation":[]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2019.101024_bib0001","series-title":"Proceedings of the Odyssey 2004, The Speaker and Language Recognition Workshop","article-title":"NIST speaker recognition evaluation chronicles","author":"Alvin","year":"2004"},{"key":"10.1016\/j.csl.2019.101024_bib0002","series-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop","year":"2006"},{"issue":"2","key":"10.1016\/j.csl.2019.101024_bib0003","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.csl.2005.08.001","article-title":"Application-independent evaluation of speaker detection","volume":"20","author":"Br\u00fcmmer","year":"2006","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2019.101024_bib0004","series-title":"Proceedings of Odyssey 2018","first-page":"349","article-title":"Gaussian meta-embeddings for efficient scoring of a heavy-tailed PLDA model","author":"Br\u00fcmmer","year":"2018"},{"key":"10.1016\/j.csl.2019.101024_bib0005","series-title":"Proceedings of the Odyssey","article-title":"The speaker partitioning problem","author":"Br\u00fcmmer","year":"2010"},{"issue":"1","key":"10.1016\/j.csl.2019.101024_bib0006","first-page":"159","article-title":"Operations for learning with graphical models","volume":"2","author":"Buntine","year":"1994","journal-title":"J. Artif. Int. Res."},{"key":"10.1016\/j.csl.2019.101024_bib0007","series-title":"Proceedings of the 25th USENIX Security Symposium (USENIX Security 16). Austin, TX","article-title":"Hidden voice commands","author":"Carlini","year":"2016"},{"key":"10.1016\/j.csl.2019.101024_bib0008","series-title":"Proceedings of the INTERSPEECH","article-title":"VoxCeleb2: deep speaker recognition","author":"Chung","year":"2018"},{"issue":"4","key":"10.1016\/j.csl.2019.101024_bib0009","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"Dehak","year":"2011","journal-title":"IEEE Trans. Audio Speech & Lang. Process."},{"issue":"1","key":"10.1016\/j.csl.2019.101024_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. Royal Stat. Soc. Ser. B"},{"issue":"2\u20133","key":"10.1016\/j.csl.2019.101024_bib0011","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0167-6393(99)00080-1","article-title":"The NIST speaker recognition evaluation - overview, methodology, systems, results, perspective","volume":"31","author":"Doddington","year":"2000","journal-title":"Speech Commun."},{"key":"10.1016\/j.csl.2019.101024_bib0012","series-title":"Bayesian Data Analysis","author":"Gelman","year":"2013"},{"key":"10.1016\/j.csl.2019.101024_bib0013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2017.10.002","article-title":"Acoustical and perceptual study of voice disguise by age modification in speaker verification","volume":"95","author":"Gonz\u00e1lez Hautam\u00e4ki","year":"2017","journal-title":"Speech Commun."},{"key":"10.1016\/j.csl.2019.101024_bib0014","series-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"10.1016\/j.csl.2019.101024_sbref0015","series-title":"Proceedings of the Interspeech","first-page":"261","article-title":"Report on performance results in the NIST 2010 speaker recognition evaluation","author":"Greenberg","year":"2011"},{"issue":"4","key":"10.1016\/j.csl.2019.101024_bib0016","doi-asserted-by":"crossref","first-page":"2957","DOI":"10.1121\/1.4979337","article-title":"Analysis of human scream and its impact on text-independent speaker verification","volume":"141","author":"Hansen","year":"2017","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2019.101024_bib0017","unstructured":"ISO\/IEC 30107-1:2016, 2016. Information technology\u2013Biometric presentation attack detection \u2013 Part 1: framework. https:\/\/www.iso.org\/obp\/ui\/#iso:std:iso-iec:30107:-1:ed-1:v1:en. (Online; accessed 06 May 2019)."},{"issue":"2","key":"10.1016\/j.csl.2019.101024_bib0018","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1023\/A:1007665907178","article-title":"An introduction to variational methods for graphical models","volume":"37","author":"Jordan","year":"1999","journal-title":"Mach. Learn."},{"key":"10.1016\/j.csl.2019.101024_bib0019","unstructured":"Kenny, P., 2010. Bayesian speaker verification with heavy-tailed priors."},{"key":"10.1016\/j.csl.2019.101024_bib0020","series-title":"Proceedings of the Odyssey 2018: The Speaker and Language Recognition Workshop","first-page":"312","article-title":"t-DCF: a detection cost function for the tandem assessment of spoofing countermeasures and automatic speaker verification","author":"Kinnunen","year":"2018"},{"key":"10.1016\/j.csl.2019.101024_bib0021","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1017\/S0962492919000060","article-title":"Derivative-free optimization methods","volume":"28","author":"Larson","year":"2019","journal-title":"Acta Numer."},{"key":"10.1016\/j.csl.2019.101024_sbref0020","series-title":"Proceedings of the International Symposium on Intelligent Multimedia, Video & Speech Processing (ISIMP\u20192004)","first-page":"145","article-title":"Vulnerability of speaker verification to voice mimicking","author":"Lau","year":"2004"},{"issue":"5","key":"10.1016\/j.csl.2019.101024_bib0023","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1109\/TCYB.2015.2423271","article-title":"Entropy measurement for biometric verification systems","volume":"46","author":"Lim","year":"2016","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.csl.2019.101024_bib0024","unstructured":"Llera, A., F. Beckmann, C., 2016. Estimating an inverse gamma distribution. https:\/\/arxiv.org\/abs\/1605.01019."},{"key":"10.1016\/j.csl.2019.101024_bib0025","unstructured":"Minka, T., 2002. Estimating a gamma distribution. https:\/\/tminka.github.io\/papers\/minka-gamma.pdf."},{"key":"10.1016\/j.csl.2019.101024_bib0026","series-title":"Proceedings of the Interspeech 2017","first-page":"2616","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"Nagrani","year":"2017"},{"key":"10.1016\/j.csl.2019.101024_bib0027","series-title":"Proceedings of the IEEE ICASSP. Brisbane, Queensland, Australia","first-page":"4674","article-title":"Entropy analysis of i-vector feature spaces in duration-sensitive speaker recognition","author":"Nautsch","year":"2015"},{"key":"10.1016\/j.csl.2019.101024_bib0028","series-title":"Technical Report","article-title":"The Kaldi speech recognition toolkit","author":"Povey","year":"2011"},{"key":"10.1016\/j.csl.2019.101024_bib0029","series-title":"Proceedings of the Advances in Biometrics, International Conference, ICB 2007, Seoul, Korea, August 27\u201329, 2007","first-page":"424","article-title":"Latent identity variables: Biometric matching without explicit identity estimation","author":"Prince","year":"2007"},{"key":"10.1016\/j.csl.2019.101024_bib0030","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"4267","article-title":"On nesting Monte Carlo estimators","author":"Rainforth","year":"2018"},{"key":"10.1016\/j.csl.2019.101024_bib0031","series-title":"Proceedings of the 17th International Conference on Artificial Intelligence and Statistics, AISTATS 2014, Reykjavik, Iceland, April 22\u201325, 2014","first-page":"814","article-title":"Black box variational inference","author":"Ranganath","year":"2014"},{"issue":"3","key":"10.1016\/j.csl.2019.101024_bib0032","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1147\/sj.403.0614","article-title":"Enhancing security and privacy in biometrics-based authentication systems","volume":"40","author":"Ratha","year":"2001","journal-title":"IBM Syst. J."},{"issue":"1\u20132","key":"10.1016\/j.csl.2019.101024_bib0033","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","article-title":"Speaker identification and verification using Gaussian mixture speaker models","volume":"17","author":"Reynolds","year":"1995","journal-title":"Speech Commun."},{"issue":"3","key":"10.1016\/j.csl.2019.101024_bib0034","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","volume":"22","author":"Robbins","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.csl.2019.101024_bib0035","series-title":"Monte Carlo Statistical Methods (Springer Texts in Statistics)","author":"Robert","year":"2005"},{"key":"10.1016\/j.csl.2019.101024_bib0036","series-title":"Proceedings of the Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20\u201324, 2017","first-page":"1353","article-title":"The 2016\u202fNIST speaker recognition evaluation","author":"Sadjadi","year":"2017"},{"key":"10.1016\/j.csl.2019.101024_sbref0033","series-title":"Handbook of Biometric Anti-Spoofing: Presentation Attack Detection","article-title":"Introduction to voice presentation attack detection and recent advances","author":"Sahidullah","year":"2018"},{"key":"10.1016\/j.csl.2019.101024_bib0038","series-title":"Proceedings of the IEEE ICASSP. Calcary, Canada","first-page":"5329","article-title":"X-vectors: Robust DNN embeddings for speaker recognition","author":"Snyder","year":"2018"},{"key":"10.1016\/j.csl.2019.101024_bib0039","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.csl.2019.05.005","article-title":"Voice mimicry attacks assisted by automatic speaker verification","volume":"59","author":"Vestman","year":"2020","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"10.1016\/j.csl.2019.101024_bib0040","first-page":"1005","article-title":"Variational inference in nonconjugate models","volume":"14","author":"Wang","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.csl.2019.101024_bib0041","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/TASLP.2016.2614725","article-title":"The impact of data dependence on speaker recognition evaluation","volume":"25","author":"Wu","year":"2017","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2019.101024_bib0042","series-title":"Proceedings of the ACM Conference on Computer and Communications Security","first-page":"103","article-title":"Dolphinattack: inaudible voice commands","author":"Zhang","year":"2017"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230819302682?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230819302682?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T13:41:30Z","timestamp":1721828490000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230819302682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":42,"alternative-id":["S0885230819302682"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2019.101024","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2020,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Voice biometrics security: Extrapolating false alarm rate via hierarchical Bayesian modeling of speaker verification scores","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2019.101024","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"101024"}}