Supercharge Your Innovation With Domain-Expert AI Agents!

Voice graph adaptive spectral subtraction method based on non-uniform graph sub-band division

A non-uniform and spectral subtraction technology, which is applied in speech analysis, instruments, etc., can solve the problem of not taking into account the different distribution characteristics of speech signals and noise signals

Pending Publication Date: 2022-03-22
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Under this scheme, the graph spectrum subtraction uniformly adopts the same spectral subtraction strategy for the entire graph frequency domain, which fails to take into account the different distribution characteristics of speech signals and noise signals in the graph frequency domain, so its noise reduction technology and performance still have further development. room for improvement

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice graph adaptive spectral subtraction method based on non-uniform graph sub-band division
  • Voice graph adaptive spectral subtraction method based on non-uniform graph sub-band division
  • Voice graph adaptive spectral subtraction method based on non-uniform graph sub-band division

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The following is a detailed description of the examples of the present invention. This example is implemented on the premise of the technical solutions of the present invention, and provides detailed implementation methods and specific operating procedures.

[0026] like figure 2 As shown, this example is implemented through the following steps:

[0027] Step 1: Use the forgetting graph based on the forgetting factor to construct the graph topology of the speech signal. For an N-order speech graph adjacency matrix A, the element in the i-th row and the j-th column satisfies

[0028]

[0029] Where λ∈(0,1) is the forgetting factor, i, j∈[1,N]∩i, Indicates that the farther the time distance between the sampling points, the weaker the correlation between the two. At the same time, Ψ is the forgetting threshold, and when the time correlation between the two is lower than the threshold, it is considered that there is no correlation.

[0030] According to the theory o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a voice graph adaptive spectral subtraction method based on non-uniform graph sub-band division, which is characterized in that on the basis of the original graph subtraction, non-uniform graph frequency domain division is carried out on a graph frequency according to the graph frequency domain characteristics of voice to form so-called graph sub-band signals, so that the widths of graph sub-bands in different graph frequency ranges are different. And then, according to voice distribution on graph sub-bands, sub-band signal-to-noise ratio estimation is carried out on voice signals, graph sub-bands are screened on the basis of the sub-band signal-to-noise ratio estimation, and adaptive spectral subtraction strategies are adopted for different graph sub-bands, so that the voice enhancement performance of the algorithm is improved. The noise performance of the method is obviously improved compared with that of a graph subtraction method and a sub-band spectral subtraction method.

Description

technical field [0001] The invention belongs to the field of graph voice signal noise reduction, and specifically designs a voice graph adaptive spectral subtraction method based on non-uniform graph subband division. Background technique [0002] With the advent of the era of big data, signal scenarios are becoming increasingly complex and diverse, such as large-scale sensor networks, social networks, and biological networks, so signals are gradually showing high-dimensional and irregular characteristics. The traditional signal processing method relies on the digital signal processing theory, which has a good processing effect on regular low-dimensional signals, but is helpless for irregular high-dimensional signals. In recent years, the proposal of Graph Signal Processing (Graph Signal Processing) has attracted extensive attention of researchers. It mainly establishes a graph topology structure, and uses three elements of vertices, edges and weights to describe the signal ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L21/0208G10L21/0216G10L21/0232G10L21/0264
CPCG10L21/0208G10L21/0216G10L21/0232G10L21/0264
Inventor 杨震郭振超葛子瑞
Owner NANJING UNIV OF POSTS & TELECOMM
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com