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

System and method of detecting keyboard tapping content by using sound signals

A sound signal and keyboard technology, which is applied in the field of using sound signals to detect the content of keyboard strokes, can solve the problems of high condition requirements, high computing costs, and high number of detection devices, and achieves improved accuracy, accurate recognition, and good recognition stability. Effect

Inactive Publication Date: 2016-11-16
SHENZHEN UNIV
View PDF0 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above methods either need to use special signal acquisition technology and have relatively high requirements on environmental conditions, or require a relatively large number of detection equipment and high calculation costs, which are not universal

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
  • System and method of detecting keyboard tapping content by using sound signals
  • System and method of detecting keyboard tapping content by using sound signals
  • System and method of detecting keyboard tapping content by using sound signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to facilitate the understanding of those skilled in the art, the present invention will be further described below in conjunction with the accompanying drawings and examples.

[0038] A method for detecting keyboard strokes based on sound signals, the steps comprising:

[0039] S1. The sound collection device collects the sound signal generated by tapping the keyboard, and preprocesses the sound signal;

[0040] S2. Using the energy detection algorithm to extract the signal segment of the keystroke peak of each tapping action;

[0041] S3. Calculate the short-term energy normalized value of each tap action and classify it using the time difference as a feature

[0042] S4. Feedback the response information for the recognition result, adjust the parameters of the classification algorithm, and further improve the accuracy.

[0043] Specifically, in step S1, the sound collection device can be an existing smart phone, a microphone installed on a raspberry pie, ...

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 the information processing technology, and discloses a method and a system for recognizing a keyboard tapping content based on sound signals. According to the method, a sound signal acquisition device is used for gathering sound signals generated by keystroke, pretreatment is carried out on the sound signals, and the purpose of recognizing a single key and a combined key is achieved. The method mainly comprises steps: a sound gathering device is used for gathering sound signals for keyboard tapping on a desk in specific layout, and through adopting methods such as Butterworth, denoising is carried out on the gathered sound signals; a short-time energy value for keystroke at each time is calculated, normalization processing is carried out, and the value serves as a feature; a time difference for receiving by two microphones is adopted as another feature to be fused with the above feature; and a classification algorithm is used for classifying the features, and thus, tapping of a single key or a combined key can be recognized.

Description

technical field [0001] The invention relates to the field of recognition based on sound signals, in particular to a method and system for detecting keyboard stroke content by using sound signals. Background technique [0002] Today, with the development of various signal detection systems, keyboard keystroke recognition is becoming more and more important. With different signal detections, we were able to reproduce the keystrokes. With the development of information security technology and people's higher and higher requirements for information confidentiality, being able to detect signals and do a good job of anti-detection is exactly what needs to be considered at the moment. While doing a good job of detecting keystrokes, design better ways to protect people's privacy. In the existing indoor environment, the sound generated by keystrokes, the influence of gestures on indoor WiFi signals, and the research on keystroke power can all be used as eavesdropping technology, an...

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): G10L15/02G10L25/51
CPCG01S5/18G06F3/043G10L25/48G10L25/51G10L15/02
Inventor 伍楷舜王璐王建
Owner SHENZHEN UNIV
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