Signal enhancement methods, devices and electronic equipment

By acquiring sound signal features, using multiple sound enhancement methods for enhancement processing, and performing weighted fusion based on adaptability, the problem of poor enhancement effect after sound scene switching is solved, and good adaptability in different scenarios is achieved.

CN122090865APending Publication Date: 2026-05-26TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
TENCENT TECHNOLOGY (SHENZHEN) CO LTD
Filing Date
2024-11-25
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing sound enhancement models or algorithms cannot adapt to the switching between different sound scenes, resulting in poor sound enhancement effects after the sound scene is switched.

Method used

By acquiring the features of the sound signal, multiple sound enhancement methods are used for enhancement processing. The fusion network determines the fit based on the sound features and enhancement results, and performs weighted fusion to obtain the target enhancement result.

Benefits of technology

It ensures that the target enhancement result of the sound signal can maintain a good enhancement effect under different sound scene switching, and is adapted to different sound scenes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122090865A_ABST
    Figure CN122090865A_ABST
Patent Text Reader

Abstract

This application relates to the field of computer technology, specifically to a signal enhancement method, apparatus, and electronic device. The method involves acquiring a sound signal; extracting features from the sound signal to obtain sound features; performing enhancement processing on the sound signal using multiple sound enhancement methods based on the sound features to obtain multiple sound enhancement results; and using a fusion network to determine the fit between the sound signal and each sound enhancement method based on the sound features and the multiple sound enhancement results, and then weighting and fusing the multiple sound enhancement results according to the fit between the sound signal and each sound enhancement method to obtain the target enhancement result of the sound signal. Through the method provided in this application, when facing sound signals in different sound scenarios, the weights of the multiple sound enhancement results in the target enhancement result can be adjusted by changing the fit between the sound signal and the multiple sound enhancement methods in different sound scenarios, thereby ensuring the sound enhancement effect in different sound scenarios.
Need to check novelty before this filing date? Find Prior Art