Sound masking signal generating method and system

A technology for signal generation and sound masking, which is applied in the fields of sound production equipment, speech analysis, speech recognition, etc., can solve the problems of insufficient confidentiality and low masking efficiency of sound masking signals, and achieve masking efficiency and confidentiality advantages and intelligibility. low effect

Active Publication Date: 2014-06-25
INST OF INFORMATION ENG CHINESE ACAD OF SCI
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a sound masking signal generation method and system to solve the technical problems in the prior art that the sound masking signal masking efficiency is not high and the confidentiality is not good enough

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 masking signal generating method and system
  • Sound masking signal generating method and system
  • Sound masking signal generating method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Embodiment 1 of the present invention provides a sound masking signal generation method, see figure 2 , the method specifically includes:

[0064] Step 201: Record a voice sample of a secret-related person.

[0065] In this step, the voice recorder is first used to record the voice samples of 10 confidential personnel who have the right to participate in the confidential meeting. Due to the existence of background noise, the recorded signal will contain noise and other disturbances, so it is necessary to preprocess the sound sample, including speech enhancement and noise reduction, to obtain a clean sample sound signal of secret personnel.

[0066] Step 202: Establish a sound sample feature model library.

[0067] In this step, the extracted 10 secret-related personnel sample sound signals are trained, and the training adopts the VQ vector quantization method (or can use dynamic event regularization DTW, hidden Markov model HMM, artificial neural network ANN, support...

Embodiment 2

[0077] Embodiment 2 of the present invention provides a sound masking signal generation system, see Figure 8 ,include:

[0078] A model library building unit 801, configured to extract one or more sample sound signals, and establish a sound sample feature model library;

[0079] A target sound source acquisition unit 802, configured to acquire a target sound source signal;

[0080] A sample sound selection unit 803, configured to perform sound recognition on the target sound source signal, and select one or more sample sound signals whose recognition similarity reaches a preset threshold in the sound sample feature model library;

[0081] The sound masking signal unit 804 is configured to scramble and combine the selected sample sound signals to obtain a sound masking signal.

[0082] Preferably, the model library building unit 801 may include:

[0083] The sample sound extraction subunit is used to use the recorder to record one or more secret-related personnel sound samp...

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 provides a sound masking signal generating method and system. The method includes the steps that one or more sample sound signals are extracted, and a sound sample characteristic model base is built; a target sound source signal is obtained; sound recognition is conducted on the target sound source signal, and one or more sample sound signals with recognition similarity reaching a preset threshold value are selected from the sound sample characteristic model base; scrambling combination is conducted on the selected sample sound signals, and sound masking signals are obtained. The sound masking signals generated by the method have similar sound characteristics with the target sound source signal, are low in speech intelligibility, do not contain any information of the target sound source signal, and have larger advantages in masking efficiency and security.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a method and system for generating a sound masking signal. Background technique [0002] Confidential conference room is a place where state secret meetings are held. During the meeting, a large number of state secrets will be generated, processed and stored. Studies have shown that voice is an important form of information leakage, and a method that can effectively protect secret information is urgently needed. Acoustic masking refers to adding a natural or synthetic interference source to cover the target sound source sound through auditory masking. Interference sources are arranged in places where sound leakage and eavesdropping may exist in the conference room to mask useful voices, thereby achieving the purpose of voice privacy. There are many ways of voice leakage, and a single technical means cannot be relied on. However, sound masking technology, as an important m...

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): G10L15/06G10L21/02G10K11/175
Inventor 徐艳云张萌朱大立
Owner INST OF INFORMATION ENG CHINESE ACAD OF SCI
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