Extraction of Visual Features for Lipreading

By Iain Matthews, Tim Cootes, J. Andrew Bangham, Stephen J. Cox, Richard Harvey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

597 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f78867834f7f6797ca6396f98edb10aad2a864fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

2D vs. 3D Deformable Face Models: Representational Power, Construction, and Real-Time Fitting (2007, background): “Other applications include lip-reading (Matthews et al., 2002) and gaze estimation (Ishikawa et al., 2004).”
Multimodal Transfer Deep Learning with Applications in Audio-Visual Recognition (2014, background): “The AV-Letters dataset ([14]) consists of both audio and lip-reading video data of 10 speakers saying the letters A to Z (thus 26 labels), three times each.”
Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition (2009, background): “We have shown that it is partly justified in the constant and modelaligned errors case; otherwise, one should use the more general rules in (16).”
LipNet: End-to-End Sentence-level Lipreading (2016, background): “…temporal preprocessing of frames to extract video features (e.g., optical ﬂow or movement detection), or other types of handcrafted vision pipelines (Matthews et al., 2002; Zhao et al., 2009; Gurban & Thiran, 2009; Papandreou et al., 2007; 2009; Pitsikalis et al., 2006; Lucey & Sridharan, 2006;…”
Lip Reading in the Wild (2016, background): “4%, which exceeds state-of-the-art [7, 43] on multiple datasets [19, 22] that have lexicon sizes that are orders of magnitude smaller, and a top-10 accuracy of 92.”
Large-Scale Visual Speech Recognition (2018, methodology): “D WORK While there is a large body of literature on automated lipreading, much of the early work focused on single-word classiﬁcation and relied on substantial prior knowledge (Chu & Huang, 2000; Matthews et al., 2002; Pitsikalis et al., 2006; Lucey & Sridharan, 2006; Papandreou et al., 2007”
Multimodal Deep Learning (2011, methodology): “8% Multiscale Spatial Analysis [16] 44.”
Data Fusion and Multicue Data Matching by Diffusion Maps (2006, methodology): “linear algorithms such as the PCA and SVD subspace projections [35], [34].”
Audio-visual speech recognition using deep learning (2014, background): “In previous studies, several different approaches have been proposed for extracting visual features from input images [24, 34].”
Learning to lip read words by watching videos (2018, background): “9% [15] AVLetter [16] Lab Alphabet I 26 10 43.”