Audio processing method, device, electronic device and storage medium

Abstract

The invention discloses an audio processing method, device, electronic equipment and storage medium, belonging to the technical field of audio processing. The method includes: filtering the audio through a plurality of filters to obtain low-frequency audio, intermediate-frequency audio and first high-frequency audio, the frequency of the intermediate-frequency audio is within the frequency range of the human voice, and the maximum frequency of the low-frequency audio is less than or equal to the intermediate-frequency audio The minimum frequency of the first high-frequency audio, the minimum frequency of the first high-frequency audio is greater than or equal to the maximum frequency of the intermediate-frequency audio; the low-frequency audio and the first high-frequency audio are respectively delayed by a preset duration; for the intermediate-frequency audio, and the delayed low-frequency audio and the first The high-frequency audio is subjected to audio synthesis processing to obtain the target audio. The invention can not only enhance the clarity of the human voice in the audio, but also ensure that the original balance of the audio is not damaged, and the original signal energy of the audio is not changed.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of audio processing, and in particular, to an audio processing method, an apparatus, an electronic device, and a storage medium. Background technique [0002] The core of audio such as songs is the human voice (capella). However, at present, people often do not listen to the audio in a quiet environment, and most of them listen to it when exercising or taking a transportation. The accompaniment will weaken or even cover the vocal signal of the singer in the audio, so that the user cannot hear the singer's singing content clearly, affecting the user experience. In order to make the human voice in the audio clearer, the audio needs to be processed accordingly. [0003] At present, an equalizer is generally used to enhance the human voice in the audio. In the implementation process, Fourier transform can be performed on the audio to be processed to obtain the first spectrum signal of the...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides an audio processing method, which can solve the problem of destroying the original balance of the audio and changing the energy of the audio signal when the equalizer is used for human voice enhancement

Images