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

Audio monitoring method and system

A monitoring system and audio technology, applied in the field of monitoring, can solve the problems of difficult sound monitoring and high false alarm rate, and achieve the effects of real and wide sources, lower false alarm rate, and easy implementation

Pending Publication Date: 2020-11-13
南京烽火星空通信发展有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The main purpose of the present invention is to provide an audio monitoring method and system, aiming to solve the technical problems in related technologies that sound monitoring is difficult to realize and the false alarm rate is high

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
  • Audio monitoring method and system
  • Audio monitoring method and system
  • Audio monitoring method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0053] In order to achieve the above object, in one embodiment of the present invention, an audio monitoring method is proposed, comprising the following steps:

[0054] Collect sensitive training data. The event types of this data include five types: distress, crying, pornography, gunshots and absorption;

[0055] According to the type of event, the corresponding weak label is given, and the positioning probability of various sensitive events in each frame of a piece of audio is obtained through the first-level positioning model;

[0056] Then, the type of the sensitive event is judged according to the duration of the location probability under the first specified threshold range.

[0057] Also include the following steps:

[0058] The second judgment is completed by using a discriminant model based on a cyclic neu...

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 audio monitoring method and system. The method comprises the following steps of: collecting sensitive training data, wherein the event types of the data include help seeking, crying, pornography, gunshot and absorption; giving a corresponding weak label according to the type of the event, and acquiring the positioning probability of each type of sensitive event occurringin each frame in a segment of audio through a first-level positioning model; and judging the type of the sensitive event according to the duration of the positioning probability in a first specifiedthreshold range. The detection method has the advantages of wide detection range, high coverage rate, good privacy and the like. The requirement for training data labels is low, the manual marking cost is low, implementation is easy, and the false alarm rate can be reduced by using a two-stage judgment model.

Description

technical field [0001] The invention relates to the technical field of monitoring, in particular to an audio monitoring method and system. Background technique [0002] With the development of artificial intelligence and deep neural networks in the fields of image, video, and voice, there are more and more applications of AI in the field of audio, including sound monitoring, network audio and video recommendation, etc. [0003] At present, video surveillance technology based on image recognition has been relatively mature in some areas of transportation, public security, indoor monitoring, and network monitoring, but there are still some common problems. [0004] The video surveillance currently used in the security field mainly has the following two defects: [0005] (1) Single monitoring category [0006] There are fewer types of sensitive events in video monitoring, and the events are relatively rough, such as passers-by calling for help, indoor abnormalities, etc., whi...

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): G10L15/02G10L15/16G06N3/04G06N3/08
CPCG10L15/02G10L15/16G06N3/08G06N3/045
Inventor 廖闻剑陈眺曲宝珠王康
Owner 南京烽火星空通信发展有限公司
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