Sound changing method, device, equipment and medium

Abstract

The invention provides a sound changing method and device, equipment and a medium, and relates to the technical field of computers, and the sound changing method comprises the steps: determining a target fundamental frequency offset and target sound changing parameters corresponding to an initial audio according to a target sound changing audio corresponding to the initial audio, wherein the target sound changing parameters comprise a target filtering parameter and a target equalization parameter; filtering the initial audio according to the target filtering parameter to obtain a first audio; based on the target fundamental frequency offset, carrying out fundamental frequency conversion processing on the first audio to obtain a second audio; and performing equalization processing on the second audio according to the target equalization parameter to obtain a target sound changing audio. According to the scheme, sharp noise and depressed sound after sound changing can be suppressed, and therefore the sound changing performance is improved.

Description

technical field [0001] The present disclosure relates to the technical field of computers, and in particular to a voice changing method, device, equipment and medium. Background technique [0002] This section is intended to provide a background or context for implementations of the disclosure that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Voice changing is an audio signal processing technology. By changing the fundamental frequency of the voice signal, suppressing or enhancing certain frequency components, adding reverberation, etc., some special sound changing effects can be obtained, such as male and female voices, mature, horror, robot Wait for the sound effect. Among them, changing the fundamental frequency of the voice signal can significantly change the characteristic information of the voice. Therefore, most sound changing effects need to first perform fundamental frequency conversion,...

AI Technical Summary

Problems solved by technology

[0004] The current fundamental frequency conversion method, when the fundamental frequency offset of the speech signal is large, is likely to cause sharp noise and dull sound to the voice after the voice change, resulting in poor voice change performance

For example, when the fundamental frequency offset is shifted upwards, high-frequency components are likely to produce sharp noise; when the fundamental frequency offset is shifted downwards, low-frequency components are prone to dull sounds

Images