Multimedia data processing method, device, equipment and storage medium

Abstract

The embodiment of the present application discloses a multimedia data processing method, device, device, and storage medium, which relate to machine learning technology related to artificial intelligence, wherein the method includes: acquiring target audio data that matches target video data; Carrying out audio feature extraction from the data to obtain audio feature information of the target audio data; according to the audio feature information of the target audio data, performing refrain recognition on the target audio data to obtain a refrain segment of the target audio data; Extract the key video segment from the target video data, fuse the key video segment with the chorus segment of the target audio data, and obtain the chorus segment including the key video segment and the target audio data multimedia data. The application can effectively improve the acquisition efficiency and accuracy of the chorus segment, and further improve the acquisition efficiency of multimedia data.

Description

technical field [0001] The present application relates to the technical field of machine learning in artificial intelligence, and in particular to a multimedia data processing method, device, device and storage medium. Background technique [0002] With the development of Internet technology, people can record and release multimedia data (such as short videos) anytime and anywhere, and can also watch multimedia data released by others. Usually, when creating multimedia data, a user needs to select a background music that matches the theme of the video data, and then integrate the background music with the video data to obtain multimedia data. The background music can be used to strengthen the theme of the multimedia data. For example, the multimedia data is a dance video data. The rhythm of the dance can be enhanced through the background music, so that the viewer can understand the multimedia data uploaded by the user more intuitively through the background music. Theme of...

AI Technical Summary

Problems solved by technology

At present, the chorus segment of the audio data is mainly edited manually, which requires the user to edit the audio data multiple times to obtain the chorus segment of the audio data, resulting in a relatively low efficiency in obtaining the chorus segment of the audio data, and further Make the acquisition efficiency of multimedia data relatively low

At the same time, affected by the subjective feelings of the human ear, different users have certain deviations in the understanding of the chorus segment of the audio data, resulting in a relatively low accuracy of the acquired chorus segment

Images