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

Method and device for generating sound classifier and detecting abnormal sound, and monitoring system

An abnormal sound and classifier technology, applied in speech analysis, instruments, speech recognition, etc., can solve problems such as abnormal sound and inability to recognize abnormal sound, and achieve the effect of good performance

Active Publication Date: 2016-08-03
CANON KK
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such conventional detection methods cannot identify an unknown kind of abnormal sound, even if the sound is obviously abnormal

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 and device for generating sound classifier and detecting abnormal sound, and monitoring system
  • Method and device for generating sound classifier and detecting abnormal sound, and monitoring system
  • Method and device for generating sound classifier and detecting abnormal sound, and monitoring system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0027] Note that similar reference numbers and letters refer to similar items in the figures, so that once an item is defined in one figure, it need not be discussed in subsequent figures.

[0028] Please also note that in the present disclosure, the terms "first", "second", etc. are only used to distinguish units or steps, and are not intended to indicate chronological order, priority, or importance.

[0029] figure 2 is a block diagram showing an exemplary hardware configuration of a computer system 1000 capable of implementing embodiments of the present invention.

[0030] Such as figure 2 As shown in , computer system 1000 includes computer 1110 . Computer 1110 includes processing unit 1120 connected via system bus 1121, system memory 1130, fixed nonvolatile memory interface 1140, removable nonvolatile memory interface 1150, user input interface...

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 relates to methods and devices for generating a sound classifier and detecting an abnormal sound, and a monitoring system. The sound classifier comprises at least one classifier grade. For generating each sound classifier grade, the method for generating the sound classifier comprises the following steps: generating, based on an input sound sample, a normal sound model; calculating, based on the input sound sample and the normal sound model, a first threshold value, wherein the input sound sample is segmented to a first normal sound sample and a first abnormal sound sample according to the normal sound model and the first threshold value; generating, based on a specific abnormal sound sample and the first abnormal sound sample, an abnormal sound model; and calculating, based on the first normal sound sample and the abnormal sound model, a second threshold value, wherein the first normal sound sample is segmented to a second normal sound sample and a second abnormal sound sample according to the abnormal sound model and the second threshold value. The each classifier grade comprises the normal sound model, the first threshold value, the abnormal sound model and the second threshold value.

Description

technical field [0001] The present invention relates to sound detection, and more particularly to methods and apparatus for generating sound classifiers, and methods and detectors for detecting abnormal sounds. Background technique [0002] Abnormal sound detection is important for surveillance systems. The abnormal sound may be any kind of abnormal sound in general situations, such as a specific kind of abnormal sound (for example, a scream, a gunshot, etc.) and an unknown kind of abnormal sound. [0003] Traditional abnormal sound detection methods usually aim to detect specific kinds of abnormal sounds. However, such conventional detection methods cannot identify an unknown kind of abnormal sound, even if the sound is obviously abnormal. [0004] Recently, in Document 1 (AkinoriIto et al., Detection of Abnormal Sound Using Multi-stage GMM for Surveillance Microphone, 5th International Conference on Information Assurance and Security, 2009), AkinoriIto et al. proposed a ...

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 Patents(China)
IPC IPC(8): G10L15/02G10L15/14
Inventor 胡伟湘刘贺飞穆向禹
Owner CANON KK
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