Self-adaption spectral subtraction and noise elimination processing method and device for voice signals
A speech signal, adaptive technology, applied in speech analysis, instruments, etc., to solve the problem of background noise
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0016] A schematic structural diagram of a voice resource processing and switching service platform provided by an embodiment of the present invention is as follows figure 1 As shown, the platform mainly completes functions such as voice enhancement, transcoding of audio media streams, multi-channel audio mixing, recording, playback, and echo cancellation. The platform has the code stream forwarding function, which can forward the front-end audio stream to the dispatching console and storage device; it has powerful streaming media processing capabilities, and a single unit supports 1440 channels of voice non-blocking scheduling and forwarding processing, and a single conference supports 480 parties sound.
[0017] The above-mentioned I / O board in the voice resource processing and switching service platform: mainly realizes the external connection between the switch and the hardware platform, and at the same time, uses the pins of the front and rear boards to realize the trunk ...
Embodiment 2
[0059] This embodiment provides a device for performing adaptive spectrum reduction and noise reduction processing on speech signals, and its specific structure is as follows: Figure 4 As shown, the following modules are included:
[0060] The additive model acquisition module 41 of speech signal is used for setting up the additive model of speech signal according to band noise signal, noise signal and speech signal;
[0061] The power estimation value acquisition module 42 of speech signal, is used for calculating the power spectrum of the additive model of described speech signal, obtains according to the power spectrum of the additive model of described speech signal and the power estimation value of band noise signal, noise signal an estimate of the power of the speech signal;
[0062] The denoising speech signal acquisition module 43 is configured to perform an inverse Fourier transform on the estimated power value of the speech signal to obtain a speech signal with noi...
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