Abnormal sound detection method and system of background noise adaption

A background noise and abnormal sound technology, applied in speech analysis, instruments, etc., can solve the problems of high complexity, high integration difficulty, unpredictable abnormal sound, etc., and achieve the effect of small calculation amount and low complexity

Active Publication Date: 2017-03-22
JINAN JOVISION TECH CO LTD
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] A typical abnormal sound detection method and device CN201410850883.5, which uses spectrograms to construct a method for identifying feature matrices, which is relatively complex in time-domain operations, and is difficult to integrate in embedded devices with limited resources, and real-time The performance cannot be guaranteed; and the invention needs to train the abnormal sound sample library in advance. In the field of security monitoring, various abnormal sounds are unpredictable, and the sample library cannot cover all types of abnormal sounds. It is necessary to call the police immediately. At this time, what needs to be detected is the ...

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
  • Abnormal sound detection method and system of background noise adaption
  • Abnormal sound detection method and system of background noise adaption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] The present invention mainly consists of three parts, a general module 21 , a sudden energy rise detection module 22 , and a background noise steep drop detection module 23 . All modules are processed in the time domain without involving frequency domain transformation, with relatively low complexity and fast operation speed.

[0094] The general module 21 includes a framing module 211 and a frame signal RMS energy module 212

[0095] Framing module 211: the sound signal s(n) includes a speech signal, and since the speech signal has a short-term stability of 10ms-30ms, the frame is divided according to the short-term stationarity of the speech signal, and the signal after framing is frame(n), because The processing is completely time-domain energy processing, so it is enough to use a rectangular window to divide the frame. The frame length is N, and the framed signal is frame(n).

[0096] Frame signal RMS energy module 212: Calculate the RMS value of a frame signal, b...

Embodiment 2

[0137] The specific steps of the abnormal sound detection method of the abnormal sound detection system adaptive to background noise in this embodiment are as follows:

[0138] The sampling rate is 11.025 kHz, 8bit quantization, and the sound signal frame length is 10ms, that is, 110 sampling points.

[0139] S101: Usually, audio stream data s(n) is obtained in this step; the next step is to execute S102.

[0140] S102: Frame division, using 10ms as the frame length, frame shift as 0, just use a rectangular window to divide the frame, N=110 as the frame length, and the signal after framing is frame(n).

[0141] The next step is to execute S103.

[0142] S103: frame signal RMS energy, calculate the RMS value of a frame signal, by calculating the RMS excitation average value of the frame signal frame(n), normalize on the number of quantization bits, and take the logarithm, the frame signal RMS energy can be obtained, Denote it as frame_energy.

[0143] In this embodiment, the...

Embodiment 3

[0166] The specific steps of the abnormal sound detection method of the abnormal sound detection system adaptive to background noise in this embodiment are as follows:

[0167] The sampling rate is 8kHz, 24bit quantization, and the sound signal frame length is 30ms, that is, 240 sampling points.

[0168] S101: Usually, audio stream data s(n) is obtained in this step; the next step is to execute S102.

[0169] S102: Framing, using 30ms as the frame length, frame shift as 0, and using a rectangular window to divide the frame, N=240 as the frame length, and the signal after framing is frame(n).

[0170] The next step is to execute S103.

[0171]S103: frame signal RMS energy, calculate the RMS value of a frame signal, by calculating the RMS excitation average value of the frame signal frame(n), normalize on the number of quantization bits, and take the logarithm, the frame signal RMS energy can be obtained, Denote it as frame_energy.

[0172] In this embodiment, the number of d...

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 an abnormal sound detection method and system of background noise adaption. The system comprises a universal module, also comprises an energy sharp rise detection module comprising a background noise timeout no-updating detection module, a background noise determination module, a background noise energy updating module, an abnormal sound signal energy module, an energy sharp rise determination module, a sharp rise continuous frame determination module and an output energy sharp rise alarm signal module, and further comprises a background noise sharp drop detection module. According to the present invention, the whole processing process is in a time domain and is small in operand and low in complexity by being compared with the frequency domain processing, an energy sharp rise detection method is provided originally, the background noise and the sound signal energy are separated simply, the difference value detection of the sound signal energy and the background noise energy is used, and an abnormal sound alarm threshold can be adjusted automatically according to the change of the background noise energy, and the limitation of a hard threshold is avoided effectively, thereby realizing an abnormal sound detection function of the background noise energy adaption.

Description

[0001] (1) Technical field [0002] The invention relates to the field of sound signal processing, in particular to a background noise self-adaptive abnormal sound detection method and system. [0003] (2) Background technology [0004] In daily life, various emergencies will produce abnormal sounds, which can be detected and analyzed to push alarm information to users, which can effectively prevent abnormal events. For example, the abnormally fluctuating sound signal when the warehouse is stolen, the shouting and fighting sound of the user in the ATM self-service bank when the user is robbed, and the abnormally reduced sound caused by the machine stopping in the factory, etc., can obtain alarm information through abnormal sound detection to reduce the threat to user personal safety and property damage. [0005] A typical abnormal sound detection method and device CN201410850883.5, which uses spectrograms to construct a method for identifying feature matrices, which is relativ...

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): G10L25/78G10L25/51G10L25/21
Inventor 贾永涛周苗刘琛张明
Owner JINAN JOVISION TECH CO LTD
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