Speech conversion method based on one-to-many codebook mapping
A voice conversion and codebook technology, applied in voice analysis, instruments, etc., to achieve good application prospects, fast voice conversion, and improve the effect of similarity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment
[0063] Introduce below a specific embodiment according to the speech conversion method of the present invention, specifically as follows,
[0064] Step (1), training phase:
[0065] (A) Source and target human speech are decomposed by a harmonic plus stochastic model to obtain the amplitude and phase values of the pitch frequency trace and harmonic channel spectral parameters. The specific details are described as follows:
[0066] A1) Divide the voice signal into frames, the frame length is 20ms, and the frame overlap interval is 10ms. In each frame, use the autocorrelation method to estimate the fundamental frequency. If the frame is an unvoiced frame, set the fundamental frequency to zero;
[0067] A2) For voiced frames (i.e., frames whose fundamental frequency is not zero), suppose the speech signal s h (n) can be formed by superposition of a series of sine waves:
[0068] s h ( n ) ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 