Method for identifying a sound event

A recognition method and sound technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as poor sound recognition effect, achieve the effects of improving recognition rate, avoiding manual intervention, and strong robustness

Inactive Publication Date: 2018-01-05
GUILIN UNIV OF ELECTRONIC TECH
View PDF4 Cites 56 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is the technical problem that the sound recognition effect is poor in the environment of strong noise and strong interferen

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
  • Method for identifying a sound event
  • Method for identifying a sound event

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0041] This embodiment provides a sound event recognition method. In this embodiment, the noise in the traffic environment is used as a specific embodiment. The specific process is as follows figure 1 shown, including the following steps:

[0042] A. Use a sound level meter with a microphone array to collect sound in different interference environments to form a sound digital signal;

[0043] The four kinds of sound events are collected and processed at three signal-to-noise ratios of 20dB, 10dB, and 0dB. The number of samples for each sound event is 4800, and the sampling frequency is 8KHZ. The four sound events are vehic...

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 present invention relates to a method for identifying a sound event, and problems of low accuracy of sound identification and poor robustness under a strong interference condition in the prior artare mainly solved. The method comprises a step of collecting and processing sound under different interference environments and forming a sound digital signal, a step of carrying out sub-band filtering on the sound digital signal by a filter group and obtaining a cochlear spectrum of an audio signal, a step of training a part of the cochlear spectrum into a convolution neural network model and establishing a sound recognition template, and a step of substituting the other part of the cochlear spectrum into the convolution neural network model and detecting the accuracy of sound recognition. According to the above method, the problem is solved, and the method can be used for identifying the sound event in a traffic environment.

Description

technical field [0001] The invention belongs to the technical field of audio signal processing, and in particular relates to a sound event recognition method in a strong interference environment. Background technique [0002] In recent years, researchers have proposed many feature extraction methods and recognition systems for sound event recognition, all of which have achieved certain results. There is a sound event recognition method that collects people's voice information, performs FFT processing on the sound information, and extracts the information of each person. The amplitude and frequency in the sound information of the person, and store it; after the person's information is processed in the same way, it is compared with the information in the information database to determine the person's identity and identify the sound event recognition method. This kind of sound event recognition The recognition effect of the method is ideal in the weak noise environment, but the...

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
IPC IPC(8): G10L15/05G10L15/06G10L15/16G10L21/0208
Inventor 张文涛韩莹莹徐韶华黎恒
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap