Video processing method, device, system, terminal equipment and storage medium

Abstract

The embodiment of the present application discloses a video processing method, device, terminal equipment and storage medium. The method includes: acquiring a video to be processed; acquiring a target audio segment and a face image sequence in the video to be processed; performing emotion analysis on the face image sequence to obtain emotional features; performing speech analysis on the target audio segment to obtain sentence features, sentence The features are used to characterize the keywords in the target audio clip; based on the emotional features and sentence features, determine the reply content and the performance behavior of the virtual character; generate and output the reply video for the video to be processed, the reply video contains the voice content corresponding to the reply content and Avatars that perform performative actions. The embodiment of the present application can obtain the character's emotional features and sentence features according to the character's speaking video, and generate a virtual character video matching the emotional features and sentence features as a reply, so as to improve the realism and naturalness of human-computer interaction.

Description

technical field [0001] The embodiments of the present application relate to the technical field of human-computer interaction, and more particularly, to a video processing method, apparatus, system, terminal device, and storage medium. Background technique [0002] With the development of artificial intelligence-related technologies, the functions of robot customer service are getting stronger and stronger, and more and more scenarios can be applied, which greatly improves the efficiency of customer service and saves human resources. However, most of the current robot customer service chats with users through text, the interaction method is relatively simple, and the accuracy of semantic understanding is not high. And although some robot customer service can have "face-to-face communication" with users, their expressions are more mechanical and lack vividness, which greatly reduces the user experience. SUMMARY OF THE INVENTION [0003] In view of the above problems, the e...

AI Technical Summary

Problems solved by technology

However, the current robot customer service mostly communicates with users through text, the interaction method is relatively simple, and the accuracy of semantic understanding is not high

Although some robot customer service can communicate with users face-to-face, their facial expressions are relatively mechanical and lack vividness, which greatly reduces the user experience.

Images