Audio coding method and device, computer equipment and medium

Abstract

The invention relates to an audio coding method and device, computer equipment and a medium, and belongs to the technical field of audio and video. The method comprises the following steps: acquiring audio characteristic parameters corresponding to each audio frame in an original audio; inputting the audio characteristic parameters into a coding rate prediction model to obtain audio coding rates output by the coding rate prediction model, wherein different audio characteristic parameters correspond to different audio coding rates; and performing voice coding on the audio frames based on the audio coding rate, and generating target audio data based on a coding result corresponding to each audio frame. By analyzing the audio characteristic parameters corresponding to each audio frame in the original audio, the purpose of dynamically regulating and controlling the audio coding rate based on the audio characteristic parameters is realized, a relatively suitable audio coding rate can be determined for each audio frame, and the coding quality of the whole audio is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of audio and video technologies, and in particular, to an audio coding method, device, computer equipment and media. Background technique [0002] Speech coding technology refers to the redundant analysis and compression of the original lossless audio signal collected through the audio model in the time domain and frequency domain, thereby reducing the voice transmission bandwidth and storage space while maintaining good audio quality. The input parameters of a general speech coder include: sampling rate, number of channels, and encoding bit rate, etc., wherein the larger the encoding bit rate, the more bandwidth the encoded bit stream occupies, the more storage the encoded file occupies, and the higher the quality of speech encoding. [0003] In related technologies, the coding bit rate is generally set through experimental experience values. For example, the PESQ method is used to measure...

AI Technical Summary

Problems solved by technology

[0004] Obviously, adopting the speech coding method with a fixed coding rate in the related art, since the speech signal itself is a time-varying signal, there are large differences in the compression process of speech signals at different times and different speech signals inside the speech coder, which will make the same coding rate The coding quality of different speech signals varies greatly, and the quality of speech coding cannot be guaranteed

Images