@inproceedings{bb108100,
        AUTHOR = "Liang, H. and Yu, L. and Xu, G. and Raj, B. and Singh, R.",
        TITLE = "Controlled Autoencoders to Generate Faces from Voices",
        BOOKTITLE = ISVC20,
        YEAR = "2020",
        PAGES = "I:476-487",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104815"}

@inproceedings{bb108101,
        AUTHOR = "Liao, M. and Zhang, S. and Wang, P. and Zhu, H. and Zuo, X. and Yang, R.G.",
        TITLE = "Speech2video Synthesis with 3d Skeleton Regularization and Expressive
Body Poses",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "V:308-323",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104816"}

@inproceedings{bb108102,
        AUTHOR = "Xue, H. and Ling, J. and Song, L. and Xie, R. and Zhang, W.",
        TITLE = "Realistic Talking Face Synthesis With Geometry-Aware Feature
Transformation",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1581-1585",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104817"}

@inproceedings{bb108103,
        AUTHOR = "Chen, L. and Cui, G.F. and Liu, C.L. and Li, Z. and Kou, Z. and Xu, Y. and Xu, C.L.",
        TITLE = "Talking-head Generation with Rhythmic Head Motion",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "IX:35-51",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104818"}

@inproceedings{bb108104,
        AUTHOR = "Khakhulin, T. and Sklyarova, V. and Lempitsky, V. and Zakharov, E.",
        TITLE = "Realistic One-Shot Mesh-Based Head Avatars",
        BOOKTITLE = ECCV22,
        YEAR = "2022",
        PAGES = "II:345-362",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104819"}

@inproceedings{bb108105,
        AUTHOR = "Zakharov, E. and Ivakhnenko, A. and Shysheya, A. and Lempitsky, V.",
        TITLE = "Fast Bi-layer Neural Synthesis of One-shot Realistic Head Avatars",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XII: 524-540",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104820"}

@inproceedings{bb108106,
        AUTHOR = "Chu, H. and Ma, S.G. and de la Torre, F. and Fidler, S. and Sheikh, Y.",
        TITLE = "Expressive Telepresence via Modular Codec Avatars",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XII: 330-345",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104821"}

@inproceedings{bb108107,
        AUTHOR = "Thies, J. and Elgharib, M. and Tewari, A. and Theobalt, C. and Nießner, M.",
        TITLE = "Neural Voice Puppetry: Audio-driven Facial Reenactment",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVI: 716-731",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104822"}

@inproceedings{bb108108,
        AUTHOR = "Pang, W. and Wang, X.J.",
        TITLE = "Guessing State Tracking for Visual Dialogue",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVI: 683-698",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104823"}

@inproceedings{bb108109,
        AUTHOR = "Das, D. and Biswas, S. and Sinha, S. and Bhowmick, B.",
        TITLE = "Speech-driven Facial Animation Using Cascaded Gans for Learning of
Motion and Texture",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXX: 408-424",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104824"}

@inproceedings{bb108110,
        AUTHOR = "Shalev, Y. and Wolf, L.B.",
        TITLE = "Image Animation with Perturbed Masks",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "3637-3646",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104825"}

@inproceedings{bb108111,
        AUTHOR = "Mittal, G. and Wang, B.",
        TITLE = "Animating Face using Disentangled Audio Representations",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "3279-3287",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104826"}

@inproceedings{bb108112,
        AUTHOR = "Chen, Z. and Liu, Z. and Hu, H. and Bai, J. and Lian, S. and Shi, F. and Wang, K.",
        TITLE = "A Realistic Face-to-Face Conversation System Based on Deep Neural
Networks",
        BOOKTITLE = ACVR19,
        YEAR = "2019",
        PAGES = "2575-2583",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104827"}

@inproceedings{bb108113,
        AUTHOR = "Zakharov, E. and Shysheya, A. and Burkov, E. and Lempitsky, V.",
        TITLE = "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "9458-9467",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104828"}

@inproceedings{bb108114,
        AUTHOR = "Cudeiro, D. and Bolkart, T. and Laidlaw, C. and Ranjan, A. and Black, M.J.",
        TITLE = "Capture, Learning, and Synthesis of 3D Speaking Styles",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10093-10103",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104829"}

@inproceedings{bb108115,
        AUTHOR = "Chen, L. and Maddox, R.K. and Duan, Z.Y. and Xu, C.L.",
        TITLE = "Hierarchical Cross-Modal Talking Face Generation With Dynamic
Pixel-Wise Loss",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "7824-7833",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104830"}

@inproceedings{bb108116,
        AUTHOR = "Chu, H. and Li, D.Q. and Fidler, S.",
        TITLE = "A Face-to-Face Neural Conversation Model",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7113-7121",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104831"}

@inproceedings{bb108117,
        AUTHOR = "Afouras, T. and Asano, Y.M. and Fagan, F. and Vedaldi, A. and Metze, F.",
        TITLE = "Self-supervised object detection from audio-visual correspondence",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "10565-10576",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104832"}

@inproceedings{bb108118,
        AUTHOR = "Feng, C. and Chen, Z.Y. and Owens, A.",
        TITLE = "Self-Supervised Video Forensics by Audio-Visual Anomaly Detection",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "10491-10503",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104833"}

@inproceedings{bb108119,
        AUTHOR = "Afouras, T. and Owens, A. and Chung, J.S. and Zisserman, A.",
        TITLE = "Self-supervised Learning of Audio-visual Objects from Video",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVIII:208-224",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104834"}

@inproceedings{bb108120,
        AUTHOR = "Wiles, O. and Koepke, A.S. and Zisserman, A.",
        TITLE = "Self-Supervised Learning of Class Embeddings from Video",
        BOOKTITLE = CEFRL19,
        YEAR = "2019",
        PAGES = "3019-3027",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104835"}

@inproceedings{bb108121,
        AUTHOR = "Wiles, O. and Koepke, A.S. and Zisserman, A.",
        TITLE = "X2Face: A Network for Controlling Face Generation Using Images, Audio,
and Pose Codes",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XIII: 690-706",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104836"}

@inproceedings{bb108122,
        AUTHOR = "Modrzejewski, M. and Rokita, P.",
        TITLE = "Graphical Interface Design for Chatbots for the Needs of Artificial
Intelligence Support in Web and Mobile Applications",
        BOOKTITLE = ICCVG18,
        YEAR = "2018",
        PAGES = "48-56",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104837"}

@inproceedings{bb108123,
        AUTHOR = "Nakatani, S. and Saiki, S. and Nakamura, M. and Yasuda, K.",
        TITLE = "Generating Personalized Virtual Agent in Speech Dialogue System for
People with Dementia",
        BOOKTITLE = DHM18,
        YEAR = "2018",
        PAGES = "326-337",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104838"}

@inproceedings{bb108124,
        AUTHOR = "Huber, B. and McDuff, D.",
        TITLE = "Facial Expression Grounded Conversational Dialogue Generation",
        BOOKTITLE = FG18,
        YEAR = "2018",
        PAGES = "365-372",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104839"}

@inproceedings{bb108125,
        AUTHOR = "Luo, C. and Yu, J. and Li, X. and Zhang, L.",
        TITLE = "HMM based speech-driven 3D tongue animation",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "4377-4381",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104840"}

@inproceedings{bb108126,
        AUTHOR = "Filntisis, P.P. and Katsamanis, A. and Maragos, P.",
        TITLE = "Photorealistic adaptation and interpolation of facial expressions
using HMMS and AAMS for audio-visual speech synthesis",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "2941-2945",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104841"}

@inproceedings{bb108127,
        AUTHOR = "Filntisis, P.P. and Katsamanis, A. and Maragos, P.",
        TITLE = "Demonstration of an HMM-based photorealistic expressive audio-visual
speech synthesis system",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "4588-4588",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104842"}

@inproceedings{bb108128,
        AUTHOR = "Wang, Y.B. and Khoo, E.T.",
        TITLE = "Real-time stereoscopic rendering of realistic avatar for interactive
3D telepresence system",
        BOOKTITLE = ICIVC17,
        YEAR = "2017",
        PAGES = "577-581",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104843"}

@inproceedings{bb108129,
        AUTHOR = "Yu, J.",
        TITLE = "A Real-Time 3D Visual Singing Synthesis:
From Appearance to Internal Articulators",
        BOOKTITLE = MMMod17,
        YEAR = "2017",
        PAGES = "I: 53-64",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104844"}

@inproceedings{bb108130,
        AUTHOR = "Dawood, S. and Hicks, Y. and Marshall, D.",
        TITLE = "Speech-Driven Facial Animation Using Manifold Relevance Determination",
        BOOKTITLE = CVAVM16,
        YEAR = "2016",
        PAGES = "II: 869-882",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104845"}

@inproceedings{bb108131,
        AUTHOR = "Malleson, C. and Bazin, J.C. and Wang, O. and Bradley, D. and Beeler, T. and Hilton, A. and Sorkine Hornung, A.",
        TITLE = "FaceDirector: Continuous Control of Facial Performance in Video",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "3979-3987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104846"}

@inproceedings{bb108132,
        AUTHOR = "Musti, U. and Zhou, Z.H. and Pietikainen, M.",
        TITLE = "Facial 3D Shape Estimation from Images for Visual Speech Animation",
        BOOKTITLE = ICPR14,
        YEAR = "2014",
        PAGES = "40-45",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104847"}

@inproceedings{bb108133,
        AUTHOR = "Yu, J. and Li, A.",
        TITLE = "3D visual pronunciation of Mandarine Chinese for language learning",
        BOOKTITLE = ICIP14,
        YEAR = "2014",
        PAGES = "2036-2040",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104848"}

@inproceedings{bb108134,
        AUTHOR = "Anderson, R. and Stenger, B. and Wan, V. and Cipolla, R.",
        TITLE = "Expressive Visual Text-to-Speech Using Active Appearance Models",
        BOOKTITLE = CVPR13,
        YEAR = "2013",
        PAGES = "3382-3389",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104849"}

@inproceedings{bb108135,
        AUTHOR = "Manresa Yee, C. and Ponsa, P. and Arellano, D. and Larrea, M.",
        TITLE = "An Avatar Acceptance Study for Home Automation Scenarios",
        BOOKTITLE = AMDO12,
        YEAR = "2012",
        PAGES = "230-238",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104850"}

@inproceedings{bb108136,
        AUTHOR = "Tang, Y.Q. and Fang, Y. and Huang, Q.H.",
        TITLE = "Audio personalization using head related transfer function in 3DTV",
        BOOKTITLE = "3DTV11",
        YEAR = "2011",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104851"}

@inproceedings{bb108137,
        AUTHOR = "Liu, K. and Ostermann, J.",
        TITLE = "Realistic head motion synthesis for an image-based talking head",
        BOOKTITLE = FG11,
        YEAR = "2011",
        PAGES = "125-130",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104852"}

@inproceedings{bb108138,
        AUTHOR = "Ostermann, J. and Liu, K.",
        TITLE = "Realistic head motion synthesis for an image-based talking head",
        BOOKTITLE = FG11,
        YEAR = "2011",
        PAGES = "221-226",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104852"}

@inproceedings{bb108139,
        AUTHOR = "Chaloupka, J. and Chaloupka, Z.",
        TITLE = "Czech Artificial Computerized Talking Head George",
        BOOKTITLE = COST08,
        YEAR = "2008",
        PAGES = "324-330",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104853"}

@inproceedings{bb108140,
        AUTHOR = "Zhao, H. and Chen, Y.B. and Shen, Y.M. and Tang, C.J.",
        TITLE = "Audio-Visual Speech Synthesis Based on Chinese Visual Triphone",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104854"}

@inproceedings{bb108141,
        AUTHOR = "Hu, Y.L. and Zhou, M.Q. and Wu, Z.K.",
        TITLE = "An Automatic Dense Point Registration Method for 3D Face Animation",
        BOOKTITLE = CISP09,
        YEAR = "2009",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104855"}

@inproceedings{bb108142,
        AUTHOR = "Berger, M.O. and Ponroy, J. and Wrobel Dautcourt, B.",
        TITLE = "Realistic Face Animation for Audiovisual Speech Applications: A
Densification Approach Driven by Sparse Stereo Meshes",
        BOOKTITLE = MIRAGE09,
        YEAR = "2009",
        PAGES = "297-307",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104856"}

@inproceedings{bb108143,
        AUTHOR = "Verdet, F. and Hennebert, J.",
        TITLE = "Impostures of Talking Face Systems Using Automatic Face Animation",
        BOOKTITLE = BTAS08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104857"}

@inproceedings{bb108144,
        AUTHOR = "Gaur, U. and Jain, A. and Goel, S.",
        TITLE = "Towards Real-Time Monocular Video-Based Avatar Animation",
        BOOKTITLE = ISVC08,
        YEAR = "2008",
        PAGES = "II: 949-958",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104858"}

@inproceedings{bb108145,
        AUTHOR = "Badin, P. and Elisei, F. and Bailly, G. and Tarabalka, Y.",
        TITLE = "An Audiovisual Talking Head for Augmented Speech Generation: Models and
Animations Based on a Real Speaker's Articulatory Data",
        BOOKTITLE = AMDO08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104859"}

@inproceedings{bb108146,
        AUTHOR = "Fanelli, G. and Fratarcangeli, M.",
        TITLE = "A Non-Invasive Approach for Driving Virtual Talking Heads from Real
Facial Movements",
        BOOKTITLE = "3DTV07",
        YEAR = "2007",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104860"}

@inproceedings{bb108147,
        AUTHOR = "Xiong, L. and Zheng, N.N. and You, Q. and Liu, J.Y.",
        TITLE = "Facial Expression Sequence Synthesis Based on Shape and Texture Fusion
Model",
        BOOKTITLE = ICIP07,
        YEAR = "2007",
        PAGES = "IV: 473-476",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104861"}

@inproceedings{bb108148,
        AUTHOR = "Beaumesnil, B. and Luthon, F.",
        TITLE = "Real Time Tracking for 3D Realistic Lip Animation",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "I: 219-222",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104862"}

@inproceedings{bb108149,
        AUTHOR = "Ravindra de Silva, P. and Madurapperuma, A.P. and Marasinghe, A. and Osano, M.",
        TITLE = "Integrating Animated Pedagogical Agent as Motivational Supporter into
Interactive System",
        BOOKTITLE = CRV06,
        YEAR = "2006",
        PAGES = "34-34",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104863"}

@inproceedings{bb108150,
        AUTHOR = "Pei, Y.R. and Zha, H.B.",
        TITLE = "Vision Based Speech Animation Transferring with Underlying Anatomical
Structure",
        BOOKTITLE = ACCV06,
        YEAR = "2006",
        PAGES = "I:591-600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104864"}

@inproceedings{bb108151,
        AUTHOR = "Liu, Y.H. and Xu, G.Y. and Tao, L.M.",
        TITLE = "An Efficient Approach for Multi-view Face Animation Based on Quasi 3D
Model",
        BOOKTITLE = ACCV06,
        YEAR = "2006",
        PAGES = "II:913-922",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104865"}

@inproceedings{bb108152,
        AUTHOR = "Leszczynski, M. and Skarbek, W.",
        TITLE = "Viseme Classification for Talking Head Application",
        BOOKTITLE = CAIP05,
        YEAR = "2005",
        PAGES = "773",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104866"}

@inproceedings{bb108153,
        AUTHOR = "Leszczynski, M. and Skarbek, W.",
        TITLE = "Viseme recognition: A comparative study",
        BOOKTITLE = AVSBS05,
        YEAR = "2005",
        PAGES = "287-292",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104867"}

@inproceedings{bb108154,
        AUTHOR = "Leszczynski, M. and Skarbek, W. and Badura, S.",
        TITLE = "Fast Viseme Recognition for Talking Head Application",
        BOOKTITLE = ICIAR05,
        YEAR = "2005",
        PAGES = "516-523",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104868"}

@inproceedings{bb108155,
        AUTHOR = "Gracia Roche, J.J. and Orrite, C. and Bernues, E. and Herrero, J.E.",
        TITLE = "Color Distribution Tracking for Facial Analysis",
        BOOKTITLE = IbPRIA05,
        YEAR = "2005",
        PAGES = "I:484",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104869"}

@inproceedings{bb108156,
        AUTHOR = "Ypsilos, I.A. and Hilton, A. and Turkmani, A. and Jackson, P.J.B.",
        TITLE = "Speech-driven face synthesis from 3D video",
        BOOKTITLE = "3DPVT04",
        YEAR = "2004",
        PAGES = "58-65",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104870"}

@inproceedings{bb108157,
        AUTHOR = "Saisan, P. and Bissacco, A. and Chiuso, A. and Soatto, S.",
        TITLE = "Modeling and Synthesis of Facial Motion Driven by Speech",
        BOOKTITLE = ECCV04,
        YEAR = "2004",
        PAGES = "Vol III: 456-467",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104871"}

@inproceedings{bb108158,
        AUTHOR = "Malcangi, M. and de Tintis, R.",
        TITLE = "Audio Based Real-Time Speech Animation of Embodied Conversational
Agents",
        BOOKTITLE = GW03,
        YEAR = "2003",
        PAGES = "350-360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104872"}

@inproceedings{bb108159,
        AUTHOR = "Aleksic, P.S. and Katsaggelos, A.K.",
        TITLE = "Speech-to-video synthesis using facial animation parameters",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "III: 1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104873"}

@inproceedings{bb108160,
        AUTHOR = "Hack, C.A. and Taylor, C.J.",
        TITLE = "Modelling 'Talking Head' Behaviour",
        BOOKTITLE = BMVC03,
        YEAR = "2003",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104874"}

@inproceedings{bb108161,
        AUTHOR = "Choi, K.H. and Hwang, J.N.",
        TITLE = "Creating 3D speech-driven talking heads: a probabilistic network
approach",
        BOOKTITLE = ICIP02,
        YEAR = "2002",
        PAGES = "I: 984-987",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104875"}

@inproceedings{bb108162,
        AUTHOR = "Hong, P.Y. and Wen, Z. and Huang, T.S. and Shum, H.Y.",
        TITLE = "Real-time speech-driven 3D face animation",
        BOOKTITLE = "3DPVT02",
        YEAR = "2002",
        PAGES = "713-716",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104876"}

@inproceedings{bb108163,
        AUTHOR = "Morishima, S. and Yotsukura, T.",
        TITLE = "Hypermask: Talking Head Projected Onto Moving Surface",
        BOOKTITLE = ICIP01,
        YEAR = "2001",
        PAGES = "III: 947-950",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104877"}

@inproceedings{bb108164,
        AUTHOR = "Neumann, J. and Aloimonos, Y.",
        TITLE = "Talking Heads: Introducing the tool of 3D motion fields in the study of
action",
        BOOKTITLE = HUMO00,
        YEAR = "2000",
        PAGES = "25-32",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104878"}

@inproceedings{bb108165,
        AUTHOR = "Chen, T.H. and Wang, Y. and Graf, H.P. and Swain, C.T.",
        TITLE = "A new frame interpolation scheme for talking head sequences",
        BOOKTITLE = ICIP95,
        YEAR = "1995",
        PAGES = "II: 591-594",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104879"}

@inproceedings{bb108166,
        AUTHOR = "Shan, S.",
        TITLE = "Individual 3d Face Synthesis Based on Orthogonal Photos and
Speech-driven Facial Animation",
        BOOKTITLE = ICIP00,
        YEAR = "2000",
        PAGES = "Vol III: 238-241",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104880"}

@inproceedings{bb108167,
        AUTHOR = "Noh, J.Y. and Neumann, U.",
        TITLE = "Talking Face",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "TA1",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104881"}

@inproceedings{bb108168,
        AUTHOR = "Kakihara, K. and Nakamura, S. and Shikano, K.",
        TITLE = "Speech-To-Face Movement Synthesis Based on HMMS",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "MP7",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104882"}

@inproceedings{bb108169,
        AUTHOR = "Van Gool, L.J. and Tuytelaars, T. and Pollefeys, M.",
        TITLE = "Adventurous Tourism for Couch Potatoes",
        BOOKTITLE = CAIP99,
        YEAR = "1999",
        PAGES = "98-107",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104883"}

@inproceedings{bb108170,
        AUTHOR = "Ishikawa, T. and Sera, H. and Morishima, S. and Terzopoulos, D.",
        TITLE = "Facial Image Reconstruction by Estimated Muscle Parameter",
        BOOKTITLE = AFGR98,
        YEAR = "1998",
        PAGES = "342-347",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104884"}

@inproceedings{bb108171,
        AUTHOR = "Bothe, H.H.",
        TITLE = "A visual speech model based on fuzzy-neuro methods",
        BOOKTITLE = CIAP95,
        YEAR = "1995",
        PAGES = "152-158",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe499.html#TT104885"}

@article{bb108172,
        AUTHOR = "Lavagetto, F.",
        TITLE = "Time-Delay Neural Networks for Estimating Lip Movements from
Speech Analysis:
A Useful Tool in Audio Video Synchronization",
        JOURNAL = CirSysVideo,
        VOLUME = "7",
        YEAR = "1997",
        NUMBER = "5",
        MONTH = "October",
        PAGES = "786-800",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104886"}

@inproceedings{bb108173,
        AUTHOR = "Gasper, E. and Matthews, J.H. and Wesley, R.",
        TITLE = "Advanced tools for speech synchronized animation",
        BOOKTITLE = US_Patent,
        YEAR = "1997",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104887"}

@inproceedings{bb108174,
        AUTHOR = "Wesley, R. and Matthews, J.H. and Gasper, E.",
        TITLE = "Advanced tools for speech synchronized animation",
        BOOKTITLE = US_Patent,
        YEAR = "1997",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104887"}

@inproceedings{bb108175,
        AUTHOR = "Gasper, E. and Wesley, R.",
        TITLE = "Advanced tools for speech synchronized animation",
        BOOKTITLE = US_Patent,
        YEAR = "1997",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104887"}

@article{bb108176,
        AUTHOR = "Chien, J.T. and Lin, M.S.",
        TITLE = "Frame-synchronous noise compensation for hands-free speech recognition
in car environments",
        JOURNAL = VISP,
        VOLUME = "147",
        YEAR = "2000",
        NUMBER = "6",
        MONTH = "December",
        PAGES = "508-515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104888"}

@inproceedings{bb108177,
        AUTHOR = "Rosenfeld, M.",
        TITLE = "Method for automatically animating lip synchronization and
facial expression of animated characters",
        BOOKTITLE = US_Patent,
        YEAR = "2001",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104889"}

@inproceedings{bb108178,
        AUTHOR = "Haisma, N. and Sinke, J.G. and Bergevoet, B.A.J. and van Gestel, H.A.W.",
        TITLE = "Post-synchronizing an information stream including lip
objects replacement",
        BOOKTITLE = US_Patent,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104890"}

@inproceedings{bb108179,
        AUTHOR = "Huang, Y. and Lin, S.S.T. and Guo, B.N. and Shum, H.Y.",
        TITLE = "System and method for real time lip synchronization",
        BOOKTITLE = US_Patent,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104891"}

@article{bb108180,
        AUTHOR = "Saenko, K. and Livescu, K. and Glass, J. and Darrell, T.J.",
        TITLE = "Multistream Articulatory Feature-Based Models for Visual Speech
Recognition",
        JOURNAL = PAMI,
        VOLUME = "31",
        YEAR = "2009",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1700-1707",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104892"}

@inproceedings{bb108181,
        AUTHOR = "Saenko, K. and Livescu, K. and Siracusa, M. and Wilson, K. and Glass, J. and Darrell, T.J.",
        TITLE = "Visual Speech Recognition with Loosely Synchronized Feature Streams",
        BOOKTITLE = ICCV05,
        YEAR = "2005",
        PAGES = "II: 1424-1431",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104893"}

@article{bb108182,
        AUTHOR = "El Sallam, A.A. and Mian, A.S.",
        TITLE = "Correlation based speech-video synchronization",
        JOURNAL = PRL,
        VOLUME = "32",
        YEAR = "2011",
        NUMBER = "6",
        MONTH = "April",
        PAGES = "780-786",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104894"}

@inproceedings{bb108183,
        AUTHOR = "El Sallam, A.A. and Mian, A.S.",
        TITLE = "Speech-Video Synchronization Using Lips Movements and Speech Envelope
Correlation",
        BOOKTITLE = ICIAR09,
        YEAR = "2009",
        PAGES = "397-407",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104895"}

@article{bb108184,
        AUTHOR = "Chen, Y.M. and Huang, F.C. and Guan, S.H. and Chen, B.Y.",
        TITLE = "Animating Lip-Sync Characters With Dominated Animeme Models",
        JOURNAL = CirSysVideo,
        VOLUME = "22",
        YEAR = "2012",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "1344-1353",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104896"}

@article{bb108185,
        AUTHOR = "Srinivasan, V. and Bethel, C.L. and Murphy, R.R.",
        TITLE = "Evaluation of Head Gaze Loosely Synchronized With Real-Time Synthetic
Speech for Social Robots",
        JOURNAL = HMS,
        VOLUME = "44",
        YEAR = "2014",
        NUMBER = "6",
        MONTH = "December",
        PAGES = "767-778",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104897"}

@article{bb108186,
        AUTHOR = "Liu, N. and Zhou, T. and Ji, Y.F. and Zhao, Z.Y. and Wan, L.H.",
        TITLE = "Synthesizing Talking Faces from Text and Audio: An Autoencoder and
Sequence-to-Sequence Convolutional Neural Network",
        JOURNAL = PR,
        VOLUME = "102",
        YEAR = "2020",
        PAGES = "107231",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104898"}

@article{bb108187,
        AUTHOR = "Yu, L. and Yu, J. and Li, M. and Ling, Q.",
        TITLE = "Multimodal Inputs Driven Talking Face Generation With
Spatial-Temporal Dependency",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "203-216",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104899"}

@article{bb108188,
        AUTHOR = "Liu, L. and Feng, G. and Beautemps, D. and Zhang, X.P.",
        TITLE = "Re-Synchronization Using the Hand Preceding Model for Multi-Modal
Fusion in Automatic Continuous Cued Speech Recognition",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "292-305",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104900"}

@article{bb108189,
        AUTHOR = "Beyan, C. and Shahid, M. and Murino, V.",
        TITLE = "RealVAD: A Real-World Dataset and A Method for Voice Activity
Detection by Body Motion Analysis",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "2071-2085",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104901"}

@article{bb108190,
        AUTHOR = "Eskimez, S.E. and Zhang, Y. and Duan, Z.Y.",
        TITLE = "Speech Driven Talking Face Generation From a Single Image and an
Emotion Condition",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "3480-3490",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104902"}

@article{bb108191,
        AUTHOR = "Ghose, S. and Prevost, J.J.",
        TITLE = "FoleyGAN: Visually Guided Generative Adversarial Network-Based
Synchronous Sound Generation in Silent Videos",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "4508-4519",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104903"}

@article{bb108192,
        AUTHOR = "Zhou, J.X. and Guo, D. and Wang, M.",
        TITLE = "Contrastive Positive Sample Propagation Along the Audio-Visual Event
Line",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "7239-7257",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104904"}

@inproceedings{bb108193,
        AUTHOR = "Zhou, J.X. and Zheng, L. and Zhong, Y.R. and Hao, S.J. and Wang, M.",
        TITLE = "Positive Sample Propagation along the Audio-Visual Event Line",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "8432-8440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104905"}

@article{bb108194,
        AUTHOR = "Wang, X.S. and Xie, Q. and Zhu, J. and Xie, L. and Scharenborg, O.",
        TITLE = "AnyoneNet: Synchronized Speech and Talking Head Generation for
Arbitrary Persons",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "6717-6728",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104906"}

@article{bb108195,
        AUTHOR = "Yang, D. and Huang, S. and Jiang, W. and Zou, J.",
        TITLE = "Implicit Memory-Based Variational Motion Talking Face Generation",
        JOURNAL = SPLetters,
        VOLUME = "31",
        YEAR = "2024",
        PAGES = "431-435",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104907"}

@article{bb108196,
        AUTHOR = "Cheng, H. and Guo, Y.Y. and Yin, J.H. and Chen, H. and Wang, J. and Nie, L.Q.",
        TITLE = "Audio-Driven Talking Video Frame Restoration",
        JOURNAL = MultMed,
        VOLUME = "26",
        YEAR = "2024",
        PAGES = "4110-4122",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104908"}

@article{bb108197,
        AUTHOR = "Sheng, Z.C. and Nie, L.Q. and Zhang, M. and Chang, X.J. and Yan, Y.",
        TITLE = "Stochastic Latent Talking Face Generation Toward Emotional
Expressions and Head Poses",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "2734-2748",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104909"}

@article{bb108198,
        AUTHOR = "Liu, M. and Li, D. and Li, Y.Q. and Song, X.M. and Nie, L.Q.",
        TITLE = "Audio-Semantic Enhanced Pose-Driven Talking Head Generation",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "11056-11069",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104910"}

@article{bb108199,
        AUTHOR = "Ahn, Y. and Chae, J. and Shin, J.W.",
        TITLE = "Text-to-Speech With Lip Synchronization Based on Speech-Assisted
Text-to-Video Alignment and Masked Unit Prediction",
        JOURNAL = SPLetters,
        VOLUME = "32",
        YEAR = "2025",
        PAGES = "961-965",
        BIBSOURCE = "http://www.visionbib.com/bibliography/describe500syncav1.html#TT104911"}