CN109524012A - Audio security protection control centre, intelligent audio sensor and monitoring method and system - Google Patents

Audio security protection control centre, intelligent audio sensor and monitoring method and system Download PDF

Info

Publication number
CN109524012A
CN109524012A CN201811469371.9A CN201811469371A CN109524012A CN 109524012 A CN109524012 A CN 109524012A CN 201811469371 A CN201811469371 A CN 201811469371A CN 109524012 A CN109524012 A CN 109524012A
Authority
CN
China
Prior art keywords
audio
vocal print
print feature
control centre
security protection
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
Application number
CN201811469371.9A
Other languages
Chinese (zh)
Other versions
CN109524012B (en
Inventor
田涛
徐高峰
裴卫斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Liwei Zhilian Technology Co Ltd
Original Assignee
Shenzhen Liwei Zhilian Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Liwei Zhilian Technology Co Ltd filed Critical Shenzhen Liwei Zhilian Technology Co Ltd
Priority to CN201811469371.9A priority Critical patent/CN109524012B/en
Publication of CN109524012A publication Critical patent/CN109524012A/en
Application granted granted Critical
Publication of CN109524012B publication Critical patent/CN109524012B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Telephonic Communication Services (AREA)
  • Alarm Systems (AREA)

Abstract

A kind of audio security protection control centre, intelligent audio sensor and Voice Surveillance method and system based on intelligence community, it include: the vocal print feature database of audio security protection control centre creation danger sound, distribute the vocal print feature database to the intelligent audio sensor of monitored community, and passback strategy is determined according to the type of danger sound；Audio security protection control centre receives the intelligent audio sensor according to the monitoring data of the related danger sound of the passback strategy passback.In a specific embodiment of the present application, since the application only returns and compares successful audio data in vocal print feature database, without the original data stream of all generations is all back to audio security protection control centre, thus reduce the transmitted data amount between audio sensor and audio security protection control centre.

Description

Audio security protection control centre, intelligent audio sensor and monitoring method and system
Technical field
This application involves Voice Surveillance field more particularly to a kind of audio security protection control centres based on intelligence community, intelligence It can audio sensor and Voice Surveillance method and system.
Background technique
In the Audio Monitoring System of existing community, audio sensor is acquired in community after audio-frequency information, can be by original audio Data flow (the biggish HD Audio data flow of data volume) by return link real-time delivery to audio security protection control centre, and Multiple audio sensors return original audio data stream to same audio security protection control centre by return link in real time, will produce Raw huge real-time passback voice data stream (such as HD Audio data flow at least needs 64 [kbit/s] all the way, it is assumed that sound The audio collection range of video sensor is X [m2], considers that the area of multiple communities of audio security protection control centre control is total With for Y [m2], then the audio sensor quantity that comprehensive audio deployment of audio security protection control centre control range needs isK is the real number greater than 1, then N number of audio sensor returns audio data to audio security protection control centre in real time Stream is N*64 [kbit/s], and actual conditions N is typically larger than 1000, it means that passback voice data stream is more than 64 [Mbit/ in real time S]), huge return link bandwidth is needed, thus can only be returned by wired communication mode and super broad band radio communication mode It passes, common wide communication (such as LTE and Wifi) cannot be used to return.However, ultra wide band and common wide without The more cost pressures of line communication mode acquisition frequency resource are big, and the communications cable and wiring cost that wired communication mode needs also compare Greatly, all it is not suitable for the high-volume layout of Voice Surveillance sensor.
On the other hand, Audio Monitoring System is required to the audio prison for emergency response being carried out to security incident, but current Control data processing concentrates on audio security protection control centre, needs to transmit between audio sensor and audio security protection control centre a large amount of Audio data, then generation moment at the time of audio security protection control centre detects security incident relative to security incident, Propagation delay time between audio sensor and audio security protection control centre and audio security protection control centre are increased to a large amount of sounds The processing delay of frequency monitoring data centralized processing.
Summary of the invention
The application provides a kind of audio security protection control centre, intelligent audio sensor and Voice Surveillance based on intelligence community Method and system.
According to a first aspect of the present application, the application provides a kind of Voice Surveillance method based on intelligence community, comprising:
Audio security protection control centre creates the vocal print feature database of danger sound, keeps pouring in the intelligent sound of monitored community Sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
Audio security protection control centre receives the intelligent audio sensor according to the related of the passback strategy passback The monitoring data of danger sound.
According to a second aspect of the present application, the application provides a kind of Voice Surveillance method based on intelligence community, comprising:
Intelligent audio sensor acquires audio data, calculates the vocal print feature of collected audio data；
The intelligent audio sensor is by the vocal print in the vocal print feature of collected audio data and vocal print property data base Feature is compared, if comparing successfully, the passback strategy that the intelligent audio sensor is determined according to audio security protection control centre, Monitoring data is returned to audio security protection control centre.
According to the third aspect of the application, the application provides a kind of Voice Surveillance method based on intelligence community, comprising:
Audio security protection control centre creates the vocal print feature database of danger sound, keeps pouring in the intelligent sound of monitored community Sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
The intelligent audio sensor acquires audio data, calculates the vocal print feature of collected audio data；
The intelligent audio sensor is by the vocal print in the vocal print feature of collected audio data and vocal print property data base Feature is compared, if comparing successfully, the intelligent audio sensor is according to the passback strategy, Xiang Suoshu audio security protection control Center returns the monitoring data in relation to danger sound；
Audio security protection control centre receives the monitoring data.
According to the fourth aspect of the application, the application provides a kind of audio security protection control centre based on intelligence community, packet It includes:
First processing module, for creating the vocal print feature database of danger sound, to the intelligent audio of monitored community Sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
Receiving module, for receiving intelligent audio sensor according to the prison of the related danger sound of the passback strategy passback Control data.
According to the 5th of the application the aspect, the application provides a kind of intelligent audio sensor based on intelligence community, comprising:
Acquisition module calculates the vocal print feature of collected audio data for acquiring audio data；
Comparison module, for by the vocal print feature in the vocal print feature of collected audio data and vocal print property data base into Row compares, if comparing successfully, according to the passback strategy that audio security protection control centre determines, returns to audio security protection control centre Monitoring data.
According to the 6th of the application the aspect, the application provides a kind of Audio Monitoring System based on intelligence community, including sound Frequency security protection control centre and intelligent audio sensor；Audio security protection control centre includes first processing module and reception mould Block, the intelligent audio sensor includes acquisition module and comparison module；
The first processing module, for creating the vocal print feature database of danger sound, to the intelligence of monitored community Audio sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
The acquisition module calculates the vocal print feature of collected audio data for acquiring audio data；
The comparison module, for the vocal print in the vocal print feature of collected audio data and vocal print property data base is special Sign is compared, if comparing successfully, according to the passback strategy that audio security protection control centre determines, to audio security protection control centre Return monitoring data；
The receiving module, for receiving the monitoring data.
According to the 7th of the application the aspect, the application provides a kind of computer readable storage medium, including program, the journey Sequence can be executed by processor to realize the above method.
Due to using above technical scheme, the beneficial effect for having the application is:
(1) in a specific embodiment of the present application, since audio security protection control centre creates and to intelligent audio sensor Distribute vocal print feature database, intelligent audio sensor will be in the vocal print feature of the audio data of acquisition and vocal print property data base Vocal print feature be compared, if comparing successfully, intelligent audio sensor according to passback strategy, to audio security protection control centre return The monitoring data in relation to danger sound is passed, the application only returns and compares successful audio data in vocal print feature database, and It is not necessary that the original data stream of all generations is all back to audio security protection control centre, thus reduce audio sensor and audio Transmitted data amount between security protection control centre.
(2) in a specific embodiment of the present application, since intelligent audio sensor only returns the vocal print spy of monitored personnel Sign mark and audio data raw information and the vocal print feature of abnormal sound mark, further improve audio sensor and audio Efficiency of transmission between security protection control centre, so as to shorten the response time of security incident.
Detailed description of the invention
Fig. 1 is the flow chart of the present processes in one embodiment；
Fig. 2 is the flow chart of the present processes in another embodiment；
Fig. 3 is the flow chart of the present processes in yet another embodiment；
Fig. 4 is the program module schematic diagram of the audio security protection control centre of the application in one embodiment；
Fig. 5 is the program module schematic diagram of the audio security protection control centre of the application in another embodiment；
Fig. 6 is the program module schematic diagram of the intelligent audio sensor of the application in one embodiment；
Fig. 7 is the program module schematic diagram of the system of the application in one embodiment；
Fig. 8 is the program module schematic diagram of the system of the application in another embodiment.
Specific embodiment
Below by specific embodiment combination attached drawing, invention is further described in detail.The application can be with a variety of Different forms is realized, however it is not limited to embodiment described in the present embodiment.The purpose of following specific embodiments is provided It is easy for becoming apparent from present disclosure thorough explanation, wherein the words of the indicating positions such as upper and lower, left and right is only needle To shown structure in respective figure for position.
However, those skilled in the art may be aware that one or more detail description can be by Omit, or can also adopt with other methods, component or material.In some instances, some embodiments are not described Or it is not described later in detail.
It is herein component institute serialization number itself, such as " first ", " second " etc., is only used for distinguishing described object, Without any sequence or art-recognized meanings.
In addition, technical characteristic described herein, technical solution can also be in one or more embodiments arbitrarily to close Suitable mode combines.For those skilled in the art, it should be readily appreciated that method related with embodiment provided herein Step or operation order can also change.Therefore, any sequence in drawings and examples is merely illustrative purposes, not secretly Show requirement in a certain order, is required unless expressly stated according to a certain sequence.
Embodiment one:
As shown in Figure 1, the Voice Surveillance method based on intelligence community of the application, a kind of embodiment, including it is following Step:
Step 102: audio security protection control centre creates the vocal print feature database of danger sound, to the intelligence of monitored community Energy audio sensor distributes vocal print feature database, and determines passback strategy according to the type of danger sound.In a kind of embodiment party In formula, danger sound includes the sound and/or abnormal sound of the monitored personnel in monitored community, and abnormal sound mainly includes The sound etc. that the sound of generation when natural calamity occurs or while having an accident generate, and fight, call and/or cry for help Equal voice.
Audio security protection control centre is based on various sound materials, phonetic material, abnormal sound such as the personnel for needing to monitor Material etc. creates control centre's rank vocal print feature database.Vocal print feature can utilize mel-frequency cepstrum coefficient MFCC, and The characterization such as i-vector mark vector.It is any vocal print feature number in vocal print feature database according to scheduled mark rule According to unique mark is assigned, referred to as vocal print feature is identified.The personnel that different communities need to monitor may be different, so audio security protection Control centre supports to create rank vocal print feature database in community's for different communities, in community's rank vocal print feature database Vocal print feature mark is derived from control centre's rank vocal print feature database, and it is special that this guarantees vocal prints in control centre's global scope The unique identification of sign.Vocal print feature mark can support the sound of 65536 kinds of different characteristics with 16bit binary representation, maximum Sound.
Community's rank vocal print feature database is distributed in community by audio security protection control centre using community as target unit All intelligent audio sensors, it is such as local without society after intelligent audio sensor receives community's rank vocal print feature database Area's rank vocal print feature database, then using the community's rank vocal print feature database received as Local Community rank vocal print feature Database is stored, conversely, the community's rank vocal print feature database received and the community's rank vocal print being locally stored is special Sign database is compared, and as variant, is updated.
Normal condition audio security protection control centre distributes community-level to intelligent audio sensor in a manner of periodically distributing Other vocal print feature database, so that the intelligent audio sensor newly accessed can obtain newest community's rank vocal print feature in time Database.
In system operation, when increasing the new sound material for needing monitoring personnel and new abnormal sound material Material, then audio security protection control centre needs to calculate the vocal print feature of newly-increased sound material, and newly-increased vocal print feature is added Control centre's rank vocal print feature database and community's rank vocal print feature database.The distribution period next in this way Distribute to intelligent audio sensor.
In one embodiment, MFCC calculating process is as follows:
Analog signal S (t) sample quantization for inputting sound is S (n)；
S (n) preemphasis is later S ' (n), uses single order high pass preemphasis network 1- γ Z-1, compensate the high frequency of voice spectrum It has a down dip；
It is S ' after S ' (n) zero passage detection and framingm(n), m indicates frame number；
S’mIt (n) is S " after adding windowm(n), using Hamming window:
S”m(n) Short Time Fourier Transform is
Xm(k) mel frequency MF is calculatedm(r):
Nr is number of filter；
MFm(r) mfcc Coefficient m fcc is calculatedm(j):
mfccm(j) its first-order difference is calculated:
In one embodiment, passback strategy includes:
If recognizing the vocal print of the monitored personnel in monitored community, the vocal print feature mark of the monitored personnel is returned Know and audio data raw information；
If recognizing the vocal print of the abnormal sound in monitored community, the vocal print feature mark of the abnormal sound is returned.
Audio security protection control centre can set different passback strategies for different sound, such as identify in community The personnel for needing to monitor need to return vocal print feature mark and audio data raw information, identify abnormal sound and only need to return Vocal print feature mark.Passback strategy is indicated according to predefined passback policy bit position.
Step 104: audio security protection control centre receives intelligent audio sensor according to the related danger of passback strategy passback The monitoring data of sound.
When intelligent audio sensor collects audio data, its MFCC coefficient characterization vocal print feature is calculated, then by the sound Frequency is compared according to vocal print feature with the vocal print feature in the vocal print feature database being locally stored, if comparing successfully, root According to returning tactful return data to audio security protection control centre, conversely, then not return data.
In one embodiment, the Voice Surveillance method based on intelligence community of the application can also include following step It is rapid:
Step 106: audio security protection control centre is when judging that dangerous event occurs according to monitoring data, selection region The mode of linkage, cause danger within the scope of order audio security protection the control centre community of event and the intelligent audio of neighbouring community Sensor carries out emergency monitoring.
When audio security protection control centre receives the specific vocal print feature of some intelligent audio sensor passback of some community Mark, and judge hazard event, then the mode of audio security protection control centre's selection region linkage, is ordered in control The intelligent audio sensor of the community and neighbouring community carries out emergency monitoring within the scope of the heart, i.e., pacifies in emergency response treatment process Anti- control centre needs to update emergency vocal print feature database according to the hazard event of current detection, and as early as possible with order of meeting an urgent need Mode to intelligent audio sensor distribute emergency vocal print feature database, to participate in the intelligent audio sensor of emergency response It can be quickly obtained emergency vocal print feature database, the intelligent audio sensor for receiving emergency vocal print feature database needs preferentially Sound in identification emergency vocal print feature database, comes if picked out, according to the tactful return data in real time of passback to audio Security protection control centre comes if picked out conversely, then recognize the sound in community's rank vocal print feature database, according to returning Tactful return data is passed to audio security protection control centre, conversely, then not return data.
In another embodiment, the Voice Surveillance method based on intelligence community of the application can also include following Step:
Step 108: the intelligent audio sensor for returning monitoring data is arranged to particular color by audio security protection control centre, And according to the color of intelligent audio sensor, the motion profile of danger sound is deployed troops on garrison duty and tracked.
The large-size screen monitors of audio security protection control centre can be kept pouring in the intelligent sound of all installations in the compass of competency of display control center The state of sensor.Such as give the intelligent audio sensor for having returned the mark of the specific vocal print feature in emergency response treatment process Specific color, so that the motion profile of audio security protection control centre control danger sound is targetedly to be deployed troops on garrison duty and to be chased after Track.
Embodiment two:
As shown in Fig. 2, the Voice Surveillance method based on intelligence community of the application, another embodiment, including with Lower step:
Step 202: intelligent audio sensor acquires audio data, calculates the vocal print feature of collected audio data.
Step 204: intelligent audio sensor will be in the vocal print feature of collected audio data and vocal print property data base Vocal print feature is compared, if comparing successfully, the passback strategy that intelligent audio sensor is determined according to audio security protection control centre, Monitoring data is returned to audio security protection control centre.
When intelligent audio sensor collects audio data, its MFCC coefficient characterization vocal print feature is calculated, then by the sound Frequency is compared according to vocal print feature with the vocal print feature in the community's rank vocal print feature database being locally stored, if compare at Function, then according to returning tactful return data to audio security protection control centre, conversely, then not return data.
Embodiment three:
As shown in figure 3, the Voice Surveillance method based on intelligence community of the application, another embodiment, including with Lower step:
Step 302: audio security protection control centre creates the vocal print feature database of danger sound, to the intelligence of monitored community Energy audio sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound.
In one embodiment, danger sound includes the sound and/or exception of the monitored personnel in monitored community Sound, abnormal sound mainly include the sound of generation when natural calamity occurs or the sound etc. that while having an accident generates, And the voice such as fight, call and/or cry for help.
Audio security protection control centre is based on various sound materials, phonetic material, abnormal sound such as the personnel for needing to monitor Material etc. creates control centre's rank vocal print feature database.Vocal print feature can utilize mel-frequency cepstrum coefficient MFCC, and The characterization such as i-vector mark vector.It is any vocal print feature number in vocal print feature database according to scheduled mark rule According to unique mark is assigned, referred to as vocal print feature is identified.The personnel that different communities need to monitor may be different, so audio security protection Control centre supports to create rank vocal print feature database in community's for different communities, in community's rank vocal print feature database Vocal print feature mark is derived from control centre's rank vocal print feature database, and it is special that this guarantees vocal prints in control centre's global scope The unique identification of sign.Vocal print feature mark can support the sound of 65536 kinds of different characteristics with 16bit binary representation, maximum Sound.
Community's rank vocal print feature database is distributed in community by audio security protection control centre using community as target unit All intelligent audio sensors, it is such as local without society after intelligent audio sensor receives community's rank vocal print feature database Area's rank vocal print feature database, then using the community's rank vocal print feature database received as Local Community rank vocal print feature Database is stored, conversely, the community's rank vocal print feature database received and the community's rank vocal print being locally stored is special Sign database is compared, and as variant, is updated.
Normal condition audio security protection control centre distributes community-level to intelligent audio sensor in a manner of periodically distributing Other vocal print feature database, so that the intelligent audio sensor newly accessed can obtain newest community's rank vocal print feature in time Database.
In system operation, when increasing the new sound material for needing monitoring personnel and new abnormal sound material Material, then audio security protection control centre needs to calculate the vocal print feature of newly-increased sound material, and newly-increased vocal print feature is added Control centre's rank vocal print feature database and community's rank vocal print feature database.The distribution period next in this way Distribute to intelligent audio sensor.
In one embodiment, MFCC calculating process is as follows:
Analog signal S (t) sample quantization for inputting sound is S (n)；
S (n) preemphasis is later S ' (n), uses single order high pass preemphasis network 1- γ Z-1, compensate the high frequency of voice spectrum It has a down dip；
It is S ' after S ' (n) zero passage detection and framingm(n), m indicates frame number；
S’mIt (n) is S " after adding windowm(n), using Hamming window:
S”m(n) Short Time Fourier Transform is
Xm(k) mel frequency MF is calculatedm(r):
Nr is number of filter；
MFm(r) mfcc Coefficient m fcc is calculatedm(j):
mfccm(j) its first-order difference is calculated:
In one embodiment, passback strategy includes:
If recognizing the vocal print of the monitored personnel in monitored community, the vocal print feature mark of the monitored personnel is returned Know and audio data raw information；
If recognizing the vocal print of the abnormal sound in monitored community, the vocal print feature mark of the abnormal sound is returned.
Audio security protection control centre can set different passback strategies for different sound, such as identify in community The personnel for needing to monitor need to return vocal print feature mark and audio data raw information, identify abnormal sound and only need to return Vocal print feature mark.Passback strategy is indicated according to predefined passback policy bit position.
Step 304: intelligent audio sensor acquires audio data, calculates the vocal print feature of collected audio data.
Step 306: intelligent audio sensor will be in the vocal print feature of collected audio data and vocal print property data base Vocal print feature is compared, if comparing successfully, intelligent audio sensor is according to the passback strategy, to audio security protection control centre Return the monitoring data in relation to danger sound.
When intelligent audio sensor collects audio data, its MFCC coefficient characterization vocal print feature is calculated, then by the sound Frequency is compared according to vocal print feature with the vocal print feature in the community's rank vocal print feature database being locally stored, if compare at Function, then according to returning tactful return data to audio security protection control centre, conversely, then not return data.
Step 308: audio security protection control centre receives the monitoring data.
In one embodiment, the Voice Surveillance method based on intelligence community of the application can also include following step It is rapid:
Step 310: audio security protection control centre is when judging that dangerous event occurs according to monitoring data, selection region The mode of linkage, cause danger within the scope of order audio security protection the control centre community of event and the intelligent audio of neighbouring community Sensor carries out emergency monitoring.
When audio security protection control centre receives the specific vocal print feature of some intelligent audio sensor passback of some community Mark, and judge hazard event, then the mode of audio security protection control centre's selection region linkage, is ordered in control The intelligent audio sensor of the community and neighbouring community carries out emergency monitoring within the scope of the heart, i.e., pacifies in emergency response treatment process Anti- control centre needs to update emergency vocal print feature database according to the hazard event of current detection, and as early as possible with order of meeting an urgent need Mode to intelligent audio sensor distribute emergency vocal print feature database, to participate in the intelligent audio sensor of emergency response It can be quickly obtained emergency vocal print feature database, the intelligent audio sensor for receiving emergency vocal print feature database needs preferentially Sound in identification emergency vocal print feature database, comes if picked out, according to the tactful return data in real time of passback to audio Security protection control centre comes if picked out conversely, then recognize the sound in community's rank vocal print feature database, according to returning Tactful return data is passed to audio security protection control centre, conversely, then not return data.
In another embodiment, the Voice Surveillance method based on intelligence community of the application can also include following Step:
Step 312: the intelligent audio sensor for returning monitoring data is arranged to particular color by audio security protection control centre, And according to the color of intelligent audio sensor, the motion profile of danger sound is deployed troops on garrison duty and tracked.
The large-size screen monitors of audio security protection control centre can be kept pouring in the intelligent sound of all installations in the compass of competency of display control center The state of sensor.Such as give the intelligent audio sensor for having returned the mark of the specific vocal print feature in emergency response treatment process Specific color, so that the motion profile of audio security protection control centre control danger sound is targetedly to be deployed troops on garrison duty and to be chased after Track.
Example IV:
As shown in Figure 4, Figure 5, the audio security protection control centre based on intelligence community of the application, a kind of embodiment, It include: first processing module and receiving module.
First processing module, for creating the vocal print feature database of danger sound, to the intelligent audio of monitored community Sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
Receiving module, for receiving intelligent audio sensor according to the monitoring number of the related danger sound of passback strategy passback According to.
In one embodiment, the audio security protection control centre of the application can also include emergency module.Emergency mould Block, for according to the monitoring data judge hazard event occur when, selection region linkage mode, order monitoring range The intelligent audio sensor of the community for event of inside causing danger and neighbouring community carries out emergency monitoring.
In another embodiment, the audio security protection control centre of the application can also include Second processing module:
Second processing module, for the intelligent audio sensor for returning monitoring data to be arranged to particular color, root According to the color of intelligent audio sensor, the motion profile of danger sound is deployed troops on garrison duty and tracked.
Embodiment five:
As shown in fig. 6, the intelligent audio sensor based on intelligence community of the application, a kind of embodiment, including adopt Collect module and comparison module.
Acquisition module calculates the vocal print feature of collected audio data for acquiring audio data；
Comparison module, for by the vocal print feature in the vocal print feature of collected audio data and vocal print property data base into Row compares, if comparing successfully, according to the passback strategy that audio security protection control centre determines, returns to audio security protection control centre Monitoring data.
Embodiment six:
As shown in Figure 7, Figure 8, the Audio Monitoring System based on intelligence community of the application, a kind of embodiment, including Audio security protection control centre and intelligent audio sensor.
Audio security protection control centre includes first processing module and receiving module, and intelligent audio sensor includes acquisition module And comparison module；
First processing module, for creating the vocal print feature database of danger sound, to the intelligent audio of monitored community Sensor distributes vocal print feature database, and determines passback strategy according to the type of danger sound；
Acquisition module calculates the vocal print feature of collected audio data for acquiring audio data；
Comparison module, for by the vocal print feature in the vocal print feature of collected audio data and vocal print property data base into Row compares, if comparing successfully, according to the passback strategy that audio security protection control centre determines, returns to audio security protection control centre Monitoring data；
Receiving module, for receiving monitoring data.
In one embodiment, the audio security protection control centre of the application can also include emergency module.Emergency mould Block, for according to the monitoring data judge hazard event occur when, selection region linkage mode, order monitoring range The intelligent audio sensor of the community for event of inside causing danger and neighbouring community carries out emergency monitoring.
In another embodiment, the audio security protection control centre of the application can also include Second processing module:
Second processing module, for the intelligent audio sensor for returning monitoring data to be arranged to particular color, root According to the color of intelligent audio sensor, the motion profile of danger sound is deployed troops on garrison duty and tracked.
Embodiment seven:
A kind of computer readable storage medium, including program, the program can be executed by processor to realize such as embodiment One to embodiment three method.
It will be understood by those skilled in the art that all or part of the steps of various methods can pass through in above embodiment Program instructs related hardware to complete, which can be stored in a computer readable storage medium, storage medium can wrap It includes: read-only memory, random access memory, disk or CD etc..The above content is combination specific embodiments to the application institute The further description of work is, and it cannot be said that the specific implementation of the application is only limited to these instructions.Skill affiliated for the application For the those of ordinary skill in art field, without departing from the concept of this application, can also make it is several it is simple deduction or Replacement.

Claims (10)

1. a kind of Voice Surveillance method based on intelligence community characterized by comprising
Audio security protection control centre creates the vocal print feature database of danger sound, to the intelligent audio sensor of monitored community Distribute the vocal print feature database, and passback strategy is determined according to the type of danger sound；
Audio security protection control centre receives the intelligent audio sensor according to the related danger of the passback strategy passback The monitoring data of sound.
2. the method as described in claim 1, which is characterized in that the passback strategy, comprising:
If recognizing the vocal print of the monitored personnel in monitored community, return the monitored personnel vocal print feature mark and Audio data raw information；
If recognizing the vocal print of the abnormal sound in monitored community, the vocal print feature mark of the abnormal sound is returned.
3. method according to claim 1 or 2, which is characterized in that further include:
The intelligent audio sensor for returning monitoring data is arranged to particular color by audio security protection control centre；
Audio security protection control centre carries out the motion profile of danger sound according to the color of the intelligent audio sensor Deployment and tracking.
4. a kind of Voice Surveillance method based on intelligence community characterized by comprising
Intelligent audio sensor acquires audio data, calculates the vocal print feature of collected audio data；
The intelligent audio sensor is by the vocal print feature in the vocal print feature of collected audio data and vocal print property data base It is compared, if comparing successfully, the passback strategy that the intelligent audio sensor is determined according to audio security protection control centre, to institute State audio security protection control centre passback monitoring data.
5. a kind of Voice Surveillance method based on intelligence community characterized by comprising
Audio security protection control centre creates the vocal print feature database of danger sound, to the intelligent audio sensor of monitored community Distribute the vocal print feature database, and passback strategy is determined according to the type of danger sound；
The intelligent audio sensor acquires audio data, calculates the vocal print feature of collected audio data；
The intelligent audio sensor is by the vocal print feature in the vocal print feature of collected audio data and vocal print property data base It is compared, if comparing successfully, the intelligent audio sensor is according to the passback strategy, Xiang Suoshu audio security protection control centre Return the monitoring data in relation to danger sound；
Audio security protection control centre receives the monitoring data.
6. a kind of audio security protection control centre based on intelligence community characterized by comprising
First processing module is sensed for creating the vocal print feature database of danger sound to the intelligent audio of monitored community Device distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
Receiving module, for receiving intelligent audio sensor according to the monitoring number of the related danger sound of the passback strategy passback According to.
7. audio security protection control centre as claimed in claim 6, which is characterized in that further include:
Second processing module, for the intelligent audio sensor for returning monitoring data to be arranged to particular color, according to institute The color for stating intelligent audio sensor is deployed troops on garrison duty and is tracked to the motion profile of danger sound.
8. a kind of intelligent audio sensor based on intelligence community characterized by comprising
Acquisition module calculates the vocal print feature of collected audio data for acquiring audio data；
Comparison module, for comparing the vocal print feature in the vocal print feature of collected audio data and vocal print property data base It is right, if comparing successfully, according to the passback strategy that audio security protection control centre determines, returns and monitor to audio security protection control centre Data.
9. a kind of Audio Monitoring System based on intelligence community, which is characterized in that including audio security protection control centre and intelligent sound Video sensor；Audio security protection control centre includes first processing module and receiving module, the intelligent audio sensor packet Include acquisition module and comparison module；
The first processing module, for creating the vocal print feature database of danger sound, to the intelligent audio of monitored community Sensor distributes the vocal print feature database, and determines passback strategy according to the type of danger sound；
The acquisition module calculates the vocal print feature of collected audio data for acquiring audio data；
The comparison module, for by the vocal print feature in the vocal print feature of collected audio data and vocal print property data base into Row compares, if comparing successfully, according to the passback strategy that audio security protection control centre determines, returns to audio security protection control centre Monitoring data；
The receiving module, for receiving the monitoring data.
10. a kind of computer readable storage medium, which is characterized in that including program, described program can be executed by processor with Realize the method as described in claim 1-5 any one.
CN201811469371.9A 2018-11-28 2018-11-28 Audio security control center, intelligent audio sensor, monitoring method and system Active CN109524012B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811469371.9A CN109524012B (en) 2018-11-28 2018-11-28 Audio security control center, intelligent audio sensor, monitoring method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811469371.9A CN109524012B (en) 2018-11-28 2018-11-28 Audio security control center, intelligent audio sensor, monitoring method and system

Publications (2)

Publication Number Publication Date
CN109524012A true CN109524012A (en) 2019-03-26
CN109524012B CN109524012B (en) 2022-06-17

Family

ID=65793897

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811469371.9A Active CN109524012B (en) 2018-11-28 2018-11-28 Audio security control center, intelligent audio sensor, monitoring method and system

Country Status (1)

Country Link
CN (1) CN109524012B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712629A (en) * 2020-12-29 2021-04-27 浙江广维通信有限公司 Intelligent community security monitoring device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN204406507U (en) * 2014-12-25 2015-06-17 天津市大德伟业科技有限公司 A kind of Application on Voiceprint Recognition entrance guard security system
CN204833549U (en) * 2015-06-26 2015-12-02 天津联奥普科技有限公司 District property security protection monitored control system
CN105719651A (en) * 2016-02-03 2016-06-29 合肥联宝信息技术有限公司 Voiceprint collecting and processing system and collecting and processing method thereof
CN107590439A (en) * 2017-08-18 2018-01-16 湖南文理学院 Target person identification method for tracing and device based on monitor video
CN108320752A (en) * 2018-01-26 2018-07-24 青岛易方德物联科技有限公司 Cloud Voiceprint Recognition System and its method applied to community gate inhibition
US10074089B1 (en) * 2012-03-01 2018-09-11 Citigroup Technology, Inc. Smart authentication and identification via voiceprints

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10074089B1 (en) * 2012-03-01 2018-09-11 Citigroup Technology, Inc. Smart authentication and identification via voiceprints
CN204406507U (en) * 2014-12-25 2015-06-17 天津市大德伟业科技有限公司 A kind of Application on Voiceprint Recognition entrance guard security system
CN204833549U (en) * 2015-06-26 2015-12-02 天津联奥普科技有限公司 District property security protection monitored control system
CN105719651A (en) * 2016-02-03 2016-06-29 合肥联宝信息技术有限公司 Voiceprint collecting and processing system and collecting and processing method thereof
CN107590439A (en) * 2017-08-18 2018-01-16 湖南文理学院 Target person identification method for tracing and device based on monitor video
CN108320752A (en) * 2018-01-26 2018-07-24 青岛易方德物联科技有限公司 Cloud Voiceprint Recognition System and its method applied to community gate inhibition

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712629A (en) * 2020-12-29 2021-04-27 浙江广维通信有限公司 Intelligent community security monitoring device
CN112712629B (en) * 2020-12-29 2022-06-17 浙江广维通信有限公司 Intelligent community security monitoring device

Also Published As

Publication number Publication date
CN109524012B (en) 2022-06-17

Similar Documents

Publication Publication Date Title
US20220215748A1 (en) Automated camera response in a surveillance architecture
US20230021850A1 (en) Premises security system with dynamic risk evaluation
US10008102B1 (en) System and method for monitoring radio-frequency (RF) signals for security applications
CN109672853A (en) Method for early warning, device, equipment and computer storage medium based on video monitoring
US20190087464A1 (en) Regional population management system and method
JP2021533617A (en) Systems and methods for adapting communications in response to actionable intelligence
DE102015213583A1 (en) Failure detection system and failure detection procedure
CN105590419A (en) Police calling and sending platform based on Internet
Haouari et al. Fog computing potentials, applications, and challenges
CN110379141A (en) A kind of method and gateway system carrying out sensor linkage using gateway
CN108345829A (en) Remote monitoring goes on patrol the device at scene in the street
CN106097220A (en) A kind of prediction scheme sends method and device
US20230074279A1 (en) Methods, non-transitory computer readable media, and systems of transcription using multiple recording devices
CN108881833A (en) A kind of audio-video joint-monitoring system and method
CN116129490A (en) Monitoring device and monitoring method for complex environment behavior recognition
CN111476696A (en) Community correction group position information monitoring and alarming system based on big data
CN106791636A (en) A kind of key population monitoring system and method
CN109524012A (en) Audio security protection control centre, intelligent audio sensor and monitoring method and system
CN113112744A (en) Security management method and device, electronic equipment and storage medium
US11435706B2 (en) Control system and control method
CN107634881A (en) A kind of network or video traffic detection system and method
CN111696200A (en) Method, system, device and storage medium for displaying alarm situation
CN114158026B (en) Emergency communication command system based on satellite broadband platform
CN107993388A (en) A kind of Intelligent security apparatus, method and system
CN106937170A (en) A kind of outdoor media broadcasts monitoring method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant