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

City noise identification method based on hybrid deep neural network models

A deep neural network and urban noise technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of time loss and high complexity of model training, and achieve the effect of fast computing speed, less resources, and improved accuracy

Active Publication Date: 2018-11-30
HANGZHOU DIANZI UNIV
View PDF7 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deep learning methods require millions of urban noise data as support, and obtaining such a large amount of data is a very time-consuming process
At the same time, in the process of big data processing, the deep learning method is faced with the problem of high complexity of model training.

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
  • City noise identification method based on hybrid deep neural network models
  • City noise identification method based on hybrid deep neural network models
  • City noise identification method based on hybrid deep neural network models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with drawings and embodiments.

[0028] Figure 2- Figure 4 As shown, the present invention uses three kinds of deep neural networks trained on the large-scale image library ImageNet to carry out feature extraction on the acoustic signal spectrogram through the difference of the acoustic signal spectrogram, and proposes a method based on a hybrid deep neural network urban noise recognition method.

[0029] The present invention first predicts 11 types of sound signals, and then converts these 11 types of sound signals into Figure 2(a)-Figure 2(e) The displayed spectrogram image of the acoustic signal. The spectrograms are then fed into the Figure 3(a)-Figure 3(c) Feature extraction is performed in the deep neural network shown. Then if Figure 4 Feature fusion and classification recognition are performed as shown.

[0030] The concrete realization of the present invention 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 a city noise identification method based on hybrid deep neural network models. The city noise identification method comprises the following steps that 1, city noise is collected, and a sound sample database is built; 2, sound signals in the sound sample database are converted into a speech spectrum; 3, the obtained speech spectrum is clipped, and then feature extracting isconducted by using the multiple pre-trained deep neural network models; 4, features extracted by the multiple models are spliced; 5, the spliced fusion feature serves as final input of a classifier, and a prediction model is trained; and 6, as for unknown sound, the sound is converted into the speech spectrum firstly, feature extracting is conducted by using the multiple pre-trained deep neural network models, the extracted features are spliced, then prediction is conducted by using the trained prediction model, and the final sound type is obtained. A large quantity of datasets are not needed,the operating rate is higher, and needed resources are fewer.

Description

technical field [0001] The invention belongs to the field of machine learning and intelligent sound signal processing, and relates to an urban noise recognition method based on a hybrid deep neural network model. Background technique [0002] With the rapid development of my country's economy and society, and the continuous acceleration of urbanization, construction, transportation, social life and other activities will generate a lot of noise. Urban noise identification plays a vital role in urban management and safe operation, especially in the construction of smart city projects. The analysis and measurement of urban noise has attracted extensive attention and research all over the world. Severe urban noise will have a serious impact on the surrounding residents. At the same time, urban noise recognition also has many potential applications in urban safety detection, and effective feature representation and classification algorithms are the key to urban noise recognition...

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): G10L25/51G10L25/30G10L25/03G10L15/08G10L15/06
CPCG10L15/063G10L15/08G10L25/03G10L25/30G10L25/51
Inventor 曹九稳沈叶新王建中
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