Non-air conduction speech enhancement method based on wavelet-packet energy
An air conduction, speech enhancement technology, applied in speech analysis, instruments, etc., can solve problems such as head movement, gestures, lip movements, heartbeat, breathing, affecting the quality of speech signals, and complex signal components when speaking
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0037] see figure 1 , the present invention first carries out wavelet packet transformation 1 after digitizing the received radar non-air conduction voice signal; the obtained wavelet packet coefficients are processed in two aspects: one is to calculate the global threshold 2; the other is to calculate the Teager energy Operator 3, and then calculate the second-order low-pass filter 4, thereby generating a time-adaptive mask 5. Using the generated time-adaptive mask 5, combined with the global threshold 2, a time-scale adaptive threshold 6 is obtained. The wavelet packet coefficients are thresholded 7 by using this time-scale adaptive threshold, and the enhanced speech is obtained through wavelet packet reconstruction 8 .
[0038] The specific steps are as follows:
[0039] 1) Firstly, the radar non-air conduction voice signal is sampled and A / D converted,...
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