Animated image driving method based on artificial intelligence, and related devices

摘要

An animation image driving method and related devices based on artificial intelligence. The method includes: collecting media data of facial expression changes when a speaker speaks a voice, and determining a first facial expression base of a first animated image corresponding to the speaker, wherein the first facial expression base determines different facial expressions of the first animated image can reflect -; after the target text information used for driving the second animated image is determined, determining an acoustic characteristic and a target facial expression parameter corresponding to the target text information according to the target text information, the collected media data and the first facial expression base; and driving the second animated image having the second facial expression base by the acoustic characteristic and the target facial expression parameter, so that the second animated image can provide a sound of the target text information spoken by the speaker by the acoustic characteristic simulation, , a facial expression matching the appropriate expression of the speaker is performed in the sounding process, so that a vivid sense of substitution and immersion is delivered to the user, and the interaction experience between the user and the animated image is improved.