Audio processing method and device, storage medium and terminal

Abstract

The present invention discloses an audio processing method and device, a storage medium and a terminal, and belongs to the multimedia processing technology field. The method comprises the steps of obtaining an original singer audio and an accompaniment audio of the target audio resources; according to the accompaniment audio, obtaining a voice audio in the original singer audio; calculating the first sound accompaniment loudness proportion between the voice audio and the accompaniment audio; according to the first sound accompaniment loudness proportion, calculating the second sound accompaniment loudness proportion between the accompaniment audio and a user audio performed by a user; according to the second sound accompaniment loudness proportion, carrying out the voice mixing and synthesis processing on the accompaniment audio and the user audio. According to the present invention, based on the ideal sound accompaniment loudness proportion in an original singer work, the optimal sound accompaniment loudness proportion between the voice and the accompaniment is calculated automatically during a karaok process, and further the voice mixing and synthesis are guided by the calculatedsound accompaniment loudness proportion during a subsequent process, so that the whole process does not need the labors to adjust artificially, and a finally obtained synthesis work accords with theexpectation of the users better.

Description

technical field [0001] The present invention relates to the technical field of multimedia processing, in particular to an audio processing method, device, storage medium and terminal. Background technique [0002] For a long time, karaoke has been widely sought after by users as a daily leisure and entertainment activity. Especially with the popularization of intelligent terminals such as smart phones and tablet computers, it is possible for users to perform karaoke without leaving home. For example, after a user installs karaoke software on their smartphones, they can sing songs without going into a KTV. Among them, in the k-song scene, in order to obtain k-song works including human voice and accompaniment, smart terminals often need to mix and synthesize the user audio performed by k-song users and the accompaniment audio played during k-song. [0003] In the related art, the following two methods are usually adopted to implement the mixing and synthesis processing of u...

AI Technical Summary

Problems solved by technology

[0005] For the first method, for different types or styles of songs, or even different interpretations of the same song, the ideal sound-accompanying loudness ratio is different. Therefore, if a unified sound-accompanying loudness ratio of 1:1 is adopted If mixed sound synthesis processing is performed, the synthesized audio will not meet user expectations to a large extent, so the effect of this processing method is poor

For the second method, it is more time-consuming and complicated because manual adjustment is required; in addition, for non-professional users, the adjusted sound-accompanied loudness ratio is not accurate, so this processing method also has less effect. poor defect

Images