Vehicle model audio feature extracting method based on LMD (local mean decomposition) and energy projection methods

A technology of audio features and extraction methods, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of not considering the difference of signal frequency components, unable to directly and effectively identify signal characteristic frequencies, etc.

Active Publication Date: 2015-05-20
沈阳易达讯通科技有限公司
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Single power spectrum analysis, cepstrum analysis, filter analysis and filter, wavelet packet decomposition, empirical mode decomposition and other signal decomposition methods, or analyze the signal as a whole without distinguishing the multi-component information in the signal, or analyze each decomposed The signal components are processed uniformly without considering the difference between the signal frequency components, and the characteristic frequency in the signal cannot be directly and effectively identified. These problems need to be further resolved

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
  • Vehicle model audio feature extracting method based on LMD (local mean decomposition) and energy projection methods
  • Vehicle model audio feature extracting method based on LMD (local mean decomposition) and energy projection methods
  • Vehicle model audio feature extracting method based on LMD (local mean decomposition) and energy projection methods

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037]Step 1: Use the sound sensor to measure the moving truck and obtain the audio signal of the truck , the sampling frequency is 44100, and the number of sampling points is 4096;

[0038] Step 2: Analyze the collected truck audio signal by local mean decomposition (LMD) method To decompose, the steps are as follows

[0039] (1) Find the local mean function . find truck audio signal All local extreme points , find the average value of all adjacent local extremum points

[0040]

[0041] Among them, i=1,2,...M; M is the number of local extremum points of the original signal. Then, all adjacent mean points Connected by a straight line and smoothed by the moving average method, we get

[0042] (2) Find the envelope estimation function . The envelope estimate is

[0043]

[0044] All two adjacent envelope estimates Connected by a straight line, and then smoothed by the moving average method to obtain .

[0045] (3) The local mean function from th...

Embodiment 2

[0075] Step 1: Use the sound sensor to measure the driving tractor and obtain the audio signal of the tractor , the sampling frequency is 44100, and the number of sampling points is 4096;

[0076] Step 2: Analyze the collected tractor audio signal by local mean decomposition (LMD) method To decompose, the steps are as follows

[0077] (1) Find the local mean function . Find out the tractor audio signal All local extreme points , find the average value of all adjacent local extremum points

[0078]

[0079] Among them, i=1,2,...M; M is the number of local extremum points of the original signal. Then, all adjacent mean points Connected by a straight line and smoothed by the moving average method, we get

[0080] (2) Find the envelope estimation function . The envelope estimate is

[0081]

[0082] All two adjacent envelope estimates Connected by a straight line, and then smoothed by the moving average method to obtain .

[0083] (3) The local mean ...

Embodiment 3

[0111] Step 1: Use the sound sensor to measure the moving car and obtain the audio signal of the car , the sampling frequency is 44100, and the number of sampling points is 4096;

[0112] Step 2: Decompose by local mean Method for the collected car audio signal To decompose, the steps are as follows

[0113] (1) Find the local mean function . find car audio signal All local extreme points , find the average value of all adjacent local extremum points

[0114]

[0115] Among them, i=1,2,...M; M is the number of local extremum points of the original signal. Then, all adjacent mean points Connected by a straight line and smoothed by the moving average method, we get

[0116] (2) Find the envelope estimation function . The envelope estimate is

[0117]

[0118] All two adjacent envelope estimates Connected by a straight line, and then smoothed by the moving average method to obtain .

[0119] (3) The local mean function from the original signal ...

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 provides a vehicle model audio feature extracting method based on LMD (local mean decomposition) and energy projection methods, and relates to the field of intelligent traffic recognition. Vehicle model audio signals are decomposed by adopting a self-adapting LMD method, then, a new PF component is reconstituted by a relevant weighted analysis method, and the feature frequency component is enhanced by the PF component subjected to weighted optimization, so that the vehicle model feature is more effective, and further, the classification accuracy is improved. The vehicle model audio feature extracting method has the advantages that the energy distribution condition of the vehicle model information can be analyzed and reflected in the energy accumulation feature frequency band, the energy of signals X(t) is projected into several respective frequency bands through molecular frequency band division, the calculation quantity is reduced, the feature dimension is reduced, and the real-time performance of an algorithm is improved.

Description

technical field [0001] The invention relates to the field of intelligent traffic recognition, in particular to a vehicle audio feature extraction method based on LMD and energy projection method. Background technique [0002] Vehicle identification is an important content in the field of intelligent transportation. At present, the mainstream methods include magnetic induction coil detection, infrared detection, microwave detection, ultrasonic detection, image and video detection, etc. These methods have their own applicability, but at the same time have their own limitations. They are affected to varying degrees by environmental factors including light, climate, electromagnetic interference, etc. Some methods have high hardware costs, and some methods may even destroy the existing sensors when deploying sensors. There are road conditions. Vehicles will inevitably radiate noise during driving. These noises are different due to differences in engines, friction between tires a...

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): G10L15/02
Inventor 齐晓轩徐长源原忠虎
Owner 沈阳易达讯通科技有限公司
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap