@inproceedings{bb241600,
        AUTHOR = "Alamri, H. and Cartillier, V. and Das, A. and Wang, J. and Cherian, A. and Essa, I. and Batra, D. and Marks, T.K. and Hori, C. and Anderson, P. and Lee, S. and Parikh, D.",
        TITLE = "Audio Visual Scene-Aware Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "7550-7559",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236510"}

@inproceedings{bb241601,
        AUTHOR = "Niu, Y.L. and Zhang, H.W. and Zhang, M.L. and Zhang, J.H. and Lu, Z.W. and Wen, J.R.",
        TITLE = "Recursive Visual Attention in Visual Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6672-6681",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236511"}

@inproceedings{bb241602,
        AUTHOR = "Schwartz, I. and Schwing, A.G. and Hazan, T.",
        TITLE = "A Simple Baseline for Audio-Visual Scene-Aware Dialog",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12540-12550",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236512"}

@inproceedings{bb241603,
        AUTHOR = "Lu, Y. and Lee, H. and Tseng, H. and Yang, M.",
        TITLE = "Self-Supervised Audio Spatialization with Correspondence Classifier",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3347-3351",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236513"}

@inproceedings{bb241604,
        AUTHOR = "Saidi, I. and Zhang, L. and Barriac, V. and Deforges, O.",
        TITLE = "Laboratory and Crowdsourcing Studies of Lip Sync Effect on the
Audio-Video Quality Assessment for Videoconferencing Application",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3207-3211",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236514"}

@inproceedings{bb241605,
        AUTHOR = "Meng, D. and Peng, X. and Wang, K. and Qiao, Y.",
        TITLE = "Frame Attention Networks for Facial Expression Recognition in Videos",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "3866-3870",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236515"}

@inproceedings{bb241606,
        AUTHOR = "Shahid, M. and Beyan, C. and Murino, V.",
        TITLE = "Comparisons of Visual Activity Primitives for Voice Activity Detection",
        BOOKTITLE = CIAP19,
        YEAR = "2019",
        PAGES = "I:48-59",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236516"}

@inproceedings{bb241607,
        AUTHOR = "Kim, C.I. and Shin, H.J.V. and Oh, T.H. and Kaspar, A. and Elgharib, M. and Matusik, W.",
        TITLE = "On Learning Associations of Faces and Voices",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "V:276-292",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236517"}

@inproceedings{bb241608,
        AUTHOR = "Schindler, A. and Boyer, M. and Lindley, A. and Schreiber, D. and Philipp, T.",
        TITLE = "Large Scale Audio-Visual Video Analytics Platform for Forensic
Investigations of Terroristic Attacks",
        BOOKTITLE = "MMMod19",
        YEAR = "2019",
        PAGES = "II:106-119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236518"}

@inproceedings{bb241609,
        AUTHOR = "Oliveira, D.A.B. and Mattos, A.B. and da Silva Morais, E.",
        TITLE = "Improving Viseme Recognition Using GAN-Based Frontal View Mapping",
        BOOKTITLE = AMFG18,
        YEAR = "2018",
        PAGES = "2229-22297",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236519"}

@inproceedings{bb241610,
        AUTHOR = "Yang, X. and Molchanov, P. and Kautz, J.",
        TITLE = "Making Convolutional Networks Recurrent for Visual Sequence Learning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6469-6478",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236520"}

@inproceedings{bb241611,
        AUTHOR = "Zhang, J. and Richmond, K. and Fisher, R.B.",
        TITLE = "Dual-modality Talking-metrics: 3D Visual-Audio Integrated
Behaviometric Cues from Speakers",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3144-3149",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236521"}

@inproceedings{bb241612,
        AUTHOR = "Chowdhury, A. and Atoum, Y. and Tran, L. and Liu, X. and Ross, A.",
        TITLE = "MSU-AVIS dataset: Fusing Face and Voice Modalities for Biometric
Recognition in Indoor Surveillance Videos",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3567-3573",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236522"}

@inproceedings{bb241613,
        AUTHOR = "Nagrani, A. and Albanie, S. and Zisserman, A.",
        TITLE = "Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "8427-8436",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236523"}

@inproceedings{bb241614,
        AUTHOR = "Saitoh, T. and Kubokawa, M.",
        TITLE = "SSSD: Speech Scene database by Smart Device for Visual Speech
Recognition",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3228-3232",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236524"}

@inproceedings{bb241615,
        AUTHOR = "Owens, A. and Efros, A.A.",
        TITLE = "Audio-Visual Scene Analysis with Self-Supervised Multisensory Features",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VI: 639-658",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236525"}

@inproceedings{bb241616,
        AUTHOR = "Berlin, A.A. and Surati, R.",
        TITLE = "Video Deconfounding: Hearing-Aid Inspired Video Enhancement",
        BOOKTITLE = IVMSP18,
        YEAR = "2018",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236526"}

@inproceedings{bb241617,
        AUTHOR = "Ding, R. and Pang, C. and Liu, H.",
        TITLE = "Audio-Visual Keyword Spotting Based on Multidimensional Convolutional
Neural Network",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "4138-4142",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236527"}

@inproceedings{bb241618,
        AUTHOR = "Liao, J. and Wang, S. and Zhang, X. and Liu, G.",
        TITLE = "3D Convolutional Neural Networks Based Speaker Identification and
Authentication",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "2042-2046",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236528"}

@inproceedings{bb241619,
        AUTHOR = "Savran, A. and Tavarone, R. and Higy, B. and Badino, L. and Bartolozzi, C.",
        TITLE = "Energy and Computation Efficient Audio-Visual Voice Activity
Detection Driven by Event-Cameras",
        BOOKTITLE = FG18,
        YEAR = "2018",
        PAGES = "333-340",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236529"}

@inproceedings{bb241620,
        AUTHOR = "Ephrat, A. and Halperin, T. and Peleg, S.",
        TITLE = "Improved Speech Reconstruction from Silent Video",
        BOOKTITLE = CVAVM17,
        YEAR = "2017",
        PAGES = "455-462",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236530"}

@inproceedings{bb241621,
        AUTHOR = "Ahn, J. and Kim, Y.J. and Kim, D.J.",
        TITLE = "Patch-based visual microphone for improving quality of sound",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "3927-3932",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236531"}

@inproceedings{bb241622,
        AUTHOR = "Chung, J.S. and Zisserman, A.",
        TITLE = "Out of Time: Automated Lip Sync in the Wild",
        BOOKTITLE = LipRead16,
        YEAR = "2016",
        PAGES = "II: 251-263",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236532"}

@inproceedings{bb241623,
        AUTHOR = "Miao, C.L. and Feng, J.W. and Ding, Y. and Yang, Y. and Chen, X.G. and Ji, X.Y.",
        TITLE = "Unsupervised person clustering in videos with cross-modal
communication",
        BOOKTITLE = VCIP16,
        YEAR = "2016",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236533"}

@inproceedings{bb241624,
        AUTHOR = "Hu, D. and Li, X.L. and Lu, X.Q.",
        TITLE = "Temporal Multimodal Learning in Audiovisual Speech Recognition",
        BOOKTITLE = CVPR16,
        YEAR = "2016",
        PAGES = "3574-3582",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236534"}

@inproceedings{bb241625,
        AUTHOR = "Liu, H. and Fan, T. and Wu, P.P.",
        TITLE = "Audio-visual Keyword Spotting for Mandarin Based on Discriminative
Local Spatial-Temporal Descriptors",
        BOOKTITLE = ICPR14,
        YEAR = "2014",
        PAGES = "785-790",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236535"}

@inproceedings{bb241626,
        AUTHOR = "Ringeval, F. and Sonderegger, A. and Sauer, J. and Lalanne, D.",
        TITLE = "Introducing the RECOLA multimodal corpus of remote collaborative and
affective interactions",
        BOOKTITLE = FG13,
        YEAR = "2013",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236536"}

@inproceedings{bb241627,
        AUTHOR = "Aubrey, A.J. and Cunningham, D.W. and Marshall, D. and Rosin, P.L. and Shin, A.",
        TITLE = "The Face Speaks:
Contextual and Temporal Sensitivity to Backchannel Responses",
        BOOKTITLE = FaceCVHum12,
        YEAR = "2012",
        PAGES = "II:248-259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236537"}

@inproceedings{bb241628,
        AUTHOR = "Tawari, A. and Trivedi, M.",
        TITLE = "Audio-visual data association for face expression analysis",
        BOOKTITLE = ICPR12,
        YEAR = "2012",
        PAGES = "1120-1123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236538"}

@inproceedings{bb241629,
        AUTHOR = "Taj, M. and Cavallaro, A.",
        TITLE = "Interaction recognition in wide areas using audiovisual sensors",
        BOOKTITLE = ICIP12,
        YEAR = "2012",
        PAGES = "1113-1116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236539"}

@inproceedings{bb241630,
        AUTHOR = "Giorgolo, G.",
        TITLE = "Integration of Gesture and Verbal Language: A Formal Semantics Approach",
        BOOKTITLE = GW11,
        YEAR = "2011",
        PAGES = "216-227",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236540"}

@inproceedings{bb241631,
        AUTHOR = "Le, Q.A. and Pelachaud, C.",
        TITLE = "Generating Co-speech Gestures for the Humanoid Robot NAO through BML",
        BOOKTITLE = GW11,
        YEAR = "2011",
        PAGES = "228-237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236541"}

@inproceedings{bb241632,
        AUTHOR = "Navarathna, R. and Dean, D. and Sridharan, S. and Fookes, C. and Lucey, P.",
        TITLE = "Visual Voice Activity Detection Using Frontal versus Profile Views",
        BOOKTITLE = DICTA11,
        YEAR = "2011",
        PAGES = "134-139",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236542"}

@inproceedings{bb241633,
        AUTHOR = "Komai, Y. and Ariki, Y. and Takiguchi, T.",
        TITLE = "Audio-Visual Speech Recognition Based on AAM Parameter and Phoneme
Analysis of Visual Feature",
        BOOKTITLE = PSIVT11,
        YEAR = "2011",
        PAGES = "I: 97-108",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236543"}

@inproceedings{bb241634,
        AUTHOR = "Zheng, H.M. and Wang, M. and Li, Z.",
        TITLE = "Audio-visual speaker identification with multi-view distance metric
learning",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "4561-4564",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236544"}

@inproceedings{bb241635,
        AUTHOR = "Krishnan, R.K. and Sarkar, S.",
        TITLE = "Similarity Measure between Two Gestures Using Triplets",
        BOOKTITLE = HAU3D13,
        YEAR = "2013",
        PAGES = "506-513",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236545"}

@inproceedings{bb241636,
        AUTHOR = "Krishnan, R.K. and Sarkar, S.",
        TITLE = "Detecting Group Turn Patterns in Conversations Using Audio-Video Change
Scale-Space",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "137-140",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236546"}

@inproceedings{bb241637,
        AUTHOR = "Aran, O. and Gatica Perez, D.",
        TITLE = "Fusing Audio-Visual Nonverbal Cues to Detect Dominant People in Group
Conversations",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "3687-3690",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236547"}

@inproceedings{bb241638,
        AUTHOR = "Niese, R. and Al Hamadi, A. and Michaelis, B.",
        TITLE = "A New Multi-camera Based Facial Expression Analysis Concept",
        BOOKTITLE = ICIAR12,
        YEAR = "2012",
        PAGES = "II: 64-71",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236548"}

@inproceedings{bb241639,
        AUTHOR = "Steer, M.A. and Al Hamadi, A. and Michaelis, B.",
        TITLE = "Audio-Visual Data Fusion Using a Particle Filter in the Application of
Face Recognition",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4392-4395",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236549"}

@inproceedings{bb241640,
        AUTHOR = "Roy, A. and Marcel, S.",
        TITLE = "Crossmodal Matching of Speakers Using Lip and Voice Features in
Temporally Non-overlapping Audio and Video Streams",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4504-4507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236550"}

@inproceedings{bb241641,
        AUTHOR = "Cour, T. and Sapp, B. and Nagle, A. and Taskar, B.",
        TITLE = "Talking pictures:
Temporal grouping and dialog-supervised person recognition",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "1014-1021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236551"}

@inproceedings{bb241642,
        AUTHOR = "Wu, G.Y. and Zhu, J. and Xu, H.H.",
        TITLE = "A hybrid visual feature extraction method for audio-visual speech
recognition",
        BOOKTITLE = ICIP09,
        YEAR = "2009",
        PAGES = "1829-1832",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236552"}

@inproceedings{bb241643,
        AUTHOR = "Ceballos, A. and Gomez, J. and Prieto, F. and Redarce, T.",
        TITLE = "Robot Command Interface Using an Audio-Visual Speech Recognition System",
        BOOKTITLE = CIARP09,
        YEAR = "2009",
        PAGES = "869-876",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236553"}

@inproceedings{bb241644,
        AUTHOR = "Cifani, S. and Abel, A. and Hussain, A. and Squartini, S. and Piazza, F.",
        TITLE = "An Investigation into Audiovisual Speech Correlation in Reverberant
Noisy Environments",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "331-343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236554"}

@inproceedings{bb241645,
        AUTHOR = "Fanelli, G. and Gall, J. and Van Gool, L.J.",
        TITLE = "Hough transform-based mouth localization for audio-visual speech
recognition",
        BOOKTITLE = BMVC09,
        YEAR = "2009",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236555"}

@inproceedings{bb241646,
        AUTHOR = "Cadavid, S. and Abdel Mottaleb, M. and Messinger, D.S. and Mahoor, M.H. and Bahrick, L.E.",
        TITLE = "Detecting local audio-visual synchrony in monologues utilizing vocal
pitch and facial landmark trajectories",
        BOOKTITLE = BMVC09,
        YEAR = "2009",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236556"}

@inproceedings{bb241647,
        AUTHOR = "Lee, J.S. and Ebrahimi, T.",
        TITLE = "Two-Level Bimodal Association for Audio-Visual Speech Recognition",
        BOOKTITLE = ACIVS09,
        YEAR = "2009",
        PAGES = "133-144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236557"}

@inproceedings{bb241648,
        AUTHOR = "Marchegiani, M.L. and Pirri, F. and Pizzoli, M.",
        TITLE = "Multimodal Speaker Recognition in a Conversation Scenario",
        BOOKTITLE = CVS09,
        YEAR = "2009",
        PAGES = "11-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236558"}

@inproceedings{bb241649,
        AUTHOR = "Kumar, K. and Navratil, J. and Marcheret, E. and Libal, V. and Ramaswamy, G. and Potamianos, G.",
        TITLE = "Audio-visual speech synchronization detection using a bimodal linear
prediction model",
        BOOKTITLE = Biometrics09,
        YEAR = "2009",
        PAGES = "53-59",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236559"}

@inproceedings{bb241650,
        AUTHOR = "Karam, W. and Mokbel, C. and Greige, H. and Chollet, G.",
        TITLE = "Audio-Visual Identity Verification and Robustness to Imposture",
        BOOKTITLE = ICB09,
        YEAR = "2009",
        PAGES = "796-805",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236560"}

@inproceedings{bb241651,
        AUTHOR = "Rebillat, M. and Katz, B.F.G. and Corteel, E.",
        TITLE = "SMART-I2: Spatial Multi-user Audio-visual Real-time interactive
interface, A broadcast application context",
        BOOKTITLE = "3DTV09",
        YEAR = "2009",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236561"}

@inproceedings{bb241652,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = CSAIL,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236562"}

@inproceedings{bb241653,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = Ph.D.,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236562"}

@inproceedings{bb241654,
        AUTHOR = "Das, A. and Manyam, O.K. and Tapaswi, M.",
        TITLE = "Audio-Visual Person Authentication with Multiple Visualized-Speech
Features and Multiple Face Profiles",
        BOOKTITLE = ICCVGIP08,
        YEAR = "2008",
        PAGES = "39-46",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236563"}

@inproceedings{bb241655,
        AUTHOR = "Cao, Y. and Baang, S. and Liu, S.H. and Li, M. and Hu, S.Q.",
        TITLE = "Audio-visual event classification via spatial-temporal-audio words",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236564"}

@inproceedings{bb241656,
        AUTHOR = "Terry, L.H. and Shiell, D.J. and Katsaggelos, A.K.",
        TITLE = "Feature space video stream consistency estimation for dynamic stream
weighting in audio-visual speech recognition",
        BOOKTITLE = ICIP08,
        YEAR = "2008",
        PAGES = "1316-1319",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236565"}

@inproceedings{bb241657,
        AUTHOR = "Naseem, I. and Mian, A.S.",
        TITLE = "User Verification by Combining Speech and Face Biometrics in Video",
        BOOKTITLE = ISVC08,
        YEAR = "2008",
        PAGES = "II: 482-492",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236566"}

@inproceedings{bb241658,
        AUTHOR = "Ettinger, E. and Freund, Y.",
        TITLE = "Coordinate-free calibration of an acoustically driven camera pointing
system",
        BOOKTITLE = ICDSC08,
        YEAR = "2008",
        PAGES = "1-9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236567"}

@inproceedings{bb241659,
        AUTHOR = "Hung, H. and Friedland, G.",
        TITLE = "Towards Audio-Visual On-line Diarization Of Participants In Group
Meetings",
        BOOKTITLE = M2SFA208,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236568"}

@inproceedings{bb241660,
        AUTHOR = "Liu, Y.Y. and Sato, Y.",
        TITLE = "Finding Speaker Face Region by Audiovisual Correlation",
        BOOKTITLE = M2SFA208,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236569"}

@inproceedings{bb241661,
        AUTHOR = "Kelly, D. and Pitie, F. and Kokaram, A. and Boland, F.",
        TITLE = "A Comparative Error Analysis of Audio-Visual Source Localization",
        BOOKTITLE = M2SFA208,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236570"}

@inproceedings{bb241662,
        AUTHOR = "Pachoud, S. and Gong, S. and Cavallaro, A.",
        TITLE = "Video Augmentation for Improving Audio Speech Recognition under Noise",
        BOOKTITLE = BMVC08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236571"}

@inproceedings{bb241663,
        AUTHOR = "Horii, Y. and Kawashima, H. and Matsuyama, T.",
        TITLE = "Speaker detection using the timing structure of lip motion and sound",
        BOOKTITLE = CVPR4HB08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236572"}

@inproceedings{bb241664,
        AUTHOR = "Rua, E.A. and Castro, J.L.A. and Mateo, C.G.",
        TITLE = "Quality-Based Score Normalization for Audiovisual Person Authentication",
        BOOKTITLE = ICIAR08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236573"}

@inproceedings{bb241665,
        AUTHOR = "Wang, L. and Tjondrongoro, D. and Liu, Y.",
        TITLE = "Clustering and Visualizing Audio-Visual Dataset on Mobile Devices in a
Topic-Oriented Manner",
        BOOKTITLE = Visual07,
        YEAR = "2007",
        PAGES = "310-321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236574"}

@inproceedings{bb241666,
        AUTHOR = "Zajdel, W. and Krijnders, J.D. and Andringa, T. and Gavrila, D.M.",
        TITLE = "CASSANDRA: audio-video sensor fusion for aggression detection",
        BOOKTITLE = AVSBS07,
        YEAR = "2007",
        PAGES = "200-205",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236575"}

@inproceedings{bb241667,
        AUTHOR = "Stodle, D. and Bjorndalen, J.M. and Anshus, O.J.",
        TITLE = "A System for Hybrid Vision- and Sound-Based Interaction with Distal and
Proximal Targets on Wall-Sized, High-Resolution Tiled Displays",
        BOOKTITLE = CVHCI07,
        YEAR = "2007",
        PAGES = "59-68",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236576"}

@inproceedings{bb241668,
        AUTHOR = "van Hengel, P.W.J. and Andringa, T.C.",
        TITLE = "Verbal aggression detection in complex social environments",
        BOOKTITLE = AVSBS07,
        YEAR = "2007",
        PAGES = "15-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236577"}

@inproceedings{bb241669,
        AUTHOR = "Ikeda, O.",
        TITLE = "Detection of a Speaker in Video by Combined Analysis of Speech Sound
and Mouth Movement",
        BOOKTITLE = ISVC07,
        YEAR = "2007",
        PAGES = "II: 602-610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236578"}

@inproceedings{bb241670,
        AUTHOR = "Das, A.",
        TITLE = "Audio Visual Person Authentication by Multiple Nearest Neighbor
Classifiers",
        BOOKTITLE = ICB07,
        YEAR = "2007",
        PAGES = "1114-1123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236579"}

@inproceedings{bb241671,
        AUTHOR = "Xin, L. and Tao, J.H. and Tan, T.N.",
        TITLE = "Dynamic Audio-Visual Mapping using Fused Hidden Markov Model Inversion
Method",
        BOOKTITLE = ICIP07,
        YEAR = "2007",
        PAGES = "III: 293-296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236580"}

@inproceedings{bb241672,
        AUTHOR = "Barzelay, Z. and Schechner, Y.Y.",
        TITLE = "Harmony in Motion",
        BOOKTITLE = CVPR07,
        YEAR = "2007",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236581"}

@inproceedings{bb241673,
        AUTHOR = "O'Donovan, A. and Duraiswami, R. and Neumann, J.",
        TITLE = "Microphone Arrays as Generalized Cameras for Integrated Audio Visual
Processing",
        BOOKTITLE = CVPR07,
        YEAR = "2007",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236582"}

@inproceedings{bb241674,
        AUTHOR = "Abbas, J. and Dagli, C.K. and Huang, T.S.",
        TITLE = "A Multimodality Framework for Creating Speaker/Non-Speaker Profile
Databases for Real-World Video",
        BOOKTITLE = SLAM07,
        YEAR = "2007",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236583"}

@inproceedings{bb241675,
        AUTHOR = "Kushal, A. and Rahurkar, M. and Fei Fei, L. and Ponce, J. and Huang, T.",
        TITLE = "Audio-Visual Speaker Localization Using Graphical Models",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "I: 291-294",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236584"}

@inproceedings{bb241676,
        AUTHOR = "Tsuji, T. and Yamamoto, K. and Ishii, I.",
        TITLE = "Real-time Sound Source Localization Based on Audiovisual Frequency
Integration",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "IV: 322-325",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236585"}

@inproceedings{bb241677,
        AUTHOR = "Monaci, G. and Vandergheynst, P.",
        TITLE = "Audiovisual Gestalts",
        BOOKTITLE = PercOrg06,
        YEAR = "2006",
        PAGES = "200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236586"}

@inproceedings{bb241678,
        AUTHOR = "Zhu, Z.G. and Li, W.H. and Molina, E. and Wolberg, G.",
        TITLE = "LDV Sensing and Processing for Remote Hearing in a Multimodal
Surveillance System",
        BOOKTITLE = MSCSAS07,
        YEAR = "2007",
        PAGES = "1-2",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236587"}

@inproceedings{bb241679,
        AUTHOR = "Zhu, Z.G. and Li, W.H. and Wolberg, G.",
        TITLE = "Integrating LDV Audio and IR Video for Remote Multimodal Surveillance",
        BOOKTITLE = OTCBVS05,
        YEAR = "2005",
        PAGES = "III: 10-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236588"}

@inproceedings{bb241680,
        AUTHOR = "Wu, Z.Y. and Cai, L.H. and Meng, H.",
        TITLE = "Multi-level Fusion of Audio and Visual Features for Speaker
Identification",
        BOOKTITLE = ICB06,
        YEAR = "2006",
        PAGES = "493-499",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236589"}

@inproceedings{bb241681,
        AUTHOR = "Yang, P. and Yang, Y.C. and Wu, Z.H.",
        TITLE = "Exploiting Glottal Information in Speaker Recognition Using Parallel
GMMs",
        BOOKTITLE = AVBPA05,
        YEAR = "2005",
        PAGES = "804",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236590"}

@inproceedings{bb241682,
        AUTHOR = "Lei, Z.C.",
        TITLE = "Combining the Likelihood and the Kullback-Leibler Distance in
Estimating the Universal Background Model for Speaker Verification
Using SVM",
        BOOKTITLE = ICPR10,
        YEAR = "2010",
        PAGES = "4553-4556",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236591"}

@inproceedings{bb241683,
        AUTHOR = "Lei, Z.C. and Yang, Y.C. and Wu, Z.H.",
        TITLE = "An UBM-Based Reference Space for Speaker Recognition",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "IV: 318-321",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236592"}

@inproceedings{bb241684,
        AUTHOR = "Lei, Z.C. and Yang, Y.C. and Wu, Z.H.",
        TITLE = "Constructing the Discriminative Kernels Using GMM for Text-Independent
Speaker Identification",
        BOOKTITLE = IWBRS05,
        YEAR = "2005",
        PAGES = "165",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236593"}

@inproceedings{bb241685,
        AUTHOR = "Lei, Z.C. and Yang, Y.C. and Wu, Z.H.",
        TITLE = "Speaker Identification Using the VQ-Based Discriminative Kernels",
        BOOKTITLE = AVBPA05,
        YEAR = "2005",
        PAGES = "797",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236594"}

@inproceedings{bb241686,
        AUTHOR = "Li, D.D. and Yang, Y.C. and Wu, Z.H.",
        TITLE = "Dynamic Bayesian Networks for Audio-Visual Speaker Recognition",
        BOOKTITLE = ICB06,
        YEAR = "2006",
        PAGES = "539-545",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236595"}

@inproceedings{bb241687,
        AUTHOR = "Fox, N.A. and O'Mullane, B.A. and Reilly, R.B.",
        TITLE = "VALID:
A New Practical Audio-Visual Database, and Comparative Results",
        BOOKTITLE = AVBPA05,
        YEAR = "2005",
        PAGES = "777",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236596"}

@book{bb241688,
        AUTHOR = "Sharma, P. and Reilly, R.B.",
        TITLE = "The UCD Colour Face Image Database for Face Detection",
        PUBLISHER = "Online",
        YEAR = "1998",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236597"}

@inproceedings{bb241689,
        AUTHOR = "Fox, N.A. and O'Mullane, B.A. and Reilly, R.B.",
        TITLE = "Audio-Visual Speaker Identification via Adaptive Fusion Using
Reliability Estimates of Both Modalities",
        BOOKTITLE = AVBPA05,
        YEAR = "2005",
        PAGES = "787",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236598"}

@inproceedings{bb241690,
        AUTHOR = "Zhang, D. and Ghobakhlou, A. and Kasabov, N.",
        TITLE = "An adaptive model of person identification combining speech and image
information",
        BOOKTITLE = ICARCV04,
        YEAR = "2004",
        PAGES = "I: 413-418",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236599"}

@inproceedings{bb241691,
        AUTHOR = "Kratt, J. and Metze, F. and Stiefelhagen, R. and Waibel, A.",
        TITLE = "Large Vocabulary Audio-Visual Speech Recognition Using the Janus Speech
Recognition Toolkit",
        BOOKTITLE = DAGM04,
        YEAR = "2004",
        PAGES = "488-495",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236600"}

@inproceedings{bb241692,
        AUTHOR = "Hanafiah, Z.M. and Yamazaki, C. and Nakamura, A. and Kuno, Y.",
        TITLE = "Understanding inexplicit utterances using vision for helper robots",
        BOOKTITLE = ICPR04,
        YEAR = "2004",
        PAGES = "IV: 925-928",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236601"}

@inproceedings{bb241693,
        AUTHOR = "Hermann, T. and Henning, T. and Ritter, H.",
        TITLE = "Gesture Desk an Integrated Multi-modal Gestural Workplace
for Sonification",
        BOOKTITLE = GW03,
        YEAR = "2003",
        PAGES = "369-379",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236602"}

@inproceedings{bb241694,
        AUTHOR = "Merola, G.",
        TITLE = "The Effects of the Gesture Viewpoint on the Students' Memory of Words
and Stories",
        BOOKTITLE = GW07,
        YEAR = "2007",
        PAGES = "272-281",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236603"}

@inproceedings{bb241695,
        AUTHOR = "Merola, G. and Poggi, I.",
        TITLE = "Multimodality and Gestures in the Teacher's Communication",
        BOOKTITLE = GW03,
        YEAR = "2003",
        PAGES = "101-111",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236604"}

@inproceedings{bb241696,
        AUTHOR = "Kranstedt, A. and Kuhnlein, P. and Wachsmuth, I.",
        TITLE = "Deixis in Multimodal Human Computer Interaction:
An Interdisciplinary Approach",
        BOOKTITLE = GW03,
        YEAR = "2003",
        PAGES = "112-123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236605"}

@inproceedings{bb241697,
        AUTHOR = "Saeed, K. and Kozlowski, M.",
        TITLE = "An Image-Based System for Spoken-Letter Recognition",
        BOOKTITLE = CAIP03,
        YEAR = "2003",
        PAGES = "494-502",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236606"}

@inproceedings{bb241698,
        AUTHOR = "Ho, P. and Armington, J.",
        TITLE = "A Dual-Factor Authentication System Featuring Speaker Verification and
Token Technology",
        BOOKTITLE = AVBPA03,
        YEAR = "2003",
        PAGES = "128-136",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236607"}

@inproceedings{bb241699,
        AUTHOR = "Fox, N.A. and Reilly, R.B.",
        TITLE = "Audio-Visual Speaker Identification Based on the Use of Dynamic Audio
and Visual Features",
        BOOKTITLE = AVBPA03,
        YEAR = "2003",
        PAGES = "743-751",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT236608"}