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

Ecological sound identification method on basis of rapid sparse decomposition and deep learning

A sparse decomposition, deep learning technology, applied in the field of ecological sound recognition, can solve the problem that the classification effect is not as good as GMM or HMM

Inactive Publication Date: 2014-01-22
FUZHOU UNIV
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The discriminative model SVM and some traditional neural networks can better model nonlinear classification, but when there are many high-dimensional features and categories, the classification effect is not as good as GMM or HMM

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
  • Ecological sound identification method on basis of rapid sparse decomposition and deep learning
  • Ecological sound identification method on basis of rapid sparse decomposition and deep learning
  • Ecological sound identification method on basis of rapid sparse decomposition and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The invention utilizes the method of fast sparse decomposition and deep learning to recognize ecological sounds. Firstly, use Orthogonal Matching Pursuit (OMP) based on Firefly Algorithm (GSO) to decompose and reconstruct the sound signal with finite times of sparseness, retain high correlation components and filter out low correlation noise; secondly, extract according to atomic time-frequency information and frequency domain information Composite anti-noise features; finally, combined with deep belief network (DBN) to classify and recognize ecological sounds in different environments and signal-to-noise ratio situations. Experiments show that the performance of OMP sparse denoising is better than that of spectral subtraction and wavelet denoising. Compared with the commonly used methods of MFCCs and SVM, this method has different degrees of improvement in the recognition performance of ecological sounds under different signal-to-noise ratios. It has good noise immunit...

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 ecological sound identification method on the basis of rapid sparse decomposition and deep learning, which is characterized by comprising the following steps: S01, respectively carrying out OMP (Orthogonal Matching Pursuit) sparse decomposition on pure sound and test tape noise and correspondingly outputting reconstruction signals and OMP characteristics of the pure sound and the test tape noise; S02, respectively extracting composite characteristics comprising the OMP characteristics from the pure sound and the test tape noise; S03, carrying out DBN (Dynamic Bayesian Network) model training on the composite characteristics extracted from the reconstructed pure sound; and S04, carrying out DBN model classification on the composite characteristics extracted from the reconstructed test tape noise and the trained pure sound and outputting an ecological sound category which the test tape noise belongs to. The ecological sound identification method has a more obvious effect of improving noise resistance and robustness of a system.

Description

technical field [0001] The invention relates to an ecological sound recognition method based on fast sparse decomposition and deep learning. Background technique [0002] In recent years, habitat protection has received more and more attention, and some areas have deployed large-scale monitoring to grasp real-time information. By analyzing and identifying the audio information contained in the ecological environment, it can provide data support for applications such as invasion monitoring and species survey. In the real environment, the complex and changeable background noise is ubiquitous, therefore, the ecological sound recognition in the noise environment has important practical significance. [0003] At present, there are many speech and music classification and recognition technologies, but there are relatively few studies on environmental sounds. The audio information contained in different environments varies greatly. For example, in noisy environments such as resta...

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): G10L15/08G10L17/26G10L17/04
Inventor 李应欧阳桢
Owner FUZHOU 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