Although the TV series "Rapids" has ushered in a grand finale, its popularity has not diminished. Some netizens use the characters in the play to create entertainment videos, and some netizens edit the wonderful clips. However, some "more serious" netizens found that the voice and mouth patterns of some characters in "Rapids" did not match, so they wanted to use artificial intelligence to recognize lip language and restore the original script plot. However, AI lip-reading is not only used to decipher "hidden plot". According to statistics, there are more than 20.54 million people with hearing disabilities in China. In addition to the main sign language communication, lip reading is also an important way of communication for them. However, the artificial interpretation of lip language is easily affected by personal experience, visual perception ability, language understanding ability and other factors, and the accuracy is not satisfactory. So people began to try to use AI technology to interpret lip language. More than lip language experts, they understand lip language. "The so-called AI lip-reading, that is, artificial intelligence lip language recognition, whose core technical framework is visual recognition and natural language processing, Input it into the lip recognition model to identify the pronunciation corresponding to the figure's mouth shape, and then output the most likely expression sentence. "Visual recognition and natural language processing have a huge technical system and different technical routes, but in essence, they train AI models through a large amount of lip language data to strive for the accuracy of text output." Yan Huaizhi added. In recent years, more and more AI giants have begun to make attempts on the lip recognition track. Deep Mind, a subsidiary of Google, has developed an AI lip-reading software in cooperation with the University of Oxford in the United Kingdom to train its lip-reading ability by allowing AI lip-reading software to "watch" thousands of hours of television programs. Interestingly, in the lip-reading test of randomly selected 200 video clips, the accuracy rate of AI lip-reading software reached 46.8%, while the accuracy rate of professionally trained human lip-reading experts was only 12.4%. Why can AI lip-reading rise quietly? Yan Huaizhi gave his own analysis: first, strong demand traction, and second, huge technology drive. From the perspective of demand-driven, lip recognition can not only provide convenience for some disabled people, but also play a huge role in many fields such as public security; From the perspective of technology promotion, AI algorithm, computing power and data bottlenecks have been constantly broken, making it a reality that AI technology has achieved great success in the field of lip recognition. Many problems need to be solved, however, Yan Huaizhi also said that at present, China's AI lip recognition technology is still in its infancy, and there is still a long way to go if we want to use AI to accurately recognize lip language. From the perspective of language itself, human language has a high complexity. Of all the phonetic symbols involved in human speech, only about 30% are directly controlled by human lips, and 70% are tooth sounds, tongue sounds and throat sounds that are difficult to distinguish by the naked eye, even machine vision. Besides, the tone, dialect