Review of the lip-reading recognition

As an important component of the future HumanComputer Interface, Automatic Speech Recognition is designed for the purpose of realizing identification recognition and natural language comprehension by means of human voice. Speech recognition technology has acquired significant achievements with some successful popularity and applications. IBM's ViaVoice system, for instance, has good performances when the vocabulary pool is small and when the noise is low. But its performance will be greatly degraded when used in real application environments. In future applications of the humancomputer interaction, such as in a car, at airport, or live interviews, higher requirements for robust systems will be needed, therefore we need to explore new ways. Proved highly effective by most researchers, the combination of visual features of lip motion with vocal features can raise the recognition rate of the automatic speech system, and make it more robust and more adaptable to real environments. This focuses on the recognition methods and speech and visual fusion algorithm, which aims to attract more researchers to be interested and concerned in this area of research.