Real-time lip tracking for audio-visual speech recognition applications Export

@incollection{citeulike:3064535, abstract = {Developments in dynamic contour tracking permit sparse representation of the outlines of moving contours. Given the increasing computing power of general-purpose workstations it is now possible to track human faces and parts of faces in real-time without special hardware. This paper describes a real-time lip tracker that uses a Kalman filter based dynamic contour to track the outline of the lips. Two alternative lip trackers, one that tracks lips from a profile view and the other from a frontal view, were developed to extract visual speech recognition features from the lip contour. In both cases, visual features have been incorporated into an acoustic automatic speech recogniser. Tests on small isolated-word vocabularies using a dynamic time warping based audio-visual recogniser demonstrate that real-time, contour-based lip tracking can be used to supplement acoustic-only speech recognisers enabling robust recognition of speech in the presence of acoustic noise.}, author = {Kaucic, Robert and Dalton, Barney and Blake, Andrew}, citeulike-article-id = {3064535}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/3-540-61123-1_154}, citeulike-linkout-1 = {http://www.springerlink.com/content/fu4n813157qu153g}, doi = {10.1007/3-540-61123-1_154}, journal = {Computer Vision — ECCV '96}, keywords = {avsr, lip\_tracking}, pages = {376--387}, posted-at = {2009-10-26 03:26:05}, priority = {0}, title = {Real-time lip tracking for audio-visual speech recognition applications}, url = {http://dx.doi.org/10.1007/3-540-61123-1_154}, year = {1996} }

TY - CHAP ID - citeulike:3064535 L3 - citeulike-article-id:3064535 N2 - Developments in dynamic contour tracking permit sparse representation of the outlines of moving contours. Given the increasing computing power of general-purpose workstations it is now possible to track human faces and parts of faces in real-time without special hardware. This paper describes a real-time lip tracker that uses a Kalman filter based dynamic contour to track the outline of the lips. Two alternative lip trackers, one that tracks lips from a profile view and the other from a frontal view, were developed to extract visual speech recognition features from the lip contour. In both cases, visual features have been incorporated into an acoustic automatic speech recogniser. Tests on small isolated-word vocabularies using a dynamic time warping based audio-visual recogniser demonstrate that real-time, contour-based lip tracking can be used to supplement acoustic-only speech recognisers enabling robust recognition of speech in the presence of acoustic noise. JF - Computer Vision — ECCV '96 EP - 387 TI - Real-time lip tracking for audio-visual speech recognition applications SP - 376 KW - avsr KW - lip_tracking AU - Kaucic, Robert AU - Dalton, Barney AU - Blake, Andrew PY - 1996/// UR - http://dx.doi.org/10.1007/3-540-61123-1_154 ER -