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

Urban noise identification method based on hypercomplex random neural network

A random neural network and urban noise technology, applied in biological neural network models, neural architecture, speech analysis, etc.

Active Publication Date: 2020-08-14
HANGZHOU DIANZI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned problems at present, the present invention proposes a quaternion random neural network urban noise recognition method based on super-complex sound signal feature representation

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
  • Urban noise identification method based on hypercomplex random neural network
  • Urban noise identification method based on hypercomplex random neural network
  • Urban noise identification method based on hypercomplex random neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The present invention will be further described below in conjunction with accompanying drawing and example.

[0079] Such as figure 1 As shown in Fig. 1, all collected signals are first input to the spectral subtraction filter, and the collected signals are filtered through steps such as energy calculation, estimation of non-target sound segments, and spectral subtraction. Such as figure 2 The filtered signal is divided into frames and features are extracted. The resulting filtered signal and corresponding features such as image 3 shown. Such as Figure 4 As shown, the augmented quaternion vector feature after feature extraction and combination is trained by AQ-ELM, and then the number of hidden layer nodes with the optimal classification ability is found, and saved as an urban noise classification model. Finally, the samples to be tested are fed into the trained model to obtain classification results.

[0080] The present invention mainly comprises the followin...

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 discloses an urban noise identification method based on a hypercomplex random neural network. According to the method, urban noise signals pass through a spectral subtraction filter, then MFCC, LSP and PLP features of the urban noise signals are extracted and spliced into a quaternion augmentation vector, and finally classification and recognition of the noise signals are achieved through a quaternion extreme learning machine (Q-ELM). According to the method, useful information in the signal is fully extracted under the condition of a low signal-to-noise ratio, the augmented quaternion structure can also utilize structural information among features, and the recognition rate of the urban noise signal can be effectively improved.

Description

technical field [0001] The invention belongs to the field of smart city security and intelligent voice recognition, and relates to an urban noise recognition method based on a hypercomplex random neural network. Background technique [0002] Urban noise identification and control is a new issue in the field of urban environmental monitoring and public safety. All kinds of noise accompanying the rapid growth of automobile traffic, building construction and machinery industry have already exceeded the city's acceptable warning line. Therefore, urban environmental noise monitoring and intelligent identification have attracted extensive and high attention in recent years. [0003] For urban noise recognition, predecessors have already listed features such as Mel cepstrum coefficient (MFCC), line spectral pair parameter (LSP) and perceptual linear prediction (PLP) and support vector machine (SVM), decision tree (DT), etc. A recognition algorithm combining classifiers. However,...

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): G10L21/0232G10L25/24G06N3/04
CPCG10L21/0232G10L25/24G06N3/04
Inventor 曹九稳沈佩婷王建中曾焕强
Owner HANGZHOU DIANZI 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