{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T04:54:46Z","timestamp":1725512086875},"publisher-location":"Berlin, Heidelberg","reference-count":53,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540715030"},{"type":"electronic","value":"9783540715054"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-71505-4_8","type":"book-chapter","created":{"date-parts":[[2007,5,23]],"date-time":"2007-05-23T17:29:56Z","timestamp":1179941396000},"page":"118-134","source":"Crossref","is-referenced-by-count":2,"title":["Audio-visual Identity Verification: An Introductory Overview"],"prefix":"10.1007","author":[{"given":"Bouchra","family":"Abboud","sequence":"first","affiliation":[]},{"given":"Herv\u00e9","family":"Bredin","sequence":"additional","affiliation":[]},{"given":"Guido","family":"Aversano","sequence":"additional","affiliation":[]},{"given":"G\u00e9rard","family":"Chollet","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"D.A. Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker Verification using Adapted Gaussian Mixture Models. Digital Signal Processing\u00a010, 19\u201341 (2000)","journal-title":"Digital Signal Processing"},{"issue":"1","key":"8_CR2","first-page":"1","volume":"39","author":"A. Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., Rubin, D.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J. of Royal Statistical Society\u00a039(1), 1\u201322 (1977)","journal-title":"J. of Royal Statistical Society"},{"key":"8_CR3","unstructured":"Blouet, R., Mokbel, C., Mokbel, H., Sanchez, E., Chollet, G.: BECARS: a Free Software for Speaker Verification. In: ODYSSEY 2004, pp. 145\u2013148 (2004)"},{"key":"8_CR4","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1109\/89.917680","volume":"9","author":"C. Mokbel","year":"2001","unstructured":"Mokbel, C.: Online Adaptation of HMMs to Real-Life Conditions: A Unified Framework. IEEE Transactions on Speech and Audio Processing\u00a09, 342\u2013357 (2001)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"10","key":"8_CR5","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1109\/34.254061","volume":"15","author":"R. Brunelli","year":"1993","unstructured":"Brunelli, R., Poggio, T.: Face recognition: Features versus templates. IEEE Trans. on Pattern Analysis and Machine Intelligence\u00a015(10), 1042\u20131052 (1993)","journal-title":"IEEE Trans. on Pattern Analysis and Machine Intelligence"},{"key":"8_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/3-540-63460-6_150","volume-title":"Computer Analysis of Images and Patterns","author":"L. Wiskott","year":"1997","unstructured":"Wiskott, L., Fellous, J.M., Kr\u00fcger, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. In: Sommer, G., Daniilidis, K., Pauli, J. (eds.) CAIP 1997. LNCS, vol.\u00a01296, pp. 456\u2013463. Springer, Heidelberg (1997)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Abboud, B., Davoine, F., Dang, M.: Expressive face recognition and synthesis. In: IEEE CVPR workshop on Computer Vision and Pattern Recognition for Human Computer Interaction, Madison, U.S.A. (2003)","DOI":"10.1109\/CVPRW.2003.10056"},{"issue":"1","key":"8_CR8","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","volume":"3","author":"M. Turk","year":"1991","unstructured":"Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience\u00a03(1), 71\u201386 (1991)","journal-title":"Journal of Cognitive Neuroscience"},{"key":"8_CR9","volume-title":"Face Recognition: From Theories to Applications","author":"B. Moghaddam","year":"1998","unstructured":"Moghaddam, B., Pentland, A.: Beyond euclidean eigenspaces: Bayesian matching for visual recognition. In: Face Recognition: From Theories to Applications, Springer, Berlin (1998)"},{"key":"8_CR10","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1109\/72.750575","volume":"10","author":"S. Li","year":"1999","unstructured":"Li, S., Lu, J.: Face recognition using the nearest feature line method. IEEE Transactions on Neural Networks\u00a010, 439\u2013443 (1999)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"8_CR11","volume-title":"Statistical Learning Theory","author":"V. Vapnik","year":"1998","unstructured":"Vapnik, V.: Statistical Learning Theory. Wiley, Chichester (1998)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Bartlett, M.S., Littlewort, G., Fasel, I., Movellan, J.R.: Real time face detection and facial expression recognition: Development and applications to human computer interaction. In: IEEE CVPR workshop on Computer Vision and Pattern Recognition for Human Computer Interaction, Madison, U.S.A. (2003)","DOI":"10.1109\/CVPRW.2003.10057"},{"key":"8_CR13","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/S1077-3142(03)00073-0","volume":"91","author":"B. Heisele","year":"2003","unstructured":"Heisele, B., Ho, P., Wu, J., Poggio, T.: Face recognition: Component-based versus global approaches. Computer Vision and Image Understanding\u00a091, 6\u201321 (2003)","journal-title":"Computer Vision and Image Understanding"},{"key":"8_CR14","unstructured":"Padgett, C., Cottrell, G., Adolphs, R.: Categorical perception in facial emotion classification. In: Proceedings of the Eighteenth Annual Cognitive Science Conference, San Diego, CA, pp. 249\u2013253 (1996)"},{"key":"8_CR15","unstructured":"Lien, J., Zlochower, A., Cohn, J., Li, C., Kanade, T.: Automatically recognizing facial expressions in the spatio temporal domain. In: Proceedings of the Workshop on Perceptual User Interfaces, Alberta, Canada (1997)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Bredin, H., Dehak, N., Chollet, G.: GMM-based SVM for Face Recognition. In: International Conference on Pattern Recognition (2006)","DOI":"10.1109\/ICPR.2006.611"},{"key":"8_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/3-540-44887-X_74","volume-title":"Audio-and Video-Based Biometrie Person Authentication","author":"E. Bailly-Bailli\u00e8re","year":"2003","unstructured":"Bailly-Bailli\u00e8re, E., Bengio, S., Bimbot, F., Hamouz, M., Kittler, J., Mari\u00e9thoz, J., Matas, J., Messer, K., Popovici, V., Por\u00e9e, F., Ruiz, B., Thiran, J.P.: The BANCA Database and Evaluation Protocol. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol.\u00a02688, pp. 625\u2013638. Springer, Heidelberg (2003)"},{"key":"8_CR18","unstructured":"BT-DAVID: http:\/\/eegalilee.swan.ac.uk\/"},{"key":"8_CR19","unstructured":"Messer, K., Matas, J., Kittler, J., Luettin, J., Maitre, G.: XM2VTSDB: The Extended M2VTS Database. In: Audio- and Video-Based Biometric Person Authentication, pp. 72\u201377 (1999)"},{"key":"8_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/3-540-44887-X_98","volume-title":"Audio-and Video-Based Biometrie Person Authentication","author":"S. Garcia-Salicetti","year":"2003","unstructured":"Garcia-Salicetti, S., Beumier, C., Chollet, G., Dorizzi, B., Jardins, J.L., Lunter, J., Ni, Y., Petrovska-Delacretaz, D.: BIOMET: a Multimodal Person Authentication Database including Face, Voice, Fingerprint, Hand and Signature Modalities. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol.\u00a02688, pp. 845\u2013853. Springer, Heidelberg (2003)"},{"key":"8_CR21","unstructured":"Bredin, H., Miguel, A., Witten, I.H., Chollet, G.: Detecting Replay Attacks in Audiovisual Identity Verification. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (2006)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Stylianou, Y., Capp\u00e9, O., Moulines, E.: Statistical Methods for Voice Quality Transformation. In: European Conference on Speech Communication and Technology (1995)","DOI":"10.21437\/Eurospeech.1995-121"},{"key":"8_CR23","unstructured":"Perrot, P., Aversano, G., Chollet, G., Charbit, M.: Voice Forgery Using ALISP: Indexation in a Client Memory. In: ICASSP (2005)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Romdhani, S., Vetter, T.: Efficient, robust and accurate fitting of a 3D morphable model. In: IEEE Intl. Conference on Computer Vision, Nice, France (2003)","DOI":"10.1109\/ICCV.2003.1238314"},{"issue":"6","key":"8_CR25","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/34.216726","volume":"15","author":"D. Terzopoulos","year":"1993","unstructured":"Terzopoulos, D., Waters, K.: Analysis and synthesis of facial image sequences using physical and anatomical models. IEEE Trans. on Pattern Analysis and Machine Intelligence\u00a015(6), 569\u2013579 (1993)","journal-title":"IEEE Trans. on Pattern Analysis and Machine Intelligence"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Pighin, F., Hecker, J., Lischinski, D., Szeliski, R., Salesin, D.: Synthesizing realistic facial expressions from photographs. In: Siggraph proceedings, pp. 75\u201384 (1998)","DOI":"10.1145\/280814.280825"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Ezzat, T., Geiger, G., Poggio, T.: Trainable videorealistic speech animation. In: ACM Siggraph, San Antonio, Texas (2002)","DOI":"10.1145\/566654.566594"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Bregler, C., Covel, M., Slaney, M.: Video rewrite: Driving visual speech with audio. In: Siggraph proceedings, pp. 353\u2013360 (1997)","DOI":"10.1145\/258734.258880"},{"key":"8_CR29","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1155\/S1110865702203078","volume":"6","author":"J. Ahlberg","year":"2002","unstructured":"Ahlberg, J.: An active model for facial feature tracking. EURASIP Journal on applied signal processing\u00a06, 566\u2013571 (2002)","journal-title":"EURASIP Journal on applied signal processing"},{"issue":"8","key":"8_CR30","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1016\/j.image.2004.05.009","volume":"10","author":"B. Abboud","year":"2004","unstructured":"Abboud, B., Davoine, F., Dang, M.: Facial expression recognition and synthesis based on an appearance model. Signal Processing: Image Communication\u00a010(8), 723\u2013740 (2004)","journal-title":"Signal Processing: Image Communication"},{"issue":"6","key":"8_CR31","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"T. Cootes","year":"2001","unstructured":"Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Trans. on Pattern Analysis and Machine Intelligence\u00a023(6), 681\u2013685 (2001)","journal-title":"IEEE Trans. on Pattern Analysis and Machine Intelligence"},{"key":"8_CR32","series-title":"Lecture Notes in Computer Science","volume-title":"Audio-and Video-Based Biometrie Person Authentication","author":"E. Bailly-Bailliere","year":"2003","unstructured":"Bailly-Bailliere, E., Bengio, S., Bimbot, F., Hamouz, M., Kittler, J., Mariethoz, J., Matas, J., Messer, K., Popovici, V., Pore, F., Ruiz, B., Thiran, J.P.: The BANCA database and evaluation protocol. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol.\u00a02688, Springer, Heidelberg (2003)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Bredin, H., Chollet, G.: Measuring Audio and Visual Speech Synchrony: Methods and Applications. In: International Conference on Visual Information Engineering (2006)","DOI":"10.1049\/cp:20060538"},{"key":"8_CR34","volume-title":"Issues in Visual and Audio-Visual Speech Processing","author":"G. Potamianos","year":"2004","unstructured":"Potamianos, G., Neti, C., Luettin, J., Matthews, I.: Audio-Visual Automatic Speech Recognition: An Overview. In: Issues in Visual and Audio-Visual Speech Processing, MIT Press, Cambridge (2004)"},{"key":"8_CR35","unstructured":"Hershey, J., Movellan, J.: Audio-Vision: Using Audio-Visual Synchrony to Locate Sounds. In: Neural Information Processing Systems (1999)"},{"issue":"3","key":"8_CR36","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1109\/TMM.2004.827503","volume":"6","author":"J.W. Fisher","year":"2004","unstructured":"Fisher, J.W., Darell, T.: Speaker Association With Signal-Level Audiovisual Fusion. IEEE Transactions on Multimedia\u00a06(3), 406\u2013413 (2004)","journal-title":"IEEE Transactions on Multimedia"},{"key":"8_CR37","unstructured":"Slaney, M., Covell, M.: FaceSync: A Linear Operator for Measuring Synchronization of Video Facial Images and Audio Tracks. Neural Information Processing Society 13 (2000)"},{"key":"8_CR38","unstructured":"Cutler, R., Davis, L.: Look Who\u2019s Talking: Speaker Detection using Video and Audio Correlation. In: International Conference on Multimedia and Expo, pp. 1589\u20131592 (2000)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Nock, H., Iyengar, G., Neti, C.: Assessing Face and Speech Consistency for Monologue Detection in Video. In: Multimedia\u201902, pp. 303\u2013306 (2002)","DOI":"10.1145\/641043.641070"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Iyengar, G., Nock, H., Neti, C.: Audio-Visual Synchrony for Detection of Monologues in Video Archives. In: International Conference on Acoustics, Speech, and Signal Processing, pp. 329\u2013332 (2003)","DOI":"10.1109\/ICME.2003.1220921"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Chetty, G., Wagner, M.: \u201cLiveness\u201d Verification in Audio-Video Authentication. In: Australian International Conference on Speech Science and Technology, pp. 358\u2013363 (2004)","DOI":"10.21437\/Interspeech.2004-429"},{"issue":"2","key":"8_CR42","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/0167-6393(86)90008-7","volume":"5","author":"N. Sugamura","year":"1986","unstructured":"Sugamura, N., Itakura, F.: Speech Analysis and Synthesis Methods developed at ECL in NTT\u2013From LPC to LSP. Speech Communications\u00a05(2), 199\u2013215 (1986)","journal-title":"Speech Communications"},{"key":"8_CR43","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0167-6393(98)00048-X","volume":"28","author":"H. Yehia","year":"1998","unstructured":"Yehia, H., Rubin, P., Vatikiotis-Bateson, E.: Quantitative Association of Vocal-Tract and Facial Behavior. Speech Communication\u00a028, 23\u201343 (1998)","journal-title":"Speech Communication"},{"key":"8_CR44","unstructured":"Bregler, C., Konig, Y.: \u201cEigenlips\u201d for Robust Speech Recognition. In: International Conference on Acoustics, Speech, and Signal Processing, vol.\u00a02, pp. 19\u201322 (1994)"},{"key":"8_CR45","unstructured":"Goecke, R., Millar, B.: Statistical Analysis of the Relationship between Audio and Video Speech Parameters for Australian English. In: International Conference on Audio-Visual Speech Processing (2003)"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Eveno, N., Besacier, L.: Co-Inertia Analysis for \u201dLiveness\u201d Test in Audio-Visual Biometrics. In: International Symposium on Image and Signal Processing Analysis, pp. 257\u2013261 (2005)","DOI":"10.1109\/ISPA.2005.195419"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Eveno, N., Besacier, L.: A Speaker Independent Liveness Test for Audio-Video Biometrics. In: 9th European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-661"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Chibelushi, C.C., Mason, J.S., Deravi, F.: Integrated Person Identification Using Voice and Facial Features. In: IEE Colloquium on Image Processing for Security Applications, vol.\u00a04, pp. 1\u20135 (1997)","DOI":"10.1049\/ic:19970380"},{"key":"8_CR49","unstructured":"Smaragdis, P., Casey, M.: Audio\/Visual Independent Components. In: International Symposium on Independent Component Analysis and Blind Signal Separation, pp. 709\u2013714 (2003)"},{"key":"8_CR50","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1111\/j.1365-2427.1994.tb01741.x","volume":"31","author":"S. Dol\u00e9dec","year":"1994","unstructured":"Dol\u00e9dec, S., Chessel, D.: Co-Inertia Analysis: an Alternative Method for Studying Species-Environment Relationships. Freshwater Biology\u00a031, 277\u2013294 (1994)","journal-title":"Freshwater Biology"},{"key":"8_CR51","unstructured":"Fisher, J.W., Darrell, T., Freeman, W.T., Viola, P.: Learning Joint Statistical Models for Audio-Visual Fusion and Segregation. In: Advances in Neural Information Processing Systems (2001)"},{"issue":"2","key":"8_CR52","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L.R. Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE\u00a077(2), 257\u2013286 (1989)","journal-title":"Proceedings of the IEEE"},{"key":"8_CR53","unstructured":"Bengio, S.: An Asynchronous Hidden Markov Model for Audio-Visual Speech Recognition. In: Advances in Neural Information Processing Systems (2003)"}],"container-title":["Lecture Notes in Computer Science","Progress in Nonlinear Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-71505-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T19:30:14Z","timestamp":1683833414000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-71505-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540715030","9783540715054"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-71505-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}