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

A method for extracting auditory features of underwater target gammachirp cepstral coefficient

A cepstral coefficient and auditory feature technology, applied in the field of classification and recognition of underwater target radiation noise, can solve the problems of MFCC algorithm being easily affected by noise, signal interference, errors, etc. The effect of clear spectrum background

Active Publication Date: 2016-06-08
NORTHWESTERN POLYTECHNICAL UNIV
View PDF1 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
  • A method for extracting auditory features of underwater target gammachirp cepstral coefficient
  • A method for extracting auditory features of underwater target gammachirp cepstral coefficient
  • A method for extracting auditory features of underwater target gammachirp cepstral coefficient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0038] This embodiment is the radiated noise of underwater targets recorded at sea. The radiated noise of underwater targets is sampled at a sampling rate of 22.05 kHz, and the signal-to-noise ratio is greater than 6 dB.

[0039] For the underwater target radiation noise data that is recorded, the main steps of the present invention are as follows:

[0040] 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

[0041] ω ( n ) = 0.54 - 0.46 cos ( 2 πn N - 1 ) , ...

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

A method for extracting auditory features of underwater target gammachirp cepstrum coefficients proposed by the present invention is based on Fourier transform and logarithmic compression, combined with gammachirp auditory filter banks, firstly preprocesses the measured noise data to make the target The signal is expressed as approximately stable in a short period of time, and then Fourier transform is performed on the preprocessed data, and the time-domain signal processing is converted into a frequency-domain signal for processing, and then it is auditory filtered through the gammachirp auditory filter bank and used Logarithmic compression, and finally perform discrete cosine transform on the logarithmically compressed data to reduce its dimensionality. This feature extraction method based on the gammachirp frequency auditory perception cepstral coefficient can extract effective auditory features of underwater target radiation noise, thereby improving the correct recognition rate of underwater targets.

Description

technical field [0001] The invention relates to an auditory feature extraction method of gammachirp cepstrum coefficient of an underwater target, which can be applied to the classification and recognition of the radiation noise of the underwater target. 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. Currently, the main feature extraction methods used are: [0003] 1) Power spectrum estimation and LOFAR spectrum analysis [0004] ...

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): G10L25/24
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