CN104575486A - Sound leakage protection method and system based on sound masking principle - Google Patents
Sound leakage protection method and system based on sound masking principle Download PDFInfo
- Publication number
- CN104575486A CN104575486A CN201410822950.2A CN201410822950A CN104575486A CN 104575486 A CN104575486 A CN 104575486A CN 201410822950 A CN201410822950 A CN 201410822950A CN 104575486 A CN104575486 A CN 104575486A
- Authority
- CN
- China
- Prior art keywords
- sound
- signal
- interference
- voice signal
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000873 masking effect Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000005236 sound signal Effects 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 239000011521 glass Substances 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 230000002123 temporal effect Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 238000004378 air conditioning Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 239000005357 flat glass Substances 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 206010038743 Restlessness Diseases 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- LHMQDVIHBXWNII-UHFFFAOYSA-N 3-amino-4-methoxy-n-phenylbenzamide Chemical compound C1=C(N)C(OC)=CC=C1C(=O)NC1=CC=CC=C1 LHMQDVIHBXWNII-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Landscapes
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
The invention provides a sound leakage protection system based on the sound masking principle. The system comprises a sound monitoring unit, a sound disturbing unit and a center control management unit. The invention further provides a sound leakage protection method based on the sound masking principle. The method comprises steps as follows: the sound monitoring unit is adopted to collect a sound signal, and A-weighting sound pressure level intensity is obtained; whether the sound signal is a voice signal is judged, if the sound signal is the voice signal and the A-weighting sound pressure level intensity exceeds a preset threshold value in a period, a warning signal is emitted; the center control management unit performs analysis and feature extraction on the voice signal, generates a disturbing signal and sends the disturbing signal to the sound disturbing unit; the sound disturbing unit adopts the disturbing signal to perform sound disturbing on each area. According to the method and the system, a masking signal processed in real time has higher relevance with a target voice, the masking effect is better, and general privacy can be protected better.
Description
Technical field
The present invention relates to voice process technology field, be specifically related to the sound leakage means of defence based on sound masking principle and system.
Background technology
Phonetic sound is as the important carrier of people's information interchange and transmission, and there is occasion maximum, the quantity of information of carrying is also abundant.The leakage of sensitive sound information then can cause the destruction of speech privacy.When people have conversation in places such as rooms, create a large amount of acoustic informations.Inside plant condition and security situation, be directly connected to the safety of content of speaking.In order to improve speech privacy and security, need to carry out acoustic intelligence leakage protection.
Sound leakage guard system is as a part for inside plant, and the acoustic intelligence that effectively can produce people's everyday life, store and process carries out security protection.Existing sound leakage guard system, comprises sound collector, central processing unit and sound interference device.But sound interference device only includes voice interference unit in existing system, not involving vibrations interference unit, then existing system can not prevent the eavesdropping of laser eavesdropping, pipe vibration and wall vibrations eavesdropping etc., and voice signal still can leak.And existing system adopts traditional white noise or pink noise masking signal, but due to this masking signal and the masked sound-source signal degree of correlation low, then restore masked sound-source signal easily via after some simply process.
Summary of the invention
For the defect of prior art, the invention provides a kind of sound leakage means of defence based on sound masking principle and system, by carrying out Speech processing to voice signal, obtain the sound masking signal close with targeted voice signal, and produce spatial sound interference and vibration interference for voice signal, make system masking effect good, be not easy to be reduced out targeted voice signal.
First aspect, the invention provides a kind of sound leakage guard system based on sound masking principle, described system comprises: sound monitoring means, sound interference unit and middle control administrative unit;
Sound monitoring means, is connected with described middle control administrative unit, differentiates and sound and light alarm for sound collection, speech detection, sound pressure level;
Sound interference unit, is connected with described middle control administrative unit, for carrying out airborne sound interference and vibrating transaudient interference;
Middle control administrative unit, is connected with described sound interference unit respectively with described sound monitoring means, for providing man-machine interface, and controls described sound monitoring means and the collaborative work of described sound interference unit.
Preferably, described acoustical monitoring systems, specifically for:
Sound signal collecting, weighted filtering, octave analysis, sound-pressure-level measurement and speech detection.
Preferably, described sound interference unit comprises: spatial sound interference module, pipe vibration interference module, glass vibration interference module and wall vibrations interference module;
Spatial sound interference module, is installed on outside room building enclosure, for by producing voice masking signal, disturbs air-borne sound to leak;
Pipe vibration interference module, is installed on and imports and exports through the pipeline of room building enclosure, new wind and air-conditioning, for by producing vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because pipe vibration is transaudient from leaking;
Glass vibration interference module, is installed on the window-glass of house interior, for by producing vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because of laser eavesdropping from leaking;
Wall vibrations interference module, is installed on the wall at setting position, for by producing vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because of vibration wiretap from leaking.
Preferably, described system also comprises network element, for connecting described sound interference unit and described middle control administrative unit, described sound interference unit is communicated by procotol with described middle control administrative unit.
Second aspect, the invention provides a kind of sound leakage means of defence based on sound masking principle, described method comprises:
Adopt sound monitoring means to gather voice signal, and obtain A weighted sound pressure level intensity;
Judge whether described voice signal is voice signal, if described voice signal is voice signal and in a period of time, described A weighted sound pressure level intensity exceedes default threshold value, then send alarm signal;
Middle control administrative unit is analyzed and feature extraction described voice signal, produces undesired signal, and described undesired signal is sent to sound interference unit;
Sound interference unit adopts described undesired signal to carry out sound interference to each region.
Preferably, described method also comprises:
Middle control administrative unit timed sending heartbeat signal, to sound interference unit, if do not receive the response signal of described heartbeat signal in the schedule time, then judges that described sound interference unit breaks, and sends alarm signal.
Preferably, described employing sound monitoring means gathers voice signal, and obtains A weighted sound pressure level intensity, comprising:
Data acquisition is carried out to voice signal, obtains instantaneous sound pressure level intensity level;
Octave analysis is carried out to described voice signal, obtains the sound pressure level intensity in different frequency bands;
Weighted filtering is carried out to described voice signal, obtains A weighted sound pressure level intensity level.
Preferably, describedly judge whether described voice signal is voice signal, comprising:
Described voice signal is divided into some frames;
Calculate the short-time energy of every frame voice signal, and the short-time zero-crossing rate of every frame voice signal;
Utilize double threshold method, judge whether described voice signal is voice signal.
Preferably, described middle control administrative unit is analyzed and feature extraction described voice signal, produces undesired signal, and described undesired signal is sent to sound interference unit, comprising:
Described voice signal is analyzed, extracts temporal signatures and the frequency domain character of described voice signal;
Based on described temporal signatures and frequency domain character, described voice signal is reversed and scramble, produce sound masking signal;
Described sound masking signal is sent to the spatial sound interference module in sound interference unit, and controls pipeline vibration interference module, glass vibration interference module and wall vibrations interference module and start working.
Preferably, described sound interference unit adopts described undesired signal to carry out sound interference to each region, comprising:
Spatial sound interference module, adopts the sound masking signal received, carries out sound interference;
Pipe vibration interference module, glass vibration interference module and wall vibrations interference module, according to the control of middle control administrative unit, carry out vibration interference.
As shown from the above technical solution, the invention provides a kind of sound leakage means of defence based on sound masking principle and system, by carrying out Speech processing to voice signal, obtain the sound masking signal close with targeted voice signal, and produce spatial sound interference and vibration interference for voice signal, make system masking effect good, be not easy to be reduced out targeted voice signal.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these figure.
Fig. 1 is the structural representation of the sound leakage guard system based on sound masking principle that one embodiment of the invention provides;
Fig. 2 is the S3C2410 minimum system structural representation that another embodiment of the present invention provides;
Fig. 3 is the schematic flow sheet of the sound leakage means of defence based on sound masking principle that one embodiment of the invention provides;
Fig. 4 is the workflow schematic diagram of the sound monitoring means that another embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, be the structural representation of the sound leakage guard system based on sound masking principle that one embodiment of the invention provides, this system comprises sound monitoring means 101, sound interference unit 102 and middle control administrative unit 103.
Sound monitoring means 101, is connected with described middle control administrative unit, differentiates and sound and light alarm for sound collection, speech detection, sound pressure level.
Sound interference unit 102, is connected with described middle control administrative unit, for carrying out airborne sound interference and vibrating transaudient interference.
Middle control administrative unit 103, is connected with described sound interference unit respectively with described sound monitoring means, for providing man-machine interface, and controls described sound monitoring means and the collaborative work of described sound interference unit.
Specifically, sound monitoring means 101, adopt Distributed Design, be installed on indoor, by gathering the voice signal of current indoor and calculating A weighted sound pressure level intensity, send acousto-optic hint when sound pressure level intensity exceedes defined threshold, if indoor sound pressure level intensity continuous exceedes threshold value, send alarm signal to middle control and management system, thus control sound interference system works.In order to improve the specific aim of protection, sound monitoring modular have employed speech recognition algorithm, when indoor sound pressure level intensity exceedes threshold value, judges whether current sound is voice signal, if other non-voice class back drops then do not send alarm.Then sound monitoring means 101 is mainly used in sound signal collecting, weighted filtering, octave analysis, sound-pressure-level measurement and speech detection.
Because sound wave is mechanical wave, the vibration of wall, pipeline, door and window etc. can be caused in its transmitting procedure, and then expand the scope of acoustic intelligence propagation, therefore sound interference unit 102 comprises spatial sound interference units and the large class of chatter interference units two, and sound interference unit 102 specifically comprises:
(1) spatial sound interference module, is installed on outside room building enclosure, for by producing voice masking signal, prevents air-borne sound from leaking.
(2) pipe vibration interference module, is installed on and imports and exports through the pipeline of room building enclosure, new wind and air-conditioning, for by producing vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because pipe vibration is transaudient from leaking.
(3) glass vibration interference module, is installed on the window-glass of house interior, for by producing vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because of laser eavesdropping from leaking.
(4) wall vibrations interference module, is installed on the wall at setting position, for by producing vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because of vibration wiretap from leaking.
Wherein, spatial sound interference module is used for carrying out the transaudient interference in space, and pipe vibration interference module, glass vibration interference module and wall vibrations interference module are used for carrying out vibrating transaudient interference, vibrating transaudient interference is the interference implemented for laser eavesdropping, pipe vibration eavesdropping and wall vibrations eavesdropping.
And middle control administrative unit 103 provides man-machine interface, and also collaborative sound monitoring means 101 and sound interference unit 102 work.Middle control and management system adopts standardised networks interface, be connected with sound monitoring means 101 and sound interference units 102 respectively: four road sound collection/monitorings input (major function is sound collection, monitoring, warning), four mouthfuls of (16 tunnel) sound interference export (interference of major control air-borne sound and vibration interference).When indoor sound pressure level intensity exceedes defined threshold and is voice signal, sound monitoring unit 101 sends alarm signal to middle control administrative unit 103, middle control administrative unit 103 carries out Macro or mass analysis after receiving the cue of each road, when masking sound opened by needs, send control command by procotol to sound interference unit 102, open air-borne sound and shelter interference module and pipe vibration interference module, glass vibration interference module, wall vibrations interference module.Continue to monitor current indoor sound pressure level intensity until it stops launching back drop after recovering normal sound pressure level intensity simultaneously.
It should be noted that, because sound interference unit 102 is communicated by procotol with middle control administrative unit 103, therefore this system also comprises network element, for connecting sound interference unit 102 and middle control administrative unit 103, sound interference unit 102 is communicated by procotol with middle control administrative unit 103.
In the present embodiment; this system can monitor the sound pressure level intensity in room; when exceeding preset value; send warning; and produce the air-borne sound interference noise relevant to voice; and for the vibration noise of the weak links such as door, window, pipeline, thus reach the object of protection house interior sensitive sound information.Sound monitoring means uses the undesired signal that voice are relevant, can also process by the indoor voice signal of Real-time Collection, is converted into masking signal.The masking signal of real-time process and target voice have the higher degree of correlation, and masking effect is better, better can realize the protection to general privacy.
Below, by a specific embodiment, a kind of sound leakage guard system based on sound masking principle is described.Wherein, middle control administrative unit adopts S3C2410 embedded platform, runs built-in Linux operating system.Sound monitoring means adopts MSP430 series monolithic as coprocessor, and sound interference unit adopts WT588D as sounding module.When main control platform collect current indoor target voice and after carrying out feature extraction coupling, the best masking sound source information obtained is sent to masking sound generation module, masking sound generation module selects corresponding masking sound in sheltering in sound source of prestoring, and carries out interference and launches.In emission process, communicate with main control platform all the time, obtain the sound conditions information of current indoor, comprise sound pressure level intensity and target voice change, thus carry out Adaptive matching.For preventing masking sound module to meet accident broken string, heartbeat signal is transmitted in main control platform and the timing of masking sound intermodule.And adjust the duty of masking sound module in real time.
Wherein, S3C2410 processor is based on ARM920T processor core, adopts 32 8-digit microcontrollers of 0.18um manufacturing process.ARM920T achieves memory management unit (MemoryManagement Unit, be called for short MMU), center line (Advanced Microcontroller BusArchitecture, AMBA) and Harvard framework Harvard cache hierarchy structure on sheet.This structure has independently 16KB instruction cache Cache and 16KB data Cache, and each is be made up of the row of 8 word lengths.
In order to reduce the cost of whole system, S3C2410 provides following abundant internal unit: the Timer of lcd controller, NAND Flash controller, sdram controller, 3 passage UART, 4 passage DMA, 4 road band PWM, I/O mouth, RTC, 8 10, tunnel ADC, Touch Screen interface, IIC-BUS interface, IIS-BUS interface, 2 usb hosts, 1 USB device, SD main frame and MMC interface, 2 road SPI.By providing a series of complete system peripheral, S3C2410 greatly reduces the cost of whole system, eliminates the needs into system configuration additional devices.
Wherein, middle control administrative unit adopts embedded system, can carry out flexible customization according to application scenario.Power consumption of embedded system is low, volume is little, specificity is strong.Being completed by board of tasks many in computing machine can be integrated in chip internal, thus be conducive to Embedded System Design and be tending towards miniaturization.In order to improve execution speed and system reliability, the software solidification in embedded system is in single-chip microcomputer itself.Desktop Linux OS is carried out cutting amendment and forms by the embedded OS that product runs, and makes it to run on embedded computer system.Built-in Linux had both inherited open source code resource unlimited on network, had again the characteristic of embedded OS.
Specifically, the minimum system 28M RAM of the S3C2410 that middle control administrative unit adopts and 256M Flash forms, and its block diagram as shown in Figure 2.
And communicated by procotol due to sound interference unit and middle control administrative unit, therefore need to increase network element.In the present embodiment, network element adopts CS8900A chip, and this chip is 10M network chip.The User Datagram Protocol of standard (UserDatagram Protocol is called for short UDP) is adopted to communicate with middle keyholed back plate platform.For ensureing sound interference unit and being communicated with between middle control administrative unit, middle control administrative unit timed sending heartbeat signal also receives the response of sound interference unit, if a certain interference module is without feedback response, then sends broken string alarm signal.
Based on said system, as shown in Figure 3, be the schematic flow sheet of the sound leakage means of defence based on sound masking principle that one embodiment of the invention provides, the method comprises:
301, adopt sound monitoring means to gather voice signal, and obtain A weighted sound pressure level intensity.
302, judge whether described voice signal is voice signal, if described voice signal is voice signal and in a period of time, described A weighted sound pressure level intensity exceedes default threshold value, then send alarm signal.
Wherein, the distinguishable voice of sound monitoring system and ground unrest, only monitor for voice signal; When indoor voice sound pressure level exceedes predetermined threshold value, system alarm; Type of alarm is light prompt or auditory tone cues.
303, middle control administrative unit is analyzed and feature extraction described voice signal, produces undesired signal, and described undesired signal is sent to sound interference unit.
304, sound interference unit adopts described undesired signal to carry out sound interference to each region.
Alternatively, the method also comprises:
Middle control administrative unit timed sending heartbeat signal, to sound interference unit, if do not receive the response signal of described heartbeat signal in the schedule time, then judges that described sound interference unit breaks, and sends alarm signal.
In the present embodiment, as shown in Figure 4, step 301 specifically comprises the steps:
401, sound monitoring means carries out data acquisition to voice signal, obtains instantaneous sound pressure level intensity level.
Wherein, the measurement of sound pressure level comprises instantaneous sound pressure level, equivalence sound pressure level, peak sound pressure level etc. continuously, adopts instantaneous sound pressure level intensity level as the standard weighing indoor sound pressure level intensity in the method.
402, octave analysis is carried out to described voice signal, obtain the sound pressure level intensity in different frequency bands.
Specifically, people's ear is not single-frequency to the resolution characteristic of sound, but frequency band.Octave analysis is mainly used in dividing signal by frequency characteristic, makes it the frequency discrimination characteristic meeting people's ear.To measure the energy distribution of voice signal in different frequency bands, thus the sound pressure level intensity in display current indoor different frequency bands.
403, weighted filtering is carried out to described voice signal, obtain A weighted sound pressure level intensity level.
In this step, because people's ear is different to the response of different frequency sound, in order to the subjective loudness sensation enabling instrument measurements directly reflect people, usually by the sound pressure level that records by a rectangular window, each frequency component in sound wave is weighted process.This wave filter is called as " weighting network ".Conventional weighted wave filter comprises A, B, C, D tetra-kinds, and wherein the frequency decay of A weighted meets people's ear, therefore in measuring chamber, during sound pressure level, usually uses A weighted sound pressure level to represent.
In the present embodiment, in step 302, sound monitoring means needs to judge whether described voice signal is voice signal, and the mode that speech recognition algorithm used in this step adopts short-time average energy method and short-time average zero-crossing rate method to combine, detect voice signal by double threshold method.Comprise:
A01, described voice signal is divided into some frames.
A02, calculate the short-time energy of every frame voice signal, and the short-time zero-crossing rate of every frame voice signal.
Wherein, if the n-th frame voice signal x
nthe short-time energy E of (m)
nrepresent, its computing formula is such as formula shown in (1):
If voice signal x
nthe short-time zero-crossing rate Z of (m)
nrepresent, its computing formula is such as formula shown in (2):
Wherein, sgn [] is-symbol function, namely such as formula shown in (3):
A03, utilize double threshold method, judge whether described voice signal is voice signal.
In this step, higher thresholding amp1, a zcr1 is chosen according to the voice short-time energy of voice signal and short-time zero-crossing rate, and determine lower thresholding amp2, a zcr2 according to the average energy of the ground unrest of estimation and average zero-crossing rate, if the short-time energy of the voice signal detected is greater than higher thresholding, then judge that voice start.If after a period of time, short-time energy is less than lower thresholding, then judge that voice terminate.If voice start rear deficiency section time span, short-time energy is just less than comparatively low threshold, then judge that section of sound is just as noise section.For short-time zero-crossing rate, its judgment criterion is analogous to short-time energy determining method.Judge in conjunction with short-time energy and short-time zero-crossing rate, judged result can be made comparatively accurate.
In the present embodiment, the detailed process of step 303 comprises:
B01, described voice signal to be analyzed, extract temporal signatures and the frequency domain character of described voice signal.
In this step, speech waveform is the continuous function of time, therefore should be noted that the gradually transition of a sound to another sound.The characteristic of voice signal is time dependent.Such as, voiced sound is different with the excitation of voiceless sound, is transitioned into voiceless sound from voiced sound, will change excitation accordingly; The amplitude of voice signal changes very significantly along with the time has; Even if be both voiced sound, its fundamental frequency is also different.These time-varying characteristics of voice signal in waveform can both observation clearly out.But the characteristic of voice signal is more over time, roughly can think that the characteristic of voice signal is changeless substantially in every 10-30ms short time interval.Therefore, therefrom can intercept one section and carry out Short Time Fourier Analysis, obtain the short-time spectrum of voice.
The perception of voice signal and human auditory system have spectrum analysis function and are closely related, and different phonetic is determined by sound channel difformity and size, and this just determines them and has different spectral characteristics.Sound channel has one group of resonant frequency, is called resonance peak.Different voice correspond to a different set of formant parameter, and spectral characteristic is just main reflects the diverse location of these resonance peaks and the frequency span at each peak.
B02, based on described temporal signatures and frequency domain character, described voice signal to be reversed and scramble, produce sound masking signal.
In this step, carry out interference to indoor sensitive sound signal and need choose best sound masking signal, namely under the condition reaching same masking effect, signal transmission power is minimum.
Good sound masking signal should be higher with the degree of correlation of masked sound source, and the masking noise namely adopting voice to be correlated with can realize interference when noise emission intensity is lower.Be not difficult to judge directly to adopt the voice of speaker's (target sound source) best masking effect should be had as sheltering sound source in real time after conversion, but implement sound masking for room, speaker's voice itself have certain confidentiality, be not suitable for as sheltering sound source, in order to meet masking sound without the meaning of one's words and unnoticed requirement, the interference sound source making masking sound can not become new, obtain after the best shelters sound source, the voice signal that need continue sheltering sound source processes.This method adopts audio signal processing method, produces the sound masking signal the most close with target voice to sheltering that sound source is reversed, after scramble.
B03, the spatial sound interference module described sound masking signal is sent in sound interference unit, and control pipeline vibration interference module, glass vibration interference module and wall vibrations interference module and start working.
And step 304, detailed process is as follows:
Spatial sound interference module, adopts the sound masking signal received, carries out sound interference;
Pipe vibration interference module, glass vibration interference module and wall vibrations interference module, according to the control of middle control administrative unit, carry out vibration interference.
Present embodiments provide a kind of sound leakage means of defence based on sound masking principle, by carrying out Speech processing to voice signal, obtain the sound masking signal close with targeted voice signal, and produce spatial sound interference and vibration interference for voice signal, make system masking effect good, be not easy to be reduced out targeted voice signal.
Above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that; It still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. based on a sound leakage guard system for sound masking principle, it is characterized in that, described system comprises: sound monitoring means, sound interference unit and middle control administrative unit;
Sound monitoring means, is connected with described middle control administrative unit, differentiates and sound and light alarm for sound collection, speech detection, sound pressure level;
Sound interference unit, is connected with described middle control administrative unit, for carrying out airborne sound interference and vibrating transaudient interference;
Middle control administrative unit, is connected with described sound interference unit respectively with described sound monitoring means, for providing man-machine interface, and controls described sound monitoring means and the collaborative work of described sound interference unit.
2. system according to claim 1, is characterized in that, described acoustical monitoring systems, specifically for:
Sound signal collecting, weighted filtering, octave analysis, sound-pressure-level measurement and speech detection.
3. system according to claim 1, is characterized in that, described sound interference unit comprises: spatial sound interference module, pipe vibration interference module, glass vibration interference module and wall vibrations interference module;
Spatial sound interference module, is installed on outside room building enclosure, and for generation of voice masking signal, interference air-borne sound leaks;
Pipe vibration interference module, is installed on and imports and exports through the pipeline of room building enclosure, new wind and air-conditioning, for generation of vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because pipe vibration is transaudient from leaking;
Glass vibration interference module, is installed on the window-glass of house interior, for generation of vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because of laser eavesdropping from leaking;
Wall vibrations interference module, is installed on the wall at setting position, for generation of vibration interference signal, prevents the responsive acoustic intelligence in indoor caused because of vibration wiretap from leaking.
4. system according to claim 1, it is characterized in that, described system also comprises network element, for connecting described sound interference unit and described middle control administrative unit, described sound interference unit is communicated by procotol with described middle control administrative unit.
5. based on a sound leakage means of defence for sound masking principle, it is characterized in that, described method comprises:
Adopt sound monitoring means to gather voice signal, and obtain A weighted sound pressure level intensity;
Judge whether described voice signal is voice signal, if described voice signal is voice signal and in a period of time, described A weighted sound pressure level intensity exceedes default threshold value, then send alarm signal;
Middle control administrative unit is analyzed and feature extraction described voice signal, produces undesired signal, and described undesired signal is sent to sound interference unit;
Sound interference unit adopts described undesired signal to carry out sound interference to each region.
6. method according to claim 5, is characterized in that, described method also comprises:
Middle control administrative unit timed sending heartbeat signal, to sound interference unit, if do not receive the response signal of described heartbeat signal in the schedule time, then judges that described sound interference unit breaks, and sends alarm signal.
7. method according to claim 5, is characterized in that, described employing sound monitoring means gathers voice signal, and obtains A weighted sound pressure level intensity, comprising:
Data acquisition is carried out to voice signal, obtains instantaneous sound pressure level intensity level;
Octave analysis is carried out to described voice signal, obtains the sound pressure level intensity in different frequency bands;
Weighted filtering is carried out to described voice signal, obtains A weighted sound pressure level intensity level.
8. method according to claim 5, is characterized in that, describedly judges whether described voice signal is voice signal, comprising:
Described voice signal is divided into some frames;
Calculate the short-time energy of every frame voice signal, and the short-time zero-crossing rate of every frame voice signal;
Utilize double threshold method, judge whether described voice signal is voice signal.
9. method according to claim 5, is characterized in that, described middle control administrative unit is analyzed and feature extraction described voice signal, produces undesired signal, and described undesired signal is sent to sound interference unit, comprising:
Described voice signal is analyzed, extracts temporal signatures and the frequency domain character of described voice signal;
Based on described temporal signatures and frequency domain character, described voice signal is reversed and scramble, produce sound masking signal;
Described sound masking signal is sent to the spatial sound interference module in sound interference unit, and controls pipeline vibration interference module, glass vibration interference module and wall vibrations interference module and start working.
10. method according to claim 5, is characterized in that, described sound interference unit adopts described undesired signal to carry out sound interference to each region, comprising:
Spatial sound interference module, adopts the sound masking signal received, carries out sound interference;
Pipe vibration interference module, glass vibration interference module and wall vibrations interference module, according to the control of middle control administrative unit, carry out vibration interference.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410822950.2A CN104575486B (en) | 2014-12-25 | 2014-12-25 | Sound leakage protection method and system based on the principle of acoustic masking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410822950.2A CN104575486B (en) | 2014-12-25 | 2014-12-25 | Sound leakage protection method and system based on the principle of acoustic masking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104575486A true CN104575486A (en) | 2015-04-29 |
| CN104575486B CN104575486B (en) | 2019-04-02 |
Family
ID=53091390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410822950.2A Expired - Fee Related CN104575486B (en) | 2014-12-25 | 2014-12-25 | Sound leakage protection method and system based on the principle of acoustic masking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104575486B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992710A (en) * | 2015-06-18 | 2015-10-21 | 惠州Tcl移动通信有限公司 | Method for finding article based on intelligent device and intelligent device |
| CN105185370A (en) * | 2015-08-10 | 2015-12-23 | 电子科技大学 | Sound masking door |
| CN106558303A (en) * | 2015-09-29 | 2017-04-05 | 苏州天声学科技有限公司 | Array sound mask device and sound mask method |
| CN106601230A (en) * | 2016-12-19 | 2017-04-26 | 苏州金峰物联网技术有限公司 | Logistics sorting place name speech recognition method, system and logistics sorting system based on continuous Gaussian mixture HMM |
| CN111614829A (en) * | 2020-05-21 | 2020-09-01 | 维沃移动通信有限公司 | Electronic equipment and anti-eavesdropping method |
| US11205439B2 (en) | 2019-11-22 | 2021-12-21 | International Business Machines Corporation | Regulating speech sound dissemination |
| CN116320123A (en) * | 2022-08-11 | 2023-06-23 | 荣耀终端有限公司 | Voice signal output method and electronic equipment |
| CN116524891A (en) * | 2023-05-08 | 2023-08-01 | 拓达世纪信息产业有限公司 | AI sound masking system and secret meeting room thereof |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110441A (en) * | 2010-12-22 | 2011-06-29 | 中国科学院声学研究所 | Method for generating sound masking signal based on time reversal |
| CN102543066A (en) * | 2011-11-18 | 2012-07-04 | 中国科学院声学研究所 | Target voice privacy protection method and system |
| CN202383998U (en) * | 2011-12-22 | 2012-08-15 | 国家保密科学技术研究所 | Sound masking system |
| CN1505811B (en) * | 2001-02-26 | 2013-05-01 | 777388安大略有限公司 | Networked sound masking and paging system |
| CN103098123A (en) * | 2010-09-08 | 2013-05-08 | 雅马哈株式会社 | Sound masking device and sound masking method |
| CN103189912A (en) * | 2010-10-21 | 2013-07-03 | 雅马哈株式会社 | Voice processor and voice processing method |
| CN203273230U (en) * | 2013-04-28 | 2013-11-06 | 北京天大清源通信科技股份有限公司 | Fixing clamp and audio interference device with same |
| JP2013231987A (en) * | 2013-06-24 | 2013-11-14 | Yamaha Corp | Conversation leakage prevention device |
| CN103886858A (en) * | 2014-03-11 | 2014-06-25 | 中国科学院信息工程研究所 | Sound masking signal generating method and system |
| RU2014113010A (en) * | 2014-04-03 | 2014-08-10 | Закрытое акционерное общество "Защита электронных технологий" | ACOUSTIC SPEECH INFORMATION LEAKAGE CHANNEL VIBRATION NOISE |
| CN104142635A (en) * | 2013-05-10 | 2014-11-12 | 北京天大清源通信科技股份有限公司 | Sound masking system with monitoring center |
-
2014
- 2014-12-25 CN CN201410822950.2A patent/CN104575486B/en not_active Expired - Fee Related
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1505811B (en) * | 2001-02-26 | 2013-05-01 | 777388安大略有限公司 | Networked sound masking and paging system |
| CN103098123A (en) * | 2010-09-08 | 2013-05-08 | 雅马哈株式会社 | Sound masking device and sound masking method |
| CN103189912A (en) * | 2010-10-21 | 2013-07-03 | 雅马哈株式会社 | Voice processor and voice processing method |
| CN102110441A (en) * | 2010-12-22 | 2011-06-29 | 中国科学院声学研究所 | Method for generating sound masking signal based on time reversal |
| CN102543066A (en) * | 2011-11-18 | 2012-07-04 | 中国科学院声学研究所 | Target voice privacy protection method and system |
| CN202383998U (en) * | 2011-12-22 | 2012-08-15 | 国家保密科学技术研究所 | Sound masking system |
| CN203273230U (en) * | 2013-04-28 | 2013-11-06 | 北京天大清源通信科技股份有限公司 | Fixing clamp and audio interference device with same |
| CN104142635A (en) * | 2013-05-10 | 2014-11-12 | 北京天大清源通信科技股份有限公司 | Sound masking system with monitoring center |
| JP2013231987A (en) * | 2013-06-24 | 2013-11-14 | Yamaha Corp | Conversation leakage prevention device |
| CN103886858A (en) * | 2014-03-11 | 2014-06-25 | 中国科学院信息工程研究所 | Sound masking signal generating method and system |
| RU2014113010A (en) * | 2014-04-03 | 2014-08-10 | Закрытое акционерное общество "Защита электронных технологий" | ACOUSTIC SPEECH INFORMATION LEAKAGE CHANNEL VIBRATION NOISE |
Non-Patent Citations (3)
| Title |
|---|
| 王玥等: "《时间反转语音掩蔽的语音信号可懂度的客观评价方法》", 《网络新媒体技术》 * |
| 苗春卫等: "《保密会议室声音防护技术研究》", 《保密科学技术》 * |
| 蒋斌等: "《语音的掩蔽声实验研究》", 《声学技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104992710A (en) * | 2015-06-18 | 2015-10-21 | 惠州Tcl移动通信有限公司 | Method for finding article based on intelligent device and intelligent device |
| CN105185370A (en) * | 2015-08-10 | 2015-12-23 | 电子科技大学 | Sound masking door |
| CN105185370B (en) * | 2015-08-10 | 2019-02-12 | 电子科技大学 | A kind of sound masking door |
| CN106558303A (en) * | 2015-09-29 | 2017-04-05 | 苏州天声学科技有限公司 | Array sound mask device and sound mask method |
| CN106601230A (en) * | 2016-12-19 | 2017-04-26 | 苏州金峰物联网技术有限公司 | Logistics sorting place name speech recognition method, system and logistics sorting system based on continuous Gaussian mixture HMM |
| US11205439B2 (en) | 2019-11-22 | 2021-12-21 | International Business Machines Corporation | Regulating speech sound dissemination |
| CN111614829A (en) * | 2020-05-21 | 2020-09-01 | 维沃移动通信有限公司 | Electronic equipment and anti-eavesdropping method |
| CN111614829B (en) * | 2020-05-21 | 2021-07-23 | 维沃移动通信有限公司 | Electronic equipment and anti-eavesdropping method |
| CN116320123A (en) * | 2022-08-11 | 2023-06-23 | 荣耀终端有限公司 | Voice signal output method and electronic equipment |
| CN116320123B (en) * | 2022-08-11 | 2024-03-08 | 荣耀终端有限公司 | Voice signal output method and electronic equipment |
| CN116524891A (en) * | 2023-05-08 | 2023-08-01 | 拓达世纪信息产业有限公司 | AI sound masking system and secret meeting room thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104575486B (en) | 2019-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104575486A (en) | Sound leakage protection method and system based on sound masking principle | |
| CN105100758A (en) | Method and equipment used for security and protection monitoring as well as camera | |
| CN103607669B (en) | A kind of building conversational system audio transmission characteristic detecting method and detecting system | |
| CN105897361A (en) | Earthquake alarm broadcasting equipment and related method | |
| WO2020107261A1 (en) | Probabilistic silent failure detection method and apparatus | |
| CN105096946A (en) | Voice activation detection based awakening device and method | |
| CN108108006A (en) | The long-range control method and system of a kind of microphone | |
| CN106412188A (en) | Reminding method and apparatus | |
| CN109933933B (en) | Noise treatment method and equipment | |
| CN106764468A (en) | A kind of seepage early warning system and adaptive spectrum noise-eliminating method | |
| CN103063088B (en) | A kind of flash-bang characteristic measuring system and measuring method | |
| CN105137204A (en) | Apparatus and method for locating indoor electromagnetic radiation source | |
| CN116524891A (en) | AI sound masking system and secret meeting room thereof | |
| CN114252906A (en) | Sound event detection method and device, computer equipment and storage medium | |
| CN116105852A (en) | Intelligent noise superscript illegal evidence obtaining device | |
| CN205029789U (en) | City pipeline safety is surveyed and monitored control system | |
| Sugimoto et al. | Measurement of infrasound generated by wind turbine generator | |
| CN204968034U (en) | A equipment and camera for security protection control | |
| CN104978810A (en) | Glass breakage detection device and method and LED lighting device | |
| CN211236625U (en) | Wireless monitoring system of operation environmental noise based on Modbus TCP agreement | |
| Bellucci et al. | Implementing the Harmonica Index in the Dynamap Project | |
| Begault | Psychoacoustic Measures for UAM noise in the Context of Ambient Sound | |
| Flemmer et al. | Wind turbine infrasound: Phenomenology and effect on people | |
| Sorin et al. | STUDY ON REDUCING URBAN NOISE IN RESIDENTIAL BUILDINGS | |
| Blair-DeLeon et al. | Acoustical Standards News |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190402 |