Audio synthesis method, audio synthesis system, computer device and storage medium

By adjusting the amount of accompaniment audio data in the audio buffer to match the amount of reference buffer data, the problem of misalignment between vocals and accompaniment in unstable network environments was solved, achieving high-quality audio synthesis in various environments.

CN117116246BActive Publication Date: 2026-06-05TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
Filing Date
2023-08-14
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

In an unstable network environment, the accompaniment audio data cannot be stored or read from the audio buffer normally, resulting in misalignment between the vocals and the accompaniment in the synthesized audio.

Method used

By obtaining the current buffer data volume of the audio buffer, the amount of accompaniment audio data is adjusted to match the reference buffer data volume, ensuring that the playback duration matches the recording duration, thus guaranteeing the alignment of the accompaniment audio and the dry audio even in unstable environments.

Benefits of technology

It can guarantee the quality of synthesized audio in both stable and unstable environments, solve the problem of misalignment between vocals and accompaniment, and improve the effect of synthesized audio.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117116246B_ABST
    Figure CN117116246B_ABST
Patent Text Reader

Abstract

The application relates to an audio synthesis method, an audio synthesis system, a computer device and a computer readable storage medium. The method comprises the following steps: acquiring a current buffer data amount of an audio buffer; the current buffer data amount is used for indicating a playing time length of accompaniment audio data in the audio buffer; based on the difference between the current buffer data amount and a reference buffer data amount, the data amount of the accompaniment audio data buffered in the audio buffer is adjusted to obtain an adjusted audio buffer; the accompaniment audio data is read out from the adjusted audio buffer, and the read accompaniment audio data is played; and when a user sings along with the played accompaniment audio data, the dry audio data of the user is recorded; the read accompaniment audio data and the recorded dry audio data are subjected to audio synthesis processing to obtain synthesized audio data. By adopting the method, the read accompaniment audio data and the recorded dry audio data can be ensured to correspond to each other, and the audio quality of the synthesized audio is improved.
Need to check novelty before this filing date? Find Prior Art