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

Sound event detection system and method based on machine learning

A machine learning and event detection technology, applied in instruments, alarms, voice analysis, etc., can solve the problems of low frequency of acoustic events and scarcity of training data, and achieve good robustness

Inactive Publication Date: 2020-07-31
CHONGQING UNIV OF POSTS & TELECOMM
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide a machine learning-based acoustic event detection system and method to solve the problem of model training when the frequency of acoustic events is low and the training data is scarce, thereby improving the accuracy and robustness of acoustic event detection. sex

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
  • Sound event detection system and method based on machine learning
  • Sound event detection system and method based on machine learning
  • Sound event detection system and method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Embodiment 1: The network parameters used for system modeling in this embodiment are shown in Table 1, and the performance of the system is measured with an equal error rate (Equalerror rate, EER) as an index.

[0049] Table 1 Impact of data augmentation methods on EER

[0050]

[0051] Table 2 Effect of models with different structures on EER

[0052]

[0053] In this embodiment, the specific parameters of the DNN network and CRNN network models are shown in Table 4.

[0054] Table 4 Specific parameters of the network model

[0055]

[0056] It can be seen from Tables 1-3 that the proposed data enhancement method can significantly improve the performance of the system in quiet scenes and noisy scenes, so it can be concluded that the model proposed by the present invention can significantly improve the performance of the system.

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 a sound event detection system and method based on machine learning, which belong to the technical field of audio detection and fault detection. The system comprises a pickupmodule, an identification module and a background management module, wherein the pickup module is used for completing audio acquisition and is composed of a microphone and a corresponding peripheral circuit; the identification module is composed of an identification model based on a machine learning method and completes the real-time identification function of audio; and the background managementmodule is used for completing display of identification results. The system provided by the invention can detect the sound event more accurately and has better robustness under the condition of noiseinterference.

Description

technical field [0001] The invention belongs to the technical field of audio detection and fault detection, and relates to an acoustic event detection method based on machine learning. Background technique [0002] Acoustic event detection technology detects the type and occurrence time of the acoustic event in real time, so as to detect and alarm the emergency in the monitoring system. At present, acoustic event detection is mainly used in smart home, industrial flaw detection, fault detection and other fields. Existing technologies generally use methods such as Gaussian Mixture Model (GMM) and Markov models to classify real-time audio. However, there are some problems in the current technology, such as: the inaccurate classification and detection models lead to false positives and missed negatives of acoustic events in practical applications; the model training stage requires a large amount of data for training, and the frequency of acoustic events is often relatively low...

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): G10L15/06G10L15/16G10L15/20G10L25/24G08B21/18
CPCG10L15/063G10L15/16G10L15/20G10L25/24G08B21/18G10L2015/0631
Inventor 万同堂周翊
Owner CHONGQING UNIV OF POSTS & TELECOMM
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