{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T08:35:03Z","timestamp":1792917303702,"version":"4.5.0"},"reference-count":147,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Department of Information Security and Communication Technology, NTNU, Gj\u00f8vik and Advanced Technology Development Centre, Indian Institute of Technology, Kharagpur, India","id":[{"id":"https:\/\/ror.org\/03w5sq511","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3063031","type":"journal-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T16:52:41Z","timestamp":1614617561000},"page":"37431-37455","source":"Crossref","is-referenced-by-count":40,"title":["Audio-Visual Biometric Recognition and Presentation Attack Detection: A Comprehensive Survey"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2760-2832","authenticated-orcid":false,"given":"Hareesh","family":"Mandalapu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aravinda","family":"Reddy P N","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0484-3956","authenticated-orcid":false,"given":"Raghavendra","family":"Ramachandra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krothapalli Sreenivasa","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pabitra","family":"Mitra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. R. Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9159-2923","authenticated-orcid":false,"given":"Christoph","family":"Busch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multi-modal person verification tools using speech and images","author":"Acheroy","year":"1996","journal-title":"Multimedia Appl., Services Techn., ECMAST"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA.2013.6566630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2015.7358754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2615524"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSPA.2013.6487281"},{"key":"ref7","volume-title":"An Audio-Visual Person Identification and Verification System Using FAPs as Visual Features","author":"Aleksic","year":"2003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.886017"},{"key":"ref9","first-page":"1","article-title":"Secure computation of hidden Markov models","volume-title":"Proc. Int. Conf. Secur. Cryptogr. (SECRYPT)","author":"Aliasgari"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396517"},{"key":"ref11","article-title":"Automatic quality assessment for audio-visual verification systems. The LOVe submission to NIST SRE challenge 2019","author":"Antipov","year":"2020","journal-title":"arXiv:2008.05889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44887-X_74"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11590323_39"},{"key":"ref14","article-title":"Multi-modal data fusion for person authentication using SVM","author":"Ben-Yacoub","year":"1998"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/72.788647"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44887-X_89"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/iet-bmt.2014.0031"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00013-E"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2848-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-29451-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517954"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.464560"},{"key":"ref24","first-page":"96","article-title":"A blueprint for a comprehensive Australian english auditory-visual speech corpus","volume-title":"Proc. HCSNet Workshop Designing Austral. Nat. Corpus","author":"Burnham"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-309"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5230-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221235"},{"key":"ref28","first-page":"2255","article-title":"Biometric liveness detection based on cross modal fusion","volume-title":"Proc. 12th Int. Conf. Inf. Fusion","author":"Chetty"},{"key":"ref29","article-title":"Liveness verification in audio-video speaker authentication","volume-title":"Proc. 10th ASSTA Conf.","author":"Chetty"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/BCC.2006.4341615"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19970414"},{"key":"ref32","article-title":"Bt david database-internal report","author":"Chibelushi","year":"1996"},{"key":"ref33","volume-title":"Voice and Facial Image Integration for Person Recognition","author":"Chibelushi","year":"1994"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77347-4_2"},{"key":"ref35","first-page":"176","article-title":"Multimodal person recognition using unconstrained audio and video","volume-title":"Proc. Int. Conf. Audio-Video-Based Person Authentication","author":"Choudhury"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2877690"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref39","volume-title":"Audio-Visual Person Recognition for Security and Access Control","author":"Deravi","year":"1999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0016009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(97)00071-8"},{"key":"ref42","volume-title":"Easy PASS-Grenzkontrolle Einfach Und Schnell","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03168-7_14"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2005.195419"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.826754"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2007.02.017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44887-X_86"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/11527923_81"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/2.820041"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1520-684X(19980615)29:6<49::AID-SCJ5>3.0.CO;2-L"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00947"},{"key":"ref53","first-page":"174","article-title":"Multimodal biometrics via discriminant correlation analysis on mobile devices","volume-title":"Proc. Int. Conf. Secur. Manage. (SAM)","author":"Gofman"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2818990"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.8009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.7836"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334395"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-183"},{"key":"ref59","first-page":"113","article-title":"Multi-modal face and speaker identification on a handheld device","volume-title":"Proc. Workshop Multimodal User Authentication","author":"Hazen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.55"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/RATFG.1999.799230"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806293"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICIG.2004.97"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/737814"},{"key":"ref66","volume-title":"Information Technology\u2014Biometric Performance Testing and Reporting\u2014Part 4: Testing Methodologies for Technology and Scenario Evaluation. International Organization for Standardization and International Electrotechnical Committee","year":"2008"},{"key":"ref67","volume-title":"Information Technology\u2014Biometric Sample Quality - Part 1: Framework. International Organization for Standardization","year":"2009"},{"key":"ref68","year":"2016","journal-title":"Information Technology\u2014Biometric Presentation Attack Detection\u2014Part 1: Framework. International Organization for Standardization"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2050476"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-459"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/746481"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.10.001"},{"key":"ref74","article-title":"On the improvements of UNI-modal and bi-modal fusions of speaker and face recognition for mobile biometrics","author":"Khoury","year":"2013"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0016012"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09767-8"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-424"},{"key":"ref78","author":"Li","year":"2013","journal-title":"Identity Authentication Based on Audio Visual Biometrics: A Survey"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035365"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.1999.793814"},{"key":"ref81","first-page":"68","article-title":"An Italian database of emotional speech and facial expressions","volume-title":"Proc. Workshop Programme Corpora Res. Emotion Affect Tuesday 23rd May 2006","author":"Mana"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71711-7_18"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71711-7_15"},{"key":"ref84","article-title":"Mobio database for the ICPR 2010 face and speech competition","author":"McCool","year":"2009"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2012.116"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19951069"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3121138.3121165"},{"key":"ref88","first-page":"965","article-title":"XM2VTSDB: The extended M2VTS database","volume-title":"Proc. 2nd Int. Conf. Audio Video-Based","volume":"964","author":"Messer"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvlc.2009.01.008"},{"key":"ref90","first-page":"1100","article-title":"Bi-modal authentication in mobile environments using session variability modelling","volume-title":"Proc. 21st Int. Conf. Pattern Recognit. (ICPR)","author":"Motlicek"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325907"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ATSIP.2018.8364513"},{"key":"ref93","article-title":"Homomorphic encryption for speaker recognition: Protection of biometric templates and vendor model parameters","author":"Nautsch","year":"2018","journal-title":"arXiv:1803.03559"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44887-X_88"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.76"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2010.39"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2434151"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288262"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-42"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/34.879790"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-748-8"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0016021"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0016021"},{"key":"ref104","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understand.","author":"Povey"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900099"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref107","article-title":"Fundamentals of speech recognition","volume-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3038924"},{"key":"ref109","article-title":"Smartphone multi-modal biometric authentication: Database and evaluation","author":"Ramachandra","year":"2019","journal-title":"arXiv:1912.02487"},{"key":"ref110","volume-title":"RESPECT","year":"2019"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7285017"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/11752790_2"},{"key":"ref113","first-page":"1221","article-title":"Multimodal biometrics: An overview","volume-title":"Proc. 12th Eur. Signal Process. Conf.","author":"Ross"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-008-0121-2"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14423-3_16"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-37"},{"key":"ref117","article-title":"The vidtimit database","author":"Sanderson","year":"2002"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(03)00070-9"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2004.05.001"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1550194"},{"key":"ref122","first-page":"133","article-title":"Mobbio: A multimodal database captured with a portable handheld device","volume-title":"Proc. Int. Conf. Comput. Vis. Theory Appl. (VISAPP)","volume":"3","author":"Sequeira"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2009.78"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICICISYS.2010.5658534"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ISPACS.2012.6473450"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref127","volume-title":"SPEECHPRO","year":"2019"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2042645"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.09.003"},{"key":"ref130","article-title":"ASVspoof 2019: Future horizons in spoofed and fake audio detection","author":"Todisco","year":"2019","journal-title":"arXiv:1904.05441"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.09.004"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2012.54"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/79.911195"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2007.4380058"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2007.05.003"},{"key":"ref137","first-page":"166","article-title":"The big Australian speech corpus (the big ASC)","volume-title":"Proc. SST 13th Australas. Int. Conf. Speech Sci. Technol.","author":"Wagner"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB.2011.6117599"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.757487"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859322"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.8034"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2008.49"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICCEA.2010.196"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICSSE.2012.6257171"},{"key":"ref145","first-page":"31","article-title":"Multi-view semi-supervised discriminant analysis: A new approach to audio-visual person recognition","volume-title":"Proc. 20th Eur. Signal Process. Conf. (EUSIPCO)","author":"Zhao"},{"key":"ref146","article-title":"Features extraction using a Gabor filter family","volume-title":"Proc. 6th Lasted Int. Conf., Signal Image Process.","author":"Zheng"},{"key":"ref147","first-page":"973","article-title":"Liveness detection using time drift between lip movement and voice","volume-title":"Proc. Int. Conf. Mach. Learn. Cybern.","author":"Zhu"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09366483.pdf?arnumber=9366483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T07:38:35Z","timestamp":1792913915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9366483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":147,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3063031","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}