Vocal conversion methods, devices, electronic equipment, software products, and storage media
CN119380734BActive Publication Date: 2026-05-26TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
- Filing Date
- 2024-11-14
- Publication Date
- 2026-05-26
AI Technical Summary
Technical Problem
Current technology can only convert the timbre of dry vocals, but cannot convert singing styles, which limits the application of vocal conversion functions.
Method used
The noise reduction principle of the diffusion model is adopted. Based on the singing style information, the basic dry voice is converted into a singing style. The basic dry voice audio and singing style information are encoded into vectors. The random noise is denoised using a trained diffusion model to obtain the converted dry voice vector, which is then decoded to achieve singing style conversion.
Benefits of technology
It enhances the flexibility of vocal transitions, enabling flexible switching of the vocal style based on singing style information, and achieving flexible adjustment of timbre and style.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119380734B_ABST
Abstract
This application provides a singing voice conversion method, apparatus, electronic device, program product, and storage medium, relating to the field of singing voice conversion. The method includes: acquiring basic dry audio and singing style information; encoding the basic dry audio into a basic dry vector and encoding the singing style information into a singing style vector; using a trained diffusion model to perform noise reduction processing on random noise based on the basic dry vector and the singing style vector to obtain a converted dry vector; decoding the converted dry vector to obtain a converted dry audio; and enabling singing style conversion of the basic dry audio based on the noise reduction principle of the diffusion model and according to the singing style information, thereby improving the flexibility of singing voice conversion.
Need to check novelty before this filing date? Find Prior Art