Coupled hidden Markov model (CHMM) for continuous audiovisual speech recognition

摘要

A method for speech recognition from both audio and visual information is described, which involves a coupled hidden Markov model that intertwines stochastic models for both the speech audio and image signals. It is a relatively straightforward method of coupling the two data streams into a single stochastic model, the results of which are shown in the figure.—SAF