ANIMATION IMAGE DRIVING METHOD BASED ON ARTIFICIAL INTELLIGENCE, AND RELATED DEVICE

• Main Authors: ZHU, Zhantu, WANG, Sheng, JI, Xing, TUO, Deyi, BAO, Linchao, KANG, Shiyin, LIN, Xiangkai, LEI, Kuongchi, LIU, Peng
• Format: Patent
• Language: English; French; German
• Published: 29.12.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

An animation image driving method based on artificial intelligence, and a related device. The method comprises: collecting media data of facial expression changes when a speaker speaks a speech, and determining a first expression base of a first animation image corresponding to the speaker, wherein the first expression base can reflect different expressions of the first animation image; after target text information used for driving a second animation image is determined, determining an acoustic feature and a target expression parameter corresponding to the target text information according to the target text information, the collected media data and the first expression base; and driving the second animation image having a second expression base by means of the acoustic feature and the target expression parameter, so that the second animation image can give out the sound of the target text information spoken by the speaker by means of acoustic feature simulation, and a facial expression conforming to the due expression of the speaker is made in a sounding process, so that vivid substitution feeling and immersion feeling are brought to a user, and the interaction experience of the user and the animation image is improved.