Acoustic-wavelet-packet-based millimeter-wave biological radar speech enhancement method
A bio-radar and speech enhancement technology, applied in speech analysis, instruments, etc., can solve the problems that hinder the progress of bio-radar speech detection technology and reduce the quality of radar speech
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0091] In order to ensure the consistency of the sound source, a male experimenter's recording material "1-2-3-4-5-6" was selected and played by a speaker at a distance of 2 meters from the radar system.
[0092] The radar voice is enhanced in the following steps:
[0093] 1) Utilize 8-channel Powerlab physiological recorder to sample the biological radar voice, the sampling rate is 10kHz; the original noisy radar voice signal is obtained through sampling;
[0094] 2) The noise distribution characteristics of the original radar voice signal are: the lower the frequency, the greater the amount of noise;
[0095] 3) performing auditory characteristic wavelet packet decomposition on the above-mentioned original radar voice signal;
[0096] 4) denoising the decomposed auditory wavelet packet through adaptive node threshold and modified threshold function;
[0097] 5) Reconstruct the denoised auditory wavelet packet to obtain the enhanced radar speech.
[0098] Comparison of pro...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


