@inproceedings{bb292800,
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#TT287427"}
@inproceedings{bb292801,
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#TT287428"}
@inproceedings{bb292802,
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#TT287429"}
@inproceedings{bb292803,
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#TT287430"}
@inproceedings{bb292804,
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#TT287431"}
@inproceedings{bb292805,
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#TT287432"}
@inproceedings{bb292806,
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#TT287433"}
@inproceedings{bb292807,
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#TT287434"}
@inproceedings{bb292808,
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#TT287435"}
@inproceedings{bb292809,
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#TT287436"}
@inproceedings{bb292810,
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#TT287437"}
@inproceedings{bb292811,
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#TT287438"}
@inproceedings{bb292812,
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#TT287439"}
@inproceedings{bb292813,
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#TT287440"}
@inproceedings{bb292814,
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#TT287441"}
@inproceedings{bb292815,
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#TT287442"}
@inproceedings{bb292816,
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#TT287443"}
@inproceedings{bb292817,
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#TT287444"}
@inproceedings{bb292818,
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#TT287445"}
@inproceedings{bb292819,
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#TT287446"}
@inproceedings{bb292820,
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#TT287447"}
@inproceedings{bb292821,
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#TT287448"}
@inproceedings{bb292822,
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#TT287449"}
@inproceedings{bb292823,
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#TT287450"}
@inproceedings{bb292824,
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#TT287451"}
@inproceedings{bb292825,
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#TT287452"}
@inproceedings{bb292826,
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#TT287453"}
@inproceedings{bb292827,
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#TT287454"}
@inproceedings{bb292828,
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#TT287455"}
@inproceedings{bb292829,
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#TT287456"}
@inproceedings{bb292830,
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#TT287457"}
@inproceedings{bb292831,
AUTHOR = "Eisenstein, J.",
TITLE = "Gesture in Automatic Discourse Processing",
BOOKTITLE = CSAIL,
YEAR = "2008",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287458"}
@inproceedings{bb292832,
AUTHOR = "Eisenstein, J.",
TITLE = "Gesture in Automatic Discourse Processing",
BOOKTITLE = Ph.D.,
YEAR = "2008",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287458"}
@inproceedings{bb292833,
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#TT287459"}
@inproceedings{bb292834,
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#TT287460"}
@inproceedings{bb292835,
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#TT287461"}
@inproceedings{bb292836,
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#TT287462"}
@inproceedings{bb292837,
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#TT287463"}
@inproceedings{bb292838,
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#TT287464"}
@inproceedings{bb292839,
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#TT287465"}
@inproceedings{bb292840,
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#TT287466"}
@inproceedings{bb292841,
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#TT287467"}
@inproceedings{bb292842,
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#TT287468"}
@inproceedings{bb292843,
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#TT287469"}
@inproceedings{bb292844,
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#TT287470"}
@inproceedings{bb292845,
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#TT287471"}
@inproceedings{bb292846,
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#TT287472"}
@inproceedings{bb292847,
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#TT287473"}
@inproceedings{bb292848,
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#TT287474"}
@inproceedings{bb292849,
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#TT287475"}
@inproceedings{bb292850,
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#TT287476"}
@inproceedings{bb292851,
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#TT287477"}
@inproceedings{bb292852,
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#TT287478"}
@inproceedings{bb292853,
AUTHOR = "Monaci, G. and Vandergheynst, P.",
TITLE = "Audiovisual Gestalts",
BOOKTITLE = PercOrg06,
YEAR = "2006",
PAGES = "200",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287479"}
@inproceedings{bb292854,
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#TT287480"}
@inproceedings{bb292855,
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#TT287481"}
@inproceedings{bb292856,
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#TT287482"}
@inproceedings{bb292857,
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#TT287483"}
@inproceedings{bb292858,
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#TT287484"}
@inproceedings{bb292859,
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#TT287485"}
@inproceedings{bb292860,
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#TT287486"}
@inproceedings{bb292861,
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#TT287487"}
@inproceedings{bb292862,
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#TT287488"}
@inproceedings{bb292863,
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#TT287489"}
@book{bb292864,
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#TT287490"}
@inproceedings{bb292865,
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#TT287491"}
@inproceedings{bb292866,
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#TT287492"}
@inproceedings{bb292867,
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#TT287493"}
@inproceedings{bb292868,
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#TT287494"}
@inproceedings{bb292869,
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#TT287495"}
@inproceedings{bb292870,
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#TT287496"}
@inproceedings{bb292871,
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#TT287497"}
@inproceedings{bb292872,
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#TT287498"}
@inproceedings{bb292873,
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#TT287499"}
@inproceedings{bb292874,
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#TT287500"}
@inproceedings{bb292875,
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#TT287501"}
@inproceedings{bb292876,
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#TT287502"}
@inproceedings{bb292877,
AUTHOR = "Bengio, S.",
TITLE = "Multimodal Authentication Using Asynchronous HMMs",
BOOKTITLE = AVBPA03,
YEAR = "2003",
PAGES = "770-777",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287503"}
@inproceedings{bb292878,
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#TT287504"}
@inproceedings{bb292879,
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#TT287505"}
@inproceedings{bb292880,
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#TT287506"}
@inproceedings{bb292881,
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#TT287507"}
@inproceedings{bb292882,
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#TT287508"}
@inproceedings{bb292883,
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#TT287509"}
@inproceedings{bb292884,
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#TT287510"}
@inproceedings{bb292885,
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#TT287511"}
@inproceedings{bb292886,
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#TT287512"}
@inproceedings{bb292887,
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#TT287513"}
@inproceedings{bb292888,
AUTHOR = "Nankaku, Y. and Tokuda, K. and Kitamura, T.",
TITLE = "Normalized Training for HMM-based Visual Speech Recognition",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol III: 234-237",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287514"}
@inproceedings{bb292889,
AUTHOR = "Zhang, Y. and Levinson, S. and Huang, T.S.",
TITLE = "Speaker Independent Audio-Visual Speech Recognition",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287515"}
@inproceedings{bb292890,
AUTHOR = "Pan, H. and Huang, T.S.",
TITLE = "A New Approach to Integrate Audio and Visual Features of Speech",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287516"}
@inproceedings{bb292891,
AUTHOR = "Potamianos, G. and Verma, A. and Neti, C. and Iyengar, G. and Basu, S.",
TITLE = "A Cascade Image Transform for Speaker Independent Automatic Speech
Reading",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287517"}
@inproceedings{bb292892,
AUTHOR = "Pan, H. and Liang, Z.P. and Huang, T.S.",
TITLE = "Fusing Audio and Visual Features of Speech",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol III: 214-217",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287518"}
@inproceedings{bb292893,
AUTHOR = "Faruquie, T.A. and Majumdar, A. and Rajput, N. and Subramaniam, L.V.",
TITLE = "Large Vocabulary Audio-visual Speech Recognition Using Active Shape
Models",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol III: 106-109",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287519"}
@inproceedings{bb292894,
AUTHOR = "Yu, K. and Jiang, X. and Bunke, H.",
TITLE = "Combining Acoustic and Visual Classifiers for the Recognition of Spoken
Sentences",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol II: 491-494",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287520"}
@inproceedings{bb292895,
AUTHOR = "Nam, J. and Alghoniemy, M. and Tewfik, A.H.",
TITLE = "Audio-visual content-based violent scene characterization",
BOOKTITLE = ICIP98,
YEAR = "1998",
PAGES = "I: 353-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287521"}
@inproceedings{bb292896,
AUTHOR = "Luettin, J. and Dupont, S.",
TITLE = "Continuous Audio-Visual Speech Recognition",
BOOKTITLE = ECCV98,
YEAR = "1998",
PAGES = "II: 657",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287522"}
@inproceedings{bb292897,
AUTHOR = "Yang, J. and Xiao, J. and Ritter, M.",
TITLE = "Automatic Selection of Visemes for Image-based Visual Speech Synthesis",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP8",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287523"}
@inproceedings{bb292898,
AUTHOR = "Sharma, R. and Cai, J.Y. and Chakravarthy, S. and Poddar, I. and Sethi, Y.",
TITLE = "Exploiting Speech/Gesture Co-occurrence for Improving Continuous
Gesture Recognition in Weather Narration",
BOOKTITLE = AFGR00,
YEAR = "2000",
PAGES = "422-427",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287524"}
@inproceedings{bb292899,
AUTHOR = "Yamamoto, E. and Nakamura, S. and Shikano, K.",
TITLE = "Lip Movement Synthesis from Speech Based on Hidden Markov Models",
BOOKTITLE = AFGR98,
YEAR = "1998",
PAGES = "154-159",
BIBSOURCE = "http://www.visionbib.com/bibliography/people916.html#TT287525"}
Last update:Jul 11, 2026 at 11:55:55