Extraction of Visual Features for Lipreading
IEEE Transactions on Pattern Analysis and Machine Intelligence
A new manifold representation for visual speech recognition
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
| Hi-index | 0.00 |
Systems that attempt to recover the spoken word from image sequences usually require complicated models of the mouth and its motions. Here we describe a new approach based on a fast mathematical morphology transform called the sieve. We form statistics of scale measurements in one and two dimensions and these are used as a feature vector for standard Hidden Markov Models (HMMs).