Method and equipment for full frequency domain digital hearing aid
A full frequency domain, digital technology, applied in the field of full frequency domain digital hearing aids, can solve problems such as no comprehensive consideration
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0119] An embodiment of the present invention provides a full frequency domain digital hearing aid method, see figure 1 , the method includes:
[0120] 101: Obtain the input voice signal of the front and rear dual microphones, divide the input voice signal into frames, and perform Fourier transform on the input voice signal after the frame division, to obtain the frame-divided voice domain signal;
[0121] 102: Recognize the voice scene on the framed voice domain signal, and obtain the voice scene category of the input voice signal;
[0122] 103: When the voice scene of the input voice signal is noisy voice, perform voice detection on the framed voice domain signal, and judge whether each frame in the framed voice domain signal is a voice frame or a noise frame;
[0123] 104: Perform dual-microphone beamforming processing on the framed voice domain signal after the voice detection;
[0124] 105: Perform wind noise processing on the voice signal formed by dual-microphone beam...
Embodiment 2
[0172] In order to solve the problem that current digital hearing aids only focus on solving a certain aspect of hearing impairment without comprehensive consideration of various factors affecting the use effect, and at the same time improve the processing speed, reduce resource occupation, and reduce energy consumption, the embodiment of the present invention provides a comprehensive Frequency-domain digital hearing aid method, unless otherwise specified, all processing in the embodiment of the present invention is performed in the frequency domain, see figure 2 , the specific implementation process is as follows:
[0173] 201: Perform buffering, frame division, windowing and FFT (Fast Fourier transform, Fast Fourier Transform) calculation on the input voice signal. The specific implementation process is as follows:
[0174] 201a: Buffering and windowing the input voice signal, and padding the framed voice signal with zeros;
[0175] Wherein, in the embodiment of the presen...
Embodiment 3
[0317] An embodiment of the present invention provides a full frequency domain digital hearing aid device, see Figure 10 , the device consists of:
[0318] The framing module 301 is used to obtain the input voice signal of the front and rear dual microphones, and divide the input voice signal into frames, and carry out Fourier transform to the input voice signal after the frame division, so as to obtain the frame-based voice audio domain signal;
[0319] Scene recognition module 302, is used for carrying out the recognition of speech scene to sub-frame speech frequency domain signal, obtains the speech scene classification of input speech signal;
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