查看文章

Lip reading is a skill of determining a person’s words by watching lip movements without having heard the sound, or in other words it is a method of determining speech by looking at the movements of the lips. Audio visual speech recognition (AVSR) is an approach that uses imageprocessing abilities in lip-reading to assist speech recognition systems. It is combination of both audio part and visual part, which implies integration of both lip-reading and speech recognition processes working separately. In this paper, we go through different methods of lip reading and discuss the steps involved in lip reading which includes face detection, lip localization followed by feature extraction and recognition. Audio-visual speech recognition is helpful in an area having audio noise. We look out for performance of hybrid models used for AVSR and trace out the limitations of different approaches which may be helpful for further research in this field. We compare and analyze with various databases of AVSR and their functions, and also discuss the challenges faced, and extend our perceptivity into direction of future research for different types of lip-reading.