Speech enhancement method using voice existence probability
A voice enhancement and voice technology, applied in voice analysis, instruments, etc., can solve problems such as insufficient suppression effect, noise residue, and impact on auditory experience, and achieve the effect of improving subjective perception quality, improving quality, and high voice quality
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0019] refer to figure 1 . According to the present invention, adopt following steps:
[0020] (1) Sampling, framing, and windowing the input noisy speech;
[0021] (2) Obtain the noisy speech spectrum Y(k,l) by Fast Fourier Transform FFT, k represents the number of frequency points, and l represents the number of frames (the following k and l represent the same meaning);
[0022] (3) Calculate the gain factor G according to the MIS measurement speech enhancement method 1 (k,l) and noise estimation spectrum λ d (k,l);
[0023] (4) Utilize the noise estimation spectrum to obtain the priori signal-to-noise ratio, and obtain the speech existence probability p(k, l) by the priori signal-to-noise ratio;
[0024] (5) Using the gain factor G 1 (k,l) and p(k,l), get the new gain factor G new (k,l);
[0025] (6) Combine the spectrum Y(k,l) of the noisy speech with the new gain factor G new (k,l) multiplied to get the spectrum of the enhanced speech
[0026] (7) For spectrum...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com