@inproceedings{bb287500,
        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#TT282137"}

@inproceedings{bb287501,
        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#TT282138"}

@inproceedings{bb287502,
        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#TT282139"}

@inproceedings{bb287503,
        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#TT282140"}

@inproceedings{bb287504,
        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#TT282141"}

@inproceedings{bb287505,
        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#TT282142"}

@inproceedings{bb287506,
        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#TT282143"}

@inproceedings{bb287507,
        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#TT282144"}

@inproceedings{bb287508,
        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#TT282145"}

@inproceedings{bb287509,
        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#TT282146"}

@inproceedings{bb287510,
        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#TT282147"}

@inproceedings{bb287511,
        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#TT282148"}

@inproceedings{bb287512,
        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#TT282149"}

@inproceedings{bb287513,
        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#TT282150"}

@inproceedings{bb287514,
        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#TT282151"}

@inproceedings{bb287515,
        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#TT282152"}

@inproceedings{bb287516,
        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#TT282153"}

@inproceedings{bb287517,
        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#TT282154"}

@inproceedings{bb287518,
        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#TT282155"}

@inproceedings{bb287519,
        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#TT282156"}

@inproceedings{bb287520,
        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#TT282157"}

@inproceedings{bb287521,
        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#TT282158"}

@inproceedings{bb287522,
        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#TT282159"}

@inproceedings{bb287523,
        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#TT282160"}

@inproceedings{bb287524,
        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#TT282161"}

@inproceedings{bb287525,
        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#TT282162"}

@inproceedings{bb287526,
        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#TT282163"}

@inproceedings{bb287527,
        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#TT282164"}

@inproceedings{bb287528,
        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#TT282165"}

@inproceedings{bb287529,
        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#TT282166"}

@inproceedings{bb287530,
        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#TT282167"}

@inproceedings{bb287531,
        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#TT282168"}

@inproceedings{bb287532,
        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#TT282169"}

@inproceedings{bb287533,
        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#TT282170"}

@inproceedings{bb287534,
        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#TT282171"}

@inproceedings{bb287535,
        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#TT282172"}

@inproceedings{bb287536,
        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#TT282173"}

@inproceedings{bb287537,
        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#TT282174"}

@inproceedings{bb287538,
        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#TT282175"}

@inproceedings{bb287539,
        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#TT282176"}

@inproceedings{bb287540,
        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#TT282177"}

@inproceedings{bb287541,
        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#TT282178"}

@inproceedings{bb287542,
        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#TT282179"}

@inproceedings{bb287543,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = CSAIL,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282180"}

@inproceedings{bb287544,
        AUTHOR = "Eisenstein, J.",
        TITLE = "Gesture in Automatic Discourse Processing",
        BOOKTITLE = Ph.D.,
        YEAR = "2008",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282180"}

@inproceedings{bb287545,
        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#TT282181"}

@inproceedings{bb287546,
        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#TT282182"}

@inproceedings{bb287547,
        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#TT282183"}

@inproceedings{bb287548,
        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#TT282184"}

@inproceedings{bb287549,
        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#TT282185"}

@inproceedings{bb287550,
        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#TT282186"}

@inproceedings{bb287551,
        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#TT282187"}

@inproceedings{bb287552,
        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#TT282188"}

@inproceedings{bb287553,
        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#TT282189"}

@inproceedings{bb287554,
        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#TT282190"}

@inproceedings{bb287555,
        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#TT282191"}

@inproceedings{bb287556,
        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#TT282192"}

@inproceedings{bb287557,
        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#TT282193"}

@inproceedings{bb287558,
        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#TT282194"}

@inproceedings{bb287559,
        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#TT282195"}

@inproceedings{bb287560,
        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#TT282196"}

@inproceedings{bb287561,
        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#TT282197"}

@inproceedings{bb287562,
        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#TT282198"}

@inproceedings{bb287563,
        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#TT282199"}

@inproceedings{bb287564,
        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#TT282200"}

@inproceedings{bb287565,
        AUTHOR = "Monaci, G. and Vandergheynst, P.",
        TITLE = "Audiovisual Gestalts",
        BOOKTITLE = PercOrg06,
        YEAR = "2006",
        PAGES = "200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282201"}

@inproceedings{bb287566,
        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#TT282202"}

@inproceedings{bb287567,
        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#TT282203"}

@inproceedings{bb287568,
        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#TT282204"}

@inproceedings{bb287569,
        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#TT282205"}

@inproceedings{bb287570,
        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#TT282206"}

@inproceedings{bb287571,
        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#TT282207"}

@inproceedings{bb287572,
        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#TT282208"}

@inproceedings{bb287573,
        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#TT282209"}

@inproceedings{bb287574,
        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#TT282210"}

@inproceedings{bb287575,
        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#TT282211"}

@book{bb287576,
        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#TT282212"}

@inproceedings{bb287577,
        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#TT282213"}

@inproceedings{bb287578,
        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#TT282214"}

@inproceedings{bb287579,
        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#TT282215"}

@inproceedings{bb287580,
        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#TT282216"}

@inproceedings{bb287581,
        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#TT282217"}

@inproceedings{bb287582,
        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#TT282218"}

@inproceedings{bb287583,
        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#TT282219"}

@inproceedings{bb287584,
        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#TT282220"}

@inproceedings{bb287585,
        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#TT282221"}

@inproceedings{bb287586,
        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#TT282222"}

@inproceedings{bb287587,
        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#TT282223"}

@inproceedings{bb287588,
        AUTHOR = "Czyz, J. and Bengio, S. and Marcel, C. and Vandendorpe, L.",
        TITLE = "Scalability Analysis of Audio-Visual Person Identity Verification",
        BOOKTITLE = AVBPA03,
        YEAR = "2003",
        PAGES = "752-760",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282224"}

@inproceedings{bb287589,
        AUTHOR = "Bengio, S.",
        TITLE = "Multimodal Authentication Using Asynchronous HMMs",
        BOOKTITLE = AVBPA03,
        YEAR = "2003",
        PAGES = "770-777",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282225"}

@inproceedings{bb287590,
        AUTHOR = "Lucey, S. and Chen, T.H.",
        TITLE = "Improved Audio-Visual Speaker Recognition via the Use of a Hybrid
Combination Strategy",
        BOOKTITLE = AVBPA03,
        YEAR = "2003",
        PAGES = "929-936",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282226"}

@inproceedings{bb287591,
        AUTHOR = "Krahnstoever, N. and Schapira, E. and Kettebeko, S. and Sharma, R.",
        TITLE = "Multimodal human-computer interaction for crisis management systems",
        BOOKTITLE = WACV02,
        YEAR = "2002",
        PAGES = "203-207",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282227"}

@inproceedings{bb287592,
        AUTHOR = "Kettebekov, S. and Yeasin, M. and Sharma, R.",
        TITLE = "Improving continuous gesture recognition with spoken prosody",
        BOOKTITLE = CVPR03,
        YEAR = "2003",
        PAGES = "I: 565-570",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282228"}

@inproceedings{bb287593,
        AUTHOR = "Poh, N. and Korczak, J.",
        TITLE = "Hybrid Biometric Person Authentication Using Face and Voice Features",
        BOOKTITLE = AVBPA01,
        YEAR = "2001",
        PAGES = "348",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282229"}

@inproceedings{bb287594,
        AUTHOR = "Nakamura, S.",
        TITLE = "Fusion of Audio-Visual Information for Integrated Speech Processing",
        BOOKTITLE = AVBPA01,
        YEAR = "2001",
        PAGES = "127",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282230"}

@inproceedings{bb287595,
        AUTHOR = "Sullivan, K.P.H. and Pelecanos, J.",
        TITLE = "Revisiting Carl Bildt's Impostor: Would a Speaker Verification System
Foil Him?",
        BOOKTITLE = AVBPA01,
        YEAR = "2001",
        PAGES = "144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282231"}

@inproceedings{bb287596,
        AUTHOR = "Geiger, G. and Ezzat, T. and Poggio, T.",
        TITLE = "Perceptual Evaluation of Video-Realistic Speech",
        BOOKTITLE = "MIT AIM",
        YEAR = "2003",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282232"}

@inproceedings{bb287597,
        AUTHOR = "Zhang, X.Z. and Merserratt, R.M. and Clements, M.",
        TITLE = "Bimodal fusion in audio-visual speech recognition",
        BOOKTITLE = ICIP02,
        YEAR = "2002",
        PAGES = "I: 964-967",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282233"}

@inproceedings{bb287598,
        AUTHOR = "Graf, H.P. and Cosatto, E. and Strom, V. and Huang, F.J.",
        TITLE = "Visual prosody: facial movements accompanying speech",
        BOOKTITLE = AFGR02,
        YEAR = "2002",
        PAGES = "381-386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282234"}

@inproceedings{bb287599,
        AUTHOR = "Qi, Y.",
        TITLE = "Learning Algorithms for Audio and Video Processing: 
Independent Component Analysis and Support Vector Machine Based Approaches",
        BOOKTITLE = UMD,
        YEAR = "2000",
        BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT282235"}