{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:58:10Z","timestamp":1776182290690,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","funder":[{"name":"VoicePersonae"},{"DOI":"10.13039\/501100001665","name":"French Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJCR18A6"],"award-info":[{"award-number":["JPMJCR18A6"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RESPECT"},{"DOI":"10.13039\/501100001665","name":"ANR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["309629"],"award-info":[{"award-number":["309629"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Region Grand Est, France"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/tbiom.2021.3059479","type":"journal-article","created":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T21:14:37Z","timestamp":1613682877000},"page":"252-265","source":"Crossref","is-referenced-by-count":149,"title":["ASVspoof 2019: Spoofing Countermeasures for the Detection of Synthesized, Converted and Replayed Speech"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3405-4416","authenticated-orcid":false,"given":"Andreas","family":"Nautsch","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8246-0606","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Nicholas","family":"Evans","sequence":"additional","affiliation":[]},{"given":"Tomi H.","family":"Kinnunen","sequence":"additional","affiliation":[]},{"given":"Ville","family":"Vestman","sequence":"additional","affiliation":[]},{"given":"Massimiliano","family":"Todisco","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4475-2517","authenticated-orcid":false,"given":"Hector","family":"Delgado","sequence":"additional","affiliation":[]},{"given":"Md","family":"Sahidullah","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-3000","authenticated-orcid":false,"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2170"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref31","first-page":"10","article-title":"Network in network","author":"lin","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"Proc Int Soc Music Inf Retrieval Conf (ISMIR)"},{"key":"ref36","first-page":"34","article-title":"Investigation of spectral centroid magnitude and frequency for speaker recognition","author":"kua","year":"2010","journal-title":"Proc Odyssey"},{"key":"ref35","first-page":"114","article-title":"Improved closed set text-independent speaker identification by combining MFCC with evidence from flipped filter banks","volume":"4","author":"chakroborty","year":"2007","journal-title":"Int J Signal Process Syst (IJSPS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2505"},{"key":"ref60","year":"2017","journal-title":"Common Criteria for Information Technology Security Evaluation—Part 3 Security Assurance Components Common Methodology for Information Technology Security Evaluation (CEM)"},{"key":"ref62","year":"2019"},{"key":"ref61","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref2","article-title":"Spoofing and countermeasures for speaker verification: A need for standard corpora, protocols and metrics","author":"evans","year":"2013","journal-title":"Proc IEEE Signal Process Soc Speech Lang Tech Committee Newslett"},{"key":"ref1","first-page":"321","author":"sahidullah","year":"2019","journal-title":"Introduction to Voice Presentation Attack Detection and Recent Advances"},{"key":"ref20","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recognition Understanding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.011"},{"key":"ref51","article-title":"The BOSARIS toolkit user guide: Theory, algorithms and code for binary classifier score processing","author":"br\u00fcmmer","year":"2011"},{"key":"ref59","first-page":"5","article-title":"The attacker’s perspective on automatic speaker verification: An overview","author":"das","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref56","first-page":"36","article-title":"On the vulnerability of automatic speaker recognition to spoofing attacks with artificial signals","author":"alegre","year":"2012","journal-title":"Proc Eur Signal Process Conf (EUSIPCO)"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.21"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.05.005"},{"key":"ref53","first-page":"101","article-title":"Le signe de l’elevation de la voix","volume":"37","author":"lombard","year":"1911","journal-title":"Ann Mal de L’Oreille et du Larynx"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1541"},{"key":"ref10","year":"2016"},{"key":"ref11","first-page":"48","article-title":"A MATLAB simulation of ‘shoebox’ room acoustics for use in research and teaching","volume":"9","author":"campbell","year":"2005","journal-title":"Comput Inf Syst J"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref12","author":"vincent","year":"2008","journal-title":"Roomsimove"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2015.0071"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/sec.1499"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1140"},{"key":"ref18","first-page":"2087","article-title":"A comparison of features for synthetic speech detection","author":"sahidullah","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3009494"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"},{"key":"ref8","author":"oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref7","author":"veaux","year":"2017","journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit"},{"key":"ref49","first-page":"171","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref46","first-page":"1","article-title":"FLIPOUT: Efficient pseudo-independent weight perturbations on mini-batches","author":"wen","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682640"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2676"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1230"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023158"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2279"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8423754\/9385568\/09358099.pdf?arnumber=9358099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,14]],"date-time":"2021-10-14T01:43:33Z","timestamp":1634175813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9358099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2021.3059479","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}