@article{bb261400,
AUTHOR = "Shaw, F. and Theobald, B.J.",
TITLE = "Expressive Modulation of Neutral Visual Speech",
JOURNAL = MultMedMag,
VOLUME = "23",
YEAR = "2016",
NUMBER = "4",
MONTH = "October",
PAGES = "68-78",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256181"}
@article{bb261401,
AUTHOR = "Zhang, H.P. and El Gaaly, T. and Elgammal, A.M. and Jiang, Z.G.",
TITLE = "Factorization of view-object manifolds for joint object recognition
and pose estimation",
JOURNAL = CVIU,
VOLUME = "139",
YEAR = "2015",
NUMBER = "1",
PAGES = "89-103",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256182"}
@inproceedings{bb261402,
AUTHOR = "Bakry, A. and El Gaaly, T. and Elhoseiny, M. and Elgammal, A.M.",
TITLE = "Joint Object Recognition and Pose Estimation Using a Nonlinear
View-Invariant Latent Generative Model",
BOOKTITLE = WACV16,
YEAR = "2016",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256183"}
@inproceedings{bb261403,
AUTHOR = "Bakry, A. and Elgammal, A.M.",
TITLE = "Untangling Object-View Manifold for Multiview Recognition and Pose
Estimation",
BOOKTITLE = ECCV14,
YEAR = "2014",
PAGES = "IV: 434-449",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256184"}
@inproceedings{bb261404,
AUTHOR = "Bakry, A. and Elgammal, A.M.",
TITLE = "MKPLS: Manifold Kernel Partial Least Squares for Lipreading and
Speaker Identification",
BOOKTITLE = CVPR13,
YEAR = "2013",
PAGES = "684-691",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256185"}
@article{bb261405,
AUTHOR = "Butt, W.U.",
TITLE = "Speech Recognition Supported by Lip Analysis",
JOURNAL = ELCVIA,
VOLUME = "15",
YEAR = "2016",
NUMBER = "2",
PAGES = "30-32",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256186"}
@article{bb261406,
AUTHOR = "Georgakis, C. and Petridis, S. and Pantic, M.",
TITLE = "Discrimination Between Native and Non-Native Speech Using Visual
Features Only",
JOURNAL = Cyber,
VOLUME = "46",
YEAR = "2016",
NUMBER = "12",
MONTH = "December",
PAGES = "2758-2771",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256187"}
@article{bb261407,
AUTHOR = "Wei, J.G. and Zhang, J.S. and Ji, Y. and Fang, Q.A. and Lu, W.H.",
TITLE = "Morphological normalization of vowel images for articulatory speech
recognition",
JOURNAL = JVCIR,
VOLUME = "41",
YEAR = "2016",
NUMBER = "1",
PAGES = "352-360",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256188"}
@inproceedings{bb261408,
AUTHOR = "Dungan, L. and Karaali, A. and Harte, N.",
TITLE = "The Impact of Reduced Video Quality on Visual Speech Recognition",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "2560-2564",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256189"}
@article{bb261409,
AUTHOR = "Chung, J.S. and Zisserman, A.",
TITLE = "Learning to lip read words by watching videos",
JOURNAL = CVIU,
VOLUME = "173",
YEAR = "2018",
PAGES = "76-85",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256190"}
@inproceedings{bb261410,
AUTHOR = "Chung, J.S. and Zisserman, A.",
TITLE = "Lip Reading in the Wild",
BOOKTITLE = ACCV16,
YEAR = "2016",
PAGES = "II: 87-103",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256191"}
@inproceedings{bb261411,
AUTHOR = "Chung, J.S. and Senior, A. and Vinyals, O. and Zisserman, A.",
TITLE = "Lip Reading Sentences in the Wild",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "3444-3453",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256192"}
@article{bb261412,
AUTHOR = "Jha, A. and Namboodiri, V.P. and Jawahar, C.V.",
TITLE = "Spotting words in silent speech videos: a retrieval-based approach",
JOURNAL = MVA,
VOLUME = "30",
YEAR = "2019",
NUMBER = "2",
MONTH = "March",
PAGES = "217-229",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256193"}
@inproceedings{bb261413,
AUTHOR = "Jha, A. and Namboodiri, V.P. and Jawahar, C.V.",
TITLE = "Word Spotting in Silent Lip Videos",
BOOKTITLE = WACV18,
YEAR = "2018",
PAGES = "150-159",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256194"}
@article{bb261414,
AUTHOR = "Zhang, J. and Fisher, R.B.",
TITLE = "3D Visual passcode:
Speech-driven 3D facial dynamics for behaviometrics",
JOURNAL = SP,
VOLUME = "160",
YEAR = "2019",
NUMBER = "1",
MONTH = "July",
PAGES = "164-177",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256195"}
@article{bb261415,
AUTHOR = "Radha, N. and Shahina, A. and Prabha, P. and Sri Preethi, B.T. and Nayeemulla Khan, A.",
TITLE = "An analysis of the effect of combining standard and alternate sensor
signals on recognition of syllabic units for multimodal speech
recognition",
JOURNAL = PRL,
VOLUME = "115",
YEAR = "2018",
PAGES = "39-49",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256196"}
@article{bb261416,
AUTHOR = "Mesbah, A. and Berrahou, A. and Hammouchi, H. and Berbia, H. and Qjidaa, H. and Daoudi, M.",
TITLE = "Lip reading with Hahn Convolutional Neural Networks",
JOURNAL = IVC,
VOLUME = "88",
YEAR = "2019",
PAGES = "76-83",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256197"}
@article{bb261417,
AUTHOR = "Das, S. and Muhammad, K. and Bakshi, S. and Mukherjee, I. and Sa, P.K. and Sangaiah, A.K. and Bruno, A.",
TITLE = "Lip biometric template security framework using spatial steganography",
JOURNAL = PRL,
VOLUME = "126",
YEAR = "2019",
PAGES = "102-110",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256198"}
@article{bb261418,
AUTHOR = "Petridis, S. and Wang, Y.J. and Ma, P.C. and Li, Z.W. and Pantic, M.",
TITLE = "End-to-end visual speech recognition for small-scale datasets",
JOURNAL = PRL,
VOLUME = "131",
YEAR = "2020",
PAGES = "421-427",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256199"}
@article{bb261419,
AUTHOR = "Chen, X.J. and Du, J.X. and Zhang, H.B.",
TITLE = "Lipreading with DenseNet and resBi-LSTM",
JOURNAL = SIViP,
VOLUME = "14",
YEAR = "2020",
NUMBER = "5",
MONTH = "July",
PAGES = "981-989",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256200"}
@article{bb261420,
AUTHOR = "Brahme, A. and Bhadade, U.",
TITLE = "Effect of Various Visual Speech Units on Language Identification Using
Visual Speech Recognition",
JOURNAL = IJIG,
VOLUME = "20",
YEAR = "2020",
NUMBER = "4",
MONTH = "October",
PAGES = "2050029",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256201"}
@article{bb261421,
AUTHOR = "He, L. and Ding, B. and Wang, H. and Zhang, T.",
TITLE = "An Optimal 3D Convolutional Neural Network Based Lipreading Method",
JOURNAL = IET-IPR,
VOLUME = "16",
YEAR = "2022",
NUMBER = "1",
PAGES = "113-122",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256202"}
@article{bb261422,
AUTHOR = "Sheng, C.C. and Zhu, X.Z. and Xu, H.Y. and Pietikainen, M. and Liu, L.",
TITLE = "Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip
Reading",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "3545-3557",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256203"}
@article{bb261423,
AUTHOR = "Kim, M. and Hong, J. and Park, S.J. and Ro, Y.M.",
TITLE = "CroMM-VSR: Cross-Modal Memory Augmented Visual Speech Recognition",
JOURNAL = MultMed,
VOLUME = "24",
YEAR = "2022",
PAGES = "4342-4355",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256204"}
@article{bb261424,
AUTHOR = "Preethi, S.J. and Krupa, B.N.",
TITLE = "Analyzing lower half facial gestures for lip reading applications:
Survey on vision techniques",
JOURNAL = CVIU,
VOLUME = "233",
YEAR = "2023",
PAGES = "103738",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256205"}
@article{bb261425,
AUTHOR = "Sun, B.S. and Xie, D.L. and Shi, H.",
TITLE = "MALip: Modal Amplification Lipreading based on reconstructed audio
features",
JOURNAL = SP:IC,
VOLUME = "117",
YEAR = "2023",
PAGES = "117002",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256206"}
@article{bb261426,
AUTHOR = "Nemani, P. and Krishna, G.S. and Supriya, K. and Kumar, S.",
TITLE = "Speaker independent VSR: A systematic review and futuristic
applications",
JOURNAL = IVC,
VOLUME = "138",
YEAR = "2023",
PAGES = "104787",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256207"}
@article{bb261427,
AUTHOR = "Xue, F. and Li, Y. and Liu, D. and Xie, Y. and Wu, L. and Hong, R.C.",
TITLE = "LipFormer: Learning to Lipread Unseen Speakers Based on
Visual-Landmark Transformers",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "9",
MONTH = "September",
PAGES = "4507-4517",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256208"}
@article{bb261428,
AUTHOR = "Sheng, C.C. and Liu, L. and Deng, W. and Bai, L. and Liu, Z. and Lao, S.Y. and Kuang, G.Y. and Pietikainen, M.",
TITLE = "Importance-Aware Information Bottleneck Learning Paradigm for Lip
Reading",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "6563-6574",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256209"}
@article{bb261429,
AUTHOR = "Yeo, J.H. and Kim, M. and Choi, J. and Kim, D.H. and Ro, Y.M.",
TITLE = "AKVSR: Audio Knowledge Empowered Visual Speech Recognition by
Compressing Audio Knowledge of a Pretrained Model",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "6462-6474",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256210"}
@article{bb261430,
AUTHOR = "Sheng, C.C. and Kuang, G.Y. and Bai, L. and Hou, C.P. and Guo, Y.L. and Xu, X. and Pietikainen, M. and Liu, L.",
TITLE = "Deep Learning for Visual Speech Analysis: A Survey",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "9",
MONTH = "September",
PAGES = "6001-6022",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256211"}
@article{bb261431,
AUTHOR = "Xiao, Y.W. and Liu, X.M. and Teng, L. and Zhu, A. and Tian, P. and Huang, J.",
TITLE = "Cantonese sentence dataset for lip-reading",
JOURNAL = IET-IPR,
VOLUME = "18",
YEAR = "2024",
NUMBER = "10",
PAGES = "2645-2664",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256212"}
@article{bb261432,
AUTHOR = "Chen, H. and Wang, Q. and Du, J. and Wan, G.S. and Xiong, S.F. and Yin, B.C. and Pan, J. and Lee, C.H.",
TITLE = "Collaborative Viseme Subword and End-to-End Modeling for Word-Level
Lip Reading",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "9358-9371",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256213"}
@inproceedings{bb261433,
AUTHOR = "King, S. and Ebraheem, M. and Dang, P. and Neal, T.",
TITLE = "Toward Emotion Recognition and Person Identification Using Lip
Movement from Wireless Signals: A Preliminary Study",
BOOKTITLE = FG24,
YEAR = "2024",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256214"}
@inproceedings{bb261434,
AUTHOR = "Varshney, M. and Mukherji, M. and G, S.R. and Ganesh, A. and Banerjee, K.",
TITLE = "Lip and Speech Synchronization using Supervised Contrastive Learning
and Cross-Modal Attention",
BOOKTITLE = FG24,
YEAR = "2024",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256215"}
@inproceedings{bb261435,
AUTHOR = "Djilali, Y.A.D. and Narayan, S. and Le Bihan, E. and Boussaid, H. and Almazrouei, E. and Debbah, M.",
TITLE = "Do VSR Models Generalize Beyond LRS3?",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "6621-6630",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256216"}
@inproceedings{bb261436,
AUTHOR = "Arakane, T. and Kai, C. and Saitoh, T.",
TITLE = "Can you read lips with a masked face?",
BOOKTITLE = MVA23,
YEAR = "2023",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256217"}
@inproceedings{bb261437,
AUTHOR = "Kim, M. and Yeo, J.H. and Choi, J. and Ro, Y.M.",
TITLE = "Lip Reading for Low-resource Languages by Learning and Combining
General Speech Knowledge and Language-specific Knowledge",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15313-15325",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256218"}
@inproceedings{bb261438,
AUTHOR = "Cascone, L. and Nappi, M. and Narducci, F.",
TITLE = "Language Identification as Improvement for Lip-Based Biometric Visual
Systems",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1570-1574",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256219"}
@inproceedings{bb261439,
AUTHOR = "Hu, Z.K. and Cheung, Y.M. and Li, M. and Lan, W.C.",
TITLE = "Few-Shot Lip-Password Based Speaker Verification",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "1960-1964",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256220"}
@inproceedings{bb261440,
AUTHOR = "Liu, X. and Lakomkin, E. and Vougioukas, K. and Ma, P.C. and Chen, H.L. and Xie, R.M. and Doulaty, M. and Moritz, N. and Kolar, J. and Petridis, S. and Pantic, M. and Fuegen, C.",
TITLE = "SynthVSR: Scaling Up Visual Speech Recognition With Synthetic
Supervision",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18806-18815",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256221"}
@inproceedings{bb261441,
AUTHOR = "Bulzomi, H. and Schweiker, M. and Gruel, A. and Martinet, J.",
TITLE = "End-to-end Neuromorphic Lip Reading",
BOOKTITLE = EventVision23,
YEAR = "2023",
PAGES = "4101-4108",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256222"}
@inproceedings{bb261442,
AUTHOR = "Wang, J. and Qian, X.Y. and Zhang, M. and Tan, R.T. and Li, H.Z.",
TITLE = "Seeing What You Said: Talking Face Generation Guided by a Lip Reading
Expert",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14653-14662",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256223"}
@inproceedings{bb261443,
AUTHOR = "Vajpayee, A. and Zhang, Z.K. and Jain, A. and Bhat, V.",
TITLE = "A Simple and Efficient method for Dubbed Audio Sync Detection using
Compressive Sensing",
BOOKTITLE = VAQuality23,
YEAR = "2023",
PAGES = "565-572",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256224"}
@inproceedings{bb261444,
AUTHOR = "Kim, M. and Kim, H. and Ro, Y.M.",
TITLE = "Speaker-Adaptive Lip Reading with User-Dependent Padding",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXVI:576-593",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256225"}
@inproceedings{bb261445,
AUTHOR = "Ma, X.H. and Wang, S.L.",
TITLE = "Chinese Mandarin Lipreading using Cascaded Transformers with Multiple
Intermediate Representations",
BOOKTITLE = ICIP22,
YEAR = "2022",
PAGES = "2561-2565",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256226"}
@inproceedings{bb261446,
AUTHOR = "Tan, G. and Wang, Y. and Han, H. and Cao, Y. and Wu, F. and Zha, Z.J.",
TITLE = "Multi-grained Spatio-Temporal Features Perceived Network for
Event-based Lip-Reading",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "20062-20071",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256227"}
@inproceedings{bb261447,
AUTHOR = "Prajwal, K.R. and Afouras, T. and Zisserman, A.",
TITLE = "Sub-word Level Lip Reading With Visual Attention",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "5152-5162",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256228"}
@inproceedings{bb261448,
AUTHOR = "Zhang, J. and Fisher, R.B.",
TITLE = "3D Lip Event Detection via Interframe Motion Divergence at Multiple
Temporal Resolutions",
BOOKTITLE = "3DV21",
YEAR = "2021",
PAGES = "423-431",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256229"}
@inproceedings{bb261449,
AUTHOR = "Zhang, Q. and Wang, S.L. and Chen, G.L.",
TITLE = "Speaker-Independent Lipreading By Disentangled Representation
Learning",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "2493-2497",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256230"}
@inproceedings{bb261450,
AUTHOR = "Lahiri, A. and Kwatra, V. and Frueh, C. and Lewis, J. and Bregler, C.",
TITLE = "LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces
from Video using Pose and Lighting Normalization",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "2754-2763",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256231"}
@inproceedings{bb261451,
AUTHOR = "Ren, S. and Du, Y. and Lv, J.M. and Han, G.Q. and He, S.F.",
TITLE = "Learning from the Master: Distilling Cross-modal Advanced Knowledge
for Lip Reading",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "13320-13328",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256232"}
@inproceedings{bb261452,
AUTHOR = "Shirakata, T. and Saitoh, T.",
TITLE = "Japanese Sentence Dataset for Lip- reading",
BOOKTITLE = MVA21,
YEAR = "2021",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256233"}
@inproceedings{bb261453,
AUTHOR = "Ma, P.C. and Wang, Y.J. and Shen, J. and Petridis, S. and Pantic, M.",
TITLE = "Lip-reading with Densely Connected Temporal Convolutional Networks",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "2856-2865",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256234"}
@inproceedings{bb261454,
AUTHOR = "Shahid, M. and Beyan, C. and Murino, V.",
TITLE = "S-VVAD: Visual Voice Activity Detection by Motion Segmentation",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "2331-2340",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256235"}
@inproceedings{bb261455,
AUTHOR = "Wang, J.R. and Wu, T. and Wang, S.Y. and Yu, M. and Fang, Q. and Zhang, J. and Liu, L.",
TITLE = "Three-Dimensional Lip Motion Network for Text-Independent Speaker
Recognition",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "3380-3387",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256236"}
@inproceedings{bb261456,
AUTHOR = "Tzirakis, P. and Papaioannou, A. and Lattas, A. and Tarasiou, M. and Schuller, B. and Zafeiriou, S.",
TITLE = "Synthesising 3D Facial Motion from 'In-the-Wild' Speech",
BOOKTITLE = FG20,
YEAR = "2020",
PAGES = "265-272",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256237"}
@inproceedings{bb261457,
AUTHOR = "Luo, M. and Yang, S. and Shan, S. and Chen, X.",
TITLE = "Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence
Lip-Reading",
BOOKTITLE = FG20,
YEAR = "2020",
PAGES = "273-280",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256238"}
@inproceedings{bb261458,
AUTHOR = "Zhang, Y. and Yang, S. and Xiao, J. and Shan, S. and Chen, X.",
TITLE = "Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep
Visual Speech Recognition",
BOOKTITLE = FG20,
YEAR = "2020",
PAGES = "356-363",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256239"}
@inproceedings{bb261459,
AUTHOR = "Xiao, J. and Yang, S. and Zhang, Y. and Shan, S. and Chen, X.",
TITLE = "Deformation Flow Based Two-Stream Network for Lip Reading",
BOOKTITLE = FG20,
YEAR = "2020",
PAGES = "364-370",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256240"}
@inproceedings{bb261460,
AUTHOR = "Zhao, X. and Yang, S. and Shan, S. and Chen, X.",
TITLE = "Mutual Information Maximization for Effective Lip Reading",
BOOKTITLE = FG20,
YEAR = "2020",
PAGES = "420-427",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256241"}
@inproceedings{bb261461,
AUTHOR = "Ma, J. and Wang, S. and Zhang, A. and Liew, A.W.C.",
TITLE = "Feature Extraction For Visual Speaker Authentication Against
Computer-Generated Video Attacks",
BOOKTITLE = ICIP20,
YEAR = "2020",
PAGES = "1326-1330",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256242"}
@inproceedings{bb261462,
AUTHOR = "Yang, C. and Wang, S. and Zhang, X. and Zhu, Y.",
TITLE = "Speaker-Independent Lipreading With Limited Data",
BOOKTITLE = ICIP20,
YEAR = "2020",
PAGES = "2181-2185",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256243"}
@inproceedings{bb261463,
AUTHOR = "Prajwal, K.R. and Mukhopadhyay, R. and Namboodiri, V.P. and Jawahar, C.V.",
TITLE = "Learning Individual Speaking Styles for Accurate Lip to Speech
Synthesis",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "13793-13802",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256244"}
@inproceedings{bb261464,
AUTHOR = "Zhang, X. and Cheng, F. and Shilin, W.",
TITLE = "Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip
Reading",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "713-722",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256245"}
@inproceedings{bb261465,
AUTHOR = "Ivanko, D. and Ryumin, D. and Karpov, A.",
TITLE = "Automatic Lip-reading of Hearing Impaired People",
BOOKTITLE = PTVSBB19,
YEAR = "2019",
PAGES = "97-101",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256246"}
@inproceedings{bb261466,
AUTHOR = "Sharma, R. and Somandepalli, K. and Narayanan, S.",
TITLE = "Toward Visual Voice Activity Detection for Unconstrained Videos",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "2991-2995",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256247"}
@inproceedings{bb261467,
AUTHOR = "Mattos, A.B. and Borges Oliveira, D.A. and da Silva Morais, E.",
TITLE = "Towards View-Independent Viseme Recognition Based on CNNS and
Synthetic Data",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "589-593",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256248"}
@inproceedings{bb261468,
AUTHOR = "Spyridonos, P. and Saint, A.F. and Likas, A. and Gaitanis, G. and Bassukas, I.",
TITLE = "Multi-Threshold LIP Contour Detection",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "1912-1916",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256249"}
@inproceedings{bb261469,
AUTHOR = "Sterpu, G. and Saam, C. and Harte, N.",
TITLE = "Can DNNs Learn to Lipread Full Sentences?",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "16-20",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256250"}
@inproceedings{bb261470,
AUTHOR = "Xu, K. and Li, D. and Cassimatis, N. and Wang, X.",
TITLE = "LCANet: End-to-End Lipreading with Cascaded Attention-CTC",
BOOKTITLE = FG18,
YEAR = "2018",
PAGES = "548-555",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256251"}
@inproceedings{bb261471,
AUTHOR = "Sadoughi, N. and Busso, C.",
TITLE = "Expressive Speech-Driven Lip Movements with Multitask Learning",
BOOKTITLE = FG18,
YEAR = "2018",
PAGES = "409-415",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256252"}
@inproceedings{bb261472,
AUTHOR = "Ryumin, D. and Karpov, A.A.",
TITLE = "Parametric Representation of the Speaker's Lips for Multimodal Sign
Language And Speech Recognition",
BOOKTITLE = PTVSBB17,
YEAR = "2017",
PAGES = "155-161",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256253"}
@inproceedings{bb261473,
AUTHOR = "Han, H. and Kang, S. and Yoo, C.D.",
TITLE = "Multi-view visual speech recognition based on multi task learning",
BOOKTITLE = ICIP17,
YEAR = "2017",
PAGES = "3983-3987",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256254"}
@inproceedings{bb261474,
AUTHOR = "Rahmani, M.H. and Almasganj, F.",
TITLE = "Lip-reading via a DNN-HMM hybrid system using combination of the
image-based and model-based features",
BOOKTITLE = IPRIA17,
YEAR = "2017",
PAGES = "195-199",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256255"}
@inproceedings{bb261475,
AUTHOR = "Ra, R. and Aihara, R. and Takiguchi, T. and Ariki, Y.",
TITLE = "Visual-to-speech conversion based on maximum likelihood estimation",
BOOKTITLE = MVA17,
YEAR = "2017",
PAGES = "518-521",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256256"}
@inproceedings{bb261476,
AUTHOR = "Iwasaki, M. and Kubokawa, M. and Saitoh, T.",
TITLE = "Two features combination with gated recurrent unit for visual speech
recognition",
BOOKTITLE = MVA17,
YEAR = "2017",
PAGES = "326-329",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256257"}
@inproceedings{bb261477,
AUTHOR = "Wielgat, R. and Mik, L. and Lorenc, A. and Truchan, A. and Szostek, M.",
TITLE = "Choice of optimal measurement conditions for calculating the
correlation between EMA sensor and video marker position coordinates
in electromagnetic articulography",
BOOKTITLE = WSSIP17,
YEAR = "2017",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256258"}
@inproceedings{bb261478,
AUTHOR = "Fernandez Lopez, A. and Martinez, O. and Sukno, F.M.",
TITLE = "Towards Estimating the Upper Bound of Visual-Speech Recognition:
The Visual Lip-Reading Feasibility Database",
BOOKTITLE = FG17,
YEAR = "2017",
PAGES = "208-215",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256259"}
@inproceedings{bb261479,
AUTHOR = "Spetlik, R. and Cech, J. and Franc, V. and Matas, J.G.",
TITLE = "Visual Language Identification from Facial Landmarks",
BOOKTITLE = SCIA17,
YEAR = "2017",
PAGES = "II: 389-400",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256260"}
@inproceedings{bb261480,
AUTHOR = "Zimmermann, M. and Ghazi, M.M. and Ekenel, H.K. and Thiran, J.P.",
TITLE = "Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem
GMM-HMM System",
BOOKTITLE = LipRead16,
YEAR = "2016",
PAGES = "II: 264-276",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256261"}
@inproceedings{bb261481,
AUTHOR = "Lee, D. and Lee, J.M. and Kim, K.E.",
TITLE = "Multi-view Automatic Lip-Reading Using Neural Network",
BOOKTITLE = LipRead16,
YEAR = "2016",
PAGES = "II: 290-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256262"}
@inproceedings{bb261482,
AUTHOR = "Watanabe, T. and Katsurada, K. and Kanazawa, Y.S.",
TITLE = "Lip Reading from Multi View Facial Images Using 3D-AAM",
BOOKTITLE = LipRead16,
YEAR = "2016",
PAGES = "II: 303-316",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256263"}
@inproceedings{bb261483,
AUTHOR = "Shi, X.X. and Wang, S.L. and Lai, J.Y.",
TITLE = "Visual speaker authentication by ensemble learning over static and
dynamic lip details",
BOOKTITLE = ICIP16,
YEAR = "2016",
PAGES = "3942-3946",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256264"}
@inproceedings{bb261484,
AUTHOR = "Aung, Z.H. and Ritthipravat, P.",
TITLE = "Robust Visual Voice Activity Detection Using Long Short-Term Memory
Recurrent Neural Network",
BOOKTITLE = PSIVT15,
YEAR = "2015",
PAGES = "380-391",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256265"}
@inproceedings{bb261485,
AUTHOR = "Patrona, F. and Iosifidis, A. and Tefas, A. and Nikolaidis, N. and Pitas, I.",
TITLE = "Visual voice activity detection based on spatiotemporal information
and bag of words",
BOOKTITLE = ICIP15,
YEAR = "2015",
PAGES = "2334-2338",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256266"}
@inproceedings{bb261486,
AUTHOR = "Liu, H. and Zhang, X.W. and Wu, P.P.",
TITLE = "Two-Level Multi-Task Metric Learning with Application to
Multi-Classification",
BOOKTITLE = ICIP15,
YEAR = "2015",
PAGES = "2756-2760",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256267"}
@inproceedings{bb261487,
AUTHOR = "Liu, H. and Zhang, X. and Wu, P.P.",
TITLE = "Regression based landmark estimation and multi-feature fusion for
visual speech recognition",
BOOKTITLE = ICIP15,
YEAR = "2015",
PAGES = "808-812",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256268"}
@inproceedings{bb261488,
AUTHOR = "Anina, I. and Zhou, Z.H. and Zhao, G.Y. and Pietikainen, M.",
TITLE = "OuluVS2: A multi-view audiovisual database for non-rigid mouth motion
analysis",
BOOKTITLE = FG15,
YEAR = "2015",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256269"}
@inproceedings{bb261489,
AUTHOR = "Antonakos, E. and Roussos, A. and Zafeiriou, S.P.",
TITLE = "A survey on mouth modeling and analysis for Sign Language recognition",
BOOKTITLE = FG15,
YEAR = "2015",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256270"}
@inproceedings{bb261490,
AUTHOR = "Shiraishi, J. and Saitoh, T.",
TITLE = "Optical flow based lip reading using non rectangular ROI and head
motion reduction",
BOOKTITLE = FG15,
YEAR = "2015",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256271"}
@inproceedings{bb261491,
AUTHOR = "Ichino, M. and Yamazaki, Y.S. and Jian Gang, W. and Yun, Y.W.",
TITLE = "Text independent speaker gender recognition using lip movement",
BOOKTITLE = ICARCV12,
YEAR = "2012",
PAGES = "176-181",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256272"}
@inproceedings{bb261492,
AUTHOR = "Bear, H.L. and Harvey, R.W. and Theobald, B.J. and Lan, Y.X.",
TITLE = "Resolution limits on visual speech recognition",
BOOKTITLE = ICIP14,
YEAR = "2014",
PAGES = "1371-1375",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256273"}
@inproceedings{bb261493,
AUTHOR = "Bear, H.L. and Harvey, R.W. and Theobald, B.J. and Lan, Y.X.",
TITLE = "Which Phoneme-to-Viseme Maps Best Improve Visual-Only Computer
Lip-Reading?",
BOOKTITLE = ISVC14,
YEAR = "2014",
PAGES = "II: 230-239",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256274"}
@inproceedings{bb261494,
AUTHOR = "Sad, G.D. and Reyes, F. and Alvarez, J.",
TITLE = "Asymmetric 3D face model for Speech Language Pathologist applications",
BOOKTITLE = FG21,
YEAR = "2021",
PAGES = "01-08",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256275"}
@inproceedings{bb261495,
AUTHOR = "Sad, G.D. and Terissi, L.D. and Gomez, J.C.",
TITLE = "Decision Level Fusion for Audio-Visual Speech Recognition in Noisy
Conditions",
BOOKTITLE = CIARP16,
YEAR = "2016",
PAGES = "360-367",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256276"}
@inproceedings{bb261496,
AUTHOR = "Sad, G.D. and Terissi, L.D. and Gomez, J.C.",
TITLE = "Class Confusability Reduction in Audio-Visual Speech Recognition Using
Random Forests",
BOOKTITLE = CIARP17,
YEAR = "2017",
PAGES = "584-592",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256277"}
@inproceedings{bb261497,
AUTHOR = "Terissi, L.D. and Sad, G.D. and Gomez, J.C. and Parodi, M.",
TITLE = "Audio-Visual Speech Recognition Scheme Based on Wavelets and Random
Forests Classification",
BOOKTITLE = CIARP15,
YEAR = "2015",
PAGES = "567-574",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256278"}
@inproceedings{bb261498,
AUTHOR = "Terissi, L.D. and Parodi, M. and Gomez, J.C.",
TITLE = "Lip Reading Using Wavelet-Based Features and Random Forests
Classification",
BOOKTITLE = ICPR14,
YEAR = "2014",
PAGES = "791-796",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256279"}
@inproceedings{bb261499,
AUTHOR = "Rekik, A. and Ben Hamadou, A. and Mahdi, W.",
TITLE = "A New Visual Speech Recognition Approach for RGB-D Cameras",
BOOKTITLE = ICIAR14,
YEAR = "2014",
PAGES = "II: 21-28",
BIBSOURCE = "http://www.visionbib.com/bibliography/people915.html#TT256280"}
Last update:Sep 28, 2024 at 17:47:54