Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Underwater target gammatone discrete wavelet coefficient auditory feature extraction method

A discrete wavelet and auditory feature technology, applied in vibration measurement, measurement devices, instruments, etc., can solve the problems of signal interference, MFCC algorithm is easily affected by noise, errors, etc., to improve the accuracy rate, improve the correct recognition rate, spectrum The effect of clear background

Active Publication Date: 2015-04-29
NORTHWESTERN POLYTECHNICAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The MFCC algorithm is susceptible to noise, and the signal is slightly interfered, and the amplitude, phase and frequency of the spectrum may produce large errors

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
  • Underwater target gammatone discrete wavelet coefficient auditory feature extraction method
  • Underwater target gammatone discrete wavelet coefficient auditory feature extraction method
  • Underwater target gammatone discrete wavelet coefficient auditory feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0035] The present invention will be further described in conjunction with the underwater target radiation noise recorded at sea and the accompanying drawings: the underwater target radiation noise is sampled at a sampling rate of 22.05kHz, and the signal-to-noise ratio is approximately greater than 6dB.

[0036] For the underwater target radiation noise data that is recorded, the main steps of the present invention are as follows:

[0037] Step 1: Preprocessing the radiation noise of the recorded underwater target, including framing and windowing, the window function uses the Hamming window, and its form is

[0038] ω ( n ) = 0.54 - 0.46 cos ( 2 πn N ...

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 an underwater target gammatone discrete wavelet coefficient auditory feature extraction method. Noisy data measured actually are preprocessed at first on the basis of Fourier transform and logarithm compression and in incorporation with a gammatone auditory filter bank and discrete wavelet transform to enable target signals to be approximately stable in the short time; Fourier transform is conduced on the preprocessed data, time-domain signal processing is converted into frequency-domain signal processing, auditory filtering and logarithm compression are conducted on the preprocessed data through the gammatone auditory filter bank, discrete wavelet transform is conducted on the data on which logarithm compression is conducted at last, and the dimensionality of the data is reduced. The underwater target gammatone discrete wavelet coefficient auditory feature extraction method can extract effective auditory features of underwater target radiation noise, thereby improving the correct recognition rate of the underwater target.

Description

technical field [0001] The invention relates to an underwater target gammatone discrete wavelet coefficient auditory feature extraction method, which can be applied to the classification and identification of underwater target radiation noise. Background technique [0002] Underwater target feature extraction refers to extracting a set of features reflecting its characteristics and types from the preprocessed underwater target radiation noise waveform (time-domain feature extraction), or using a certain method to transform the target radiation noise waveform, and then Extract a set of features reflecting its characteristics and target type in the transform domain (transform domain feature extraction). Feature extraction is one of the key links in target recognition, which directly affects the final recognition result of the target. At present, the more mature feature extraction methods mainly include: [0003] 1) Power spectrum estimation and LOFAR spectrum analysis [00...

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 Patents(China)
IPC IPC(8): G01H3/00
Inventor 杨益新吴姚振
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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