Singing synthetic method for tone conversion
A technology of timbre conversion and synthesis method, applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as difficult acquisition, poor generalization ability, inapplicable singing timbre conversion, etc., to achieve breakthrough dependence and good effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0022] The present invention will be further explained below in conjunction with the drawings and specific embodiments.
[0023] The invention provides a singing voice synthesis method oriented to tone color conversion, such as figure 1 The steps shown include the following:
[0024] Step S1: Obtain a cappella audio file of the singer, and extract its acoustic features using the STRAIGHT algorithm;
[0025] Step S2: Construct and train a variational self-encoding-generative confrontation network model to obtain a trained song voice color conversion model;
[0026] Step S3: Obtain a cappella audio file of the source singer, extract the acoustic features using the STRAIGHT algorithm and input the singing voice color conversion model, the model output is the acoustic feature after timbre conversion, and then STRAIGHT is used to synthesize the acoustic feature into the timbre converted singing voice.
[0027] In an embodiment of the present invention, the step S1 specifically includes the f...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap