Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for eliminating environmental noise from voice signal

An environmental noise and speech signal technology, applied in speech analysis, instruments, etc., can solve the problems of reducing the accuracy of signal recognition and inconsistency in the impact of speech signals, achieving the effects of resisting interference, eliminating noise interference, and improving adaptability

Inactive Publication Date: 2009-06-17
WUDI SCI & TECH (XIAN) CO LTD
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the noise in real life is mostly color noise, and the influence of color noise on the entire frequency spectrum of the speech signal is not consistent. Some frequency bands of the speech signal are much more affected by noise than other frequency bands, so it greatly reduces Accuracy of Signal Identification

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
  • Method for eliminating environmental noise from voice signal
  • Method for eliminating environmental noise from voice signal
  • Method for eliminating environmental noise from voice signal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] see figure 1 , which is a flow chart of the steps of the method for eliminating environmental noise in the speech signal of the present invention. Speech signal of the present invention comprises an environment noise and a pure speech signal, and this method comprises the following steps:

[0043] Step S10: first set a sound frame in the voice signal;

[0044] Step S11: detecting the upper limit frequency value and signal-to-noise ratio (SNR) in the sound frame;

[0045] Step S12: Determine a first adjustment parameter and a second adjustment parameter corresponding to the sound frame according to the upper limit frequency value and the signal-to-noise ratio;

[0046] Because of general natural noise (cars, streets and human voices, etc.), the power spectrum tends to decrease from low to high frequency, and its energy is often distributed in the entire spectrum range, while the energy of speech signals is mostly concentrated in the low frequency band. Therefore, a re...

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 relates to a method for eliminating environment noise in voice signals, comprising: (1) setting a voice frame in voice signals; (2) detecting the upper limit frequency value F and the signal noise ratio SNR of the voice frame; (3) according to the upper limit frequency value F and the signal noise ratio SNR, determining a first adjustment parameter alpha and a second adjustment parameter beta corresponding to the voice frame; (4) using the first adjustment parameter alpha, the second adjustment parameter beta, and a preset noise strength factor M to generate a corrected noise strength factor M', wherein the noise strength M'=M x alpha x beta; (5) using frequency spectrum subtraction method, the corrected noise strength factor M' and an energy spectrum equation to process calculation, thereby eliminating environment noise from the voice signals. The invention can effectively eliminate noise interference, improve the adaptability of voice recognition system on different environment noises, improve the correctness of signal recognition, and effectively resisting the interference of background environment noise under low signal noise ratio.

Description

technical field [0001] The invention relates to a method for eliminating noise, in particular to a method for eliminating environmental noise in speech signals. Background technique [0002] Noise is a sound that interferes and hinders people's normal work, study and rest. During the transmission process, the signal is more or less interfered by some unnecessary extra energy (that is, noise). The interference of noise usually causes signal distortion, and its source usually comes from the outside or inside of the system. [0003] As far as external noise sources are concerned, man-made noise is the most influential noise in speech recognition. Man-made noise sources such as ignition systems of automobiles, locomotives and aircraft, electric motors, switching equipment, high-voltage cables and fluorescent lamps using arc discharge, etc. This noise interference ranges from 0 to 600MHz. [0004] There are many sources of internal noise, one of which is the so-called thermal n...

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): G10L21/02
Inventor 赵仁宏陈淮琰
Owner WUDI SCI & TECH (XIAN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

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