Speech enhancement method and system, communication device
A voice enhancement and voice technology, applied in voice analysis, instruments, etc., can solve the problems of target object's voice damage, poor call effect, large residual acoustic structure of microphone characteristics, etc., to achieve time-frequency adaptive compensation and suppress surrounding The effect of ambient noise
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] According to an embodiment of the present invention, an embodiment of a speech enhancement method is provided. It should be noted that the steps shown in the flow charts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, although in The flowcharts show a logical order, but in some cases the steps shown or described may be performed in an order different from that shown or described herein.
[0035] figure 2 is a flowchart of an optional speech enhancement method according to an embodiment of the present invention, such as figure 2 As shown, the method includes the following steps:
[0036] Step S202, acquiring a voice input signal;
[0037] Step S204, performing time-frequency compensation on the voice input signal;
[0038] Step S206, calculating a plurality of voice feature information after time-frequency compensation, and classifying the voice input signal to obtain a voice classification re...
Embodiment 2
[0097] The speech enhancement system in the embodiment of the present invention will be described in detail below.
[0098] Figure 4 is a schematic diagram of an optional speech enhancement system according to an embodiment of the present invention, such as Figure 4 As shown, the speech enhancement system may include:
[0099] A time-frequency compensation unit 41, configured to perform time-frequency compensation to the voice input signal;
[0100] Feature processing unit 43, connected with the time-frequency compensation unit, used to calculate a plurality of speech feature information through time-frequency compensation;
[0101] Voice activation detection unit 45, connected with feature processing unit, is used to detect the type of voice input signal, obtains voice classification result, wherein, voice classification result comprises: voice signal and noise signal;
[0102] A masking calculation unit 47, configured to determine a voice masking value according to a pl...
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