Audio data processing method, device, electronic equipment and computer storage medium

Abstract

The embodiment of the invention discloses an audio data processing method, a device, electronic equipment and a computer storage medium. The method comprises the steps: detecting an audio splicing instruction; determining N segments of original audio feature sequences to be spliced, wherein N is an integer greater than or equal to 2; generating a reference audio feature sequence according to the Nsegments of original audio feature sequences, wherein the reference audio feature sequence comprises all audio frames of the N segments of original audio feature sequences; and updating the audio frames in the reference audio feature sequence according to a preset strategy to obtain a target audio feature sequence. By implementing the embodiment of the invention, the integrity of the audio data at the splicing positions can be improved, and the audio transition at the splicing positions is more natural.

Description

technical field [0001] The present application relates to the technical field of audio processing, in particular to an audio data processing method, device, electronic equipment, and computer storage medium. Background technique [0002] With the advancement of electronic technology and the development of the Internet, the explosive growth of videos circulating on the Internet; audio and video has become the main way for the public to obtain information and entertainment, so it involves the production of a large number of audio and video; in the process of making audio and video In , there are a lot of audio to be spliced. The current commonly used audio splicing method is usually to take out part of the two pieces of audio to be spliced ​​for processing. For example, for the three audio frames at the end of the first piece of audio and the beginning of the second piece of audio The three frames of audio frames are processed to generate three frames of audio frames at the sp...

AI Technical Summary

Problems solved by technology

[0002] With the advancement of electronic technology and the development of the Internet, the explosive growth of videos circulating on the Internet; audio and video has become the main way for the public to obtain information and entertainment, so it involves the production of a large number of audio and video; in the process of making audio and video In , there are a lot of audio to be spliced. The current commonly used audio splicing method is usually to take out part of the two pieces of audio to be spliced ​​for processing. For example, for the three audio frames at the end of the first piece of audio and the beginning of the second piece of audio The three frames of audio frames are processed to generate three frames of audio frames at the splicing place. Since two pieces of audio are jointly synthesized into a new three frames of audio, it may cause the loss of content information in the audio data, resulting in the easy generation of noise at the splicing point. Makes it sound unnatural, greatly affecting the experience of watching videos or listening to music

Images