CN109524012B - Audio security control center, intelligent audio sensor, monitoring method and system - Google Patents
Audio security control center, intelligent audio sensor, monitoring method and system Download PDFInfo
- Publication number
- CN109524012B CN109524012B CN201811469371.9A CN201811469371A CN109524012B CN 109524012 B CN109524012 B CN 109524012B CN 201811469371 A CN201811469371 A CN 201811469371A CN 109524012 B CN109524012 B CN 109524012B
- Authority
- CN
- China
- Prior art keywords
- community
- audio
- voiceprint feature
- feature database
- control center
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000005540 biological transmission Effects 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 230000007123 defense Effects 0.000 claims description 7
- 230000033001 locomotion Effects 0.000 claims description 6
- 239000000463 material Substances 0.000 description 13
- 230000004044 response Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
An audio security control center, an intelligent audio sensor and an audio monitoring method and system based on an intelligent community comprise the following steps: the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to an intelligent audio sensor of a monitored community, and determines a return strategy according to the types of the dangerous sounds; and the audio security control center receives the monitoring data related to the dangerous sound returned by the intelligent audio sensor according to the return strategy. In the specific implementation manner of the application, only the audio data successfully compared with the voiceprint feature database is returned, and all generated original data streams are not required to be returned to the audio security control center, so that the data transmission amount between the audio sensor and the audio security control center is reduced.
Description
Technical Field
The application relates to the field of audio monitoring, in particular to an audio security control center based on an intelligent community, an intelligent audio sensor and an audio monitoring method and system.
Background
In the existing audio monitoring system of the community, after an audio sensor collects audio information in the community, an original audio data stream (a high-fidelity audio data stream with a large data volume) is transmitted to an audio security control center in real time through a return link, and a plurality of audio sensors return the original audio data stream to the same audio security control center in real time through the return link, so that a huge real-time return audio data stream is generated (for example, one path of high-fidelity audio data stream at least needs 64 kbit/s]Suppose that the audio sensor has an audio acquisition range of X m2]Considering the sum of the areas of multiple communities controlled by one audio security control center as Y [ m2 ]]Then the number of the audio sensors required for comprehensive audio defense of the control range of the audio security control center is
k is a real number larger than 1, and then the real-time transmission of the audio data stream from the N audio sensors to the audio security control center is N x 64 kbit/s]The practical case N is typically greater than 1000, which means that the real-time back-streaming audio data stream exceeds 64 Mbit/s]) And a huge backhaul link bandwidth is required, so backhaul can only be achieved by a wired communication mode and an ultra-wideband wireless communication mode, and backhaul cannot be achieved by a common wideband wireless communication mode (such as LTE and Wifi). However, the ultra-wideband and the common wideband wireless communication methods occupy more frequency resources and have higher cost and pressure, and the communication cables and the wiring costs required by the wired communication methods are also higher, which are not suitable for the mass layout of the audio monitoring sensors.
On the other hand, the audio monitoring system needs to be capable of performing emergency response on the security event, but the current audio monitoring data processing is centralized in the audio security control center, a large amount of audio data needs to be transmitted between the audio sensor and the audio security control center, so that the audio security control center detects the time of the security event, the transmission delay between the audio sensor and the audio security control center is increased relative to the occurrence time of the security event, and the processing delay of the audio security control center on centralized processing of a large amount of audio monitoring data is increased.
Disclosure of Invention
The application provides an audio security control center based on an intelligent community, an intelligent audio sensor, an audio monitoring method and an audio monitoring system.
According to a first aspect of the present application, the present application provides an audio monitoring method based on a smart community, including:
the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to an intelligent audio sensor of a monitored community, and determines a return strategy according to the types of the dangerous sounds;
and the audio security control center receives the monitoring data related to the dangerous sound returned by the intelligent audio sensor according to the return strategy.
According to a second aspect of the present application, the present application provides an audio monitoring method based on a smart community, including:
the intelligent audio sensor collects audio data and calculates the voiceprint characteristics of the collected audio data;
the intelligent audio sensor compares the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, the intelligent audio sensor transmits the monitoring data back to the audio security control center according to the transmission strategy determined by the audio security control center.
According to a third aspect of the present application, the present application provides an audio monitoring method based on a smart community, including:
the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to an intelligent audio sensor of a monitored community, and determines a return strategy according to the types of the dangerous sounds;
the intelligent audio sensor collects audio data and calculates the voiceprint characteristics of the collected audio data;
the intelligent audio sensor compares the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, the intelligent audio sensor transmits monitoring data related to dangerous sounds back to the audio security control center according to the feedback strategy;
and the audio security control center receives the monitoring data.
According to the fourth aspect of this application, this application provides an audio security protection control center based on wisdom community, includes:
the first processing module is used for creating a voiceprint feature database of dangerous sounds, distributing the voiceprint feature database to an intelligent audio sensor of a monitored community, and determining a return strategy according to the types of the dangerous sounds;
and the receiving module is used for receiving the monitoring data which are returned by the intelligent audio sensor according to the return strategy and are related to the dangerous sound.
According to a fifth aspect of the present application, the present application provides an intelligent audio sensor based on smart community, including:
the acquisition module is used for acquiring audio data and calculating the voiceprint characteristics of the acquired audio data;
and the comparison module is used for comparing the voiceprint characteristics of the acquired audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, returning the monitoring data to the audio security control center according to a return strategy determined by the audio security control center.
According to a sixth aspect of the present application, the present application provides an audio monitoring system based on an intelligent community, comprising an audio security control center and an intelligent audio sensor; the audio security control center comprises a first processing module and a receiving module, and the intelligent audio sensor comprises an acquisition module and a comparison module;
the first processing module is used for creating a voiceprint feature database of dangerous sounds, distributing the voiceprint feature database to an intelligent audio sensor of a monitored community, and determining a return strategy according to the types of the dangerous sounds;
the acquisition module is used for acquiring audio data and calculating the voiceprint characteristics of the acquired audio data;
the comparison module is used for comparing the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, the monitoring data are transmitted back to the audio security control center according to the feedback strategy determined by the audio security control center;
the receiving module is used for receiving the monitoring data.
According to a seventh aspect of the present application, there is provided a computer readable storage medium comprising a program executable by a processor to implement the above method.
Due to the adoption of the technical scheme, the beneficial effects of the application are as follows:
the method includes the steps that a voiceprint characteristic database is created and distributed to an intelligent audio sensor by an audio security control center, the intelligent audio sensor compares voiceprint characteristics of collected audio data with voiceprint characteristics in the voiceprint characteristic database, if the comparison is successful, the intelligent audio sensor returns monitoring data related to dangerous sounds to the audio security control center according to a return strategy, only the audio data successfully compared with the voiceprint characteristic database are returned, and all generated original data streams do not need to be returned to the audio security control center, so that the data transmission amount between the audio sensor and the audio security control center is reduced.
Two in the embodiment of this application, because intelligent audio sensor only passbacks by the voiceprint characteristic identification of monitored personnel and the voiceprint characteristic identification of audio data original message and unusual sound, further promoted the transmission efficiency between audio sensor and the audio security control center to the response time of security incident has been shortened.
Drawings
FIG. 1 is a flow chart of the method of the present application in one embodiment;
FIG. 2 is a flow chart of the method of the present application in another embodiment;
FIG. 3 is a flow chart of a method of the present application in yet another embodiment;
FIG. 4 is a schematic diagram of program modules of an audio security control center according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of program modules of an audio security control center according to another embodiment of the present disclosure;
FIG. 6 is a schematic diagram of program modules in one embodiment of an intelligent audio sensor of the present application;
FIG. 7 is a schematic diagram of program modules in one embodiment of the system of the present application;
FIG. 8 is a schematic diagram of program modules in another embodiment of the system of the present application.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. The present application may be embodied in many different forms and is not limited to the embodiments described in the present embodiment. The following detailed description is provided to facilitate a more thorough understanding of the present disclosure, and the words used to indicate orientation, top, bottom, left, right, etc. are used solely to describe the illustrated structure in connection with the accompanying figures.
One skilled in the relevant art will recognize, however, that one or more of the specific details can be omitted, or other methods, components, or materials can be used. In some instances, some embodiments are not described or not described in detail.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning.
Furthermore, the technical features, aspects or characteristics described herein may be combined in any suitable manner in one or more embodiments. It will be readily appreciated by those of skill in the art that the order of the steps or operations of the methods associated with the embodiments provided herein may be varied. Thus, any sequence in the figures and examples is for illustrative purposes only and does not imply a requirement in a certain order unless explicitly stated to require a certain order.
The first embodiment is as follows:
as shown in fig. 1, one embodiment of the audio monitoring method based on smart community of the present application includes the following steps:
step 102: the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to the intelligent audio sensor of the monitored community, and determines a return strategy according to the types of the dangerous sounds. In one embodiment, the dangerous sound includes the sound of the monitored person in the monitored community and/or abnormal sound, and the abnormal sound mainly includes the sound generated when natural disaster occurs or the sound generated when dangerous accident occurs, and the like, and the sound of people fighting, calling and/or asking for help, and the like.
The audio security control center creates a control center level voiceprint feature database based on various sound materials, such as voice materials of personnel needing to be monitored, abnormal sound materials and the like. The voiceprint features can be characterized by using Mel frequency cepstrum coefficients MFCC, i-vector identification vectors and the like. According to a preset identification rule, a unique identification is given to any voiceprint characteristic data in the voiceprint characteristic database, and the unique identification is called a voiceprint characteristic identification. The personnel that different communities need to monitor may be different, so the audio security control center supports the establishment of community-level voiceprint feature databases for different communities, and voiceprint feature identifiers in the community-level voiceprint feature databases are obtained from the control center-level voiceprint feature database, so that the unique identification of voiceprint features in the global range of the control center is guaranteed. The voiceprint feature identification is expressed by 16bit binary, and can support 65536 sounds with different features at most.
The audio security control center takes a community as a target unit, distributes the community-level voiceprint feature database to all intelligent audio sensors in the community, after the intelligent audio sensors receive the community-level voiceprint feature database, if the local community-level voiceprint feature database does not exist, the received community-level voiceprint feature database is used as a local community-level voiceprint feature database to be stored, otherwise, the received community-level voiceprint feature database is compared with the locally-stored community-level voiceprint feature database, and if the difference exists, the received community-level voiceprint feature database is updated.
The audio security control center distributes the community-level voiceprint feature database to the intelligent audio sensor in a periodic distribution mode under normal conditions, so that the newly-accessed intelligent audio sensor can obtain the latest community-level voiceprint feature database in time.
In the system operation process, when new sound materials needing monitoring personnel and new abnormal sound materials are added, the audio security control center needs to calculate the voiceprint characteristics of the new sound materials, and the new voiceprint characteristics are added into the control center level voiceprint characteristic database and the community level voiceprint characteristic database. So that the next dispensing cycle can be dispensed to the intelligent audio sensor.
In one embodiment, the MFCC calculation process is as follows:
an analog signal S (t) of an input sound is sampled and quantized into S (n);
s (n) after pre-emphasis is S' (n), one is usedOrder high-pass pre-emphasis network 1-gamma Z-1Compensating for high frequency downtilt of the speech spectrum;
s '(n) zero-crossing detection and framing to be S'm(n), m represents a frame number;
S’m(n) S after windowing "m(n), using a hamming window:
S”m(n) short-time Fourier transform
Xm(k) Calculating mel frequency MFm(r)：
MFm(r) calculating the mfcc coefficient mfccm(j)：
mfccm(j) Calculate its first order difference:
in one embodiment, the backhaul strategy includes:
if the voiceprint of the monitored person in the monitored community is identified, returning the voiceprint characteristic identification and the original audio data information of the monitored person;
and if the voiceprint of the abnormal sound in the monitored community is identified, returning the voiceprint characteristic identification of the abnormal sound.
The audio security control center can set different return strategies according to different sounds, for example, it is recognized that a person needing to be monitored in a community needs to return voiceprint feature identification and original information of audio data, and it is recognized that abnormal sounds only need to return voiceprint feature identification. The backhaul strategy is represented according to predefined backhaul strategy bits.
Step 104: and the audio security control center receives the monitoring data related to the dangerous sound returned by the intelligent audio sensor according to the return strategy.
When the intelligent audio sensor acquires audio data, the MFCC coefficient of the intelligent audio sensor is calculated to represent the voiceprint characteristics, then the voiceprint characteristics of the audio data are compared with the voiceprint characteristics in a locally stored voiceprint characteristic database, if the comparison is successful, the data are returned to an audio security control center according to a return strategy, otherwise, the data are not returned.
In an embodiment, the audio monitoring method based on the smart community of the present application may further include the following steps:
step 106: when the audio security control center judges that a dangerous event occurs according to the monitoring data, the audio security control center selects a region linkage mode and commands the communities with the dangerous event and the intelligent audio sensors of the nearby communities in the range of the audio security control center to carry out emergency monitoring.
When the audio security control center receives a specific voiceprint feature identifier returned by an intelligent audio sensor of a certain community and judges that a dangerous event occurs, the audio security control center selects a region linkage mode to command the intelligent audio sensors of the community and nearby communities in the control center range to perform emergency monitoring, namely, the security control center needs to update an emergency voiceprint feature database according to the currently detected dangerous event in the emergency response processing process, and distributes the emergency voiceprint feature database to the intelligent audio sensors in an emergency command mode as soon as possible so that the intelligent audio sensors participating in the emergency response can quickly obtain the emergency voiceprint feature database, the intelligent audio sensors receiving the emergency voiceprint feature database need to preferentially identify the sound in the emergency voiceprint feature database, and if the emergency voiceprint feature database is identified, the data are returned to the audio control center in real time according to a security return strategy, and otherwise, identifying the sound in the community-level voiceprint feature database, if the sound is identified, returning the data to the audio security control center according to the return strategy, and otherwise, not returning the data.
In another embodiment, the audio monitoring method based on the smart community may further include the following steps:
step 108: the audio security control center sets the intelligent audio sensor which transmits the monitoring data back to a specific color, and according to the color of the intelligent audio sensor, the moving track of the dangerous sound is defended and tracked.
The large screen of the audio security control center can display the states of all installed intelligent audio sensors in the jurisdiction range of the control center. For example, a specific color is given to the intelligent audio sensor which transmits back a specific voiceprint feature identifier in the emergency response processing process, so that the audio security control center controls the motion track of the dangerous sound to perform targeted defense and tracking.
Example two:
as shown in fig. 2, another embodiment of the audio monitoring method based on smart community of the present application includes the following steps:
step 202: the intelligent audio sensor collects audio data and calculates the voiceprint characteristics of the collected audio data.
Step 204: the intelligent audio sensor compares the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, the intelligent audio sensor transmits the monitoring data back to the audio security control center according to the feedback strategy determined by the audio security control center.
When the intelligent audio sensor collects audio data, the MFCC coefficient representation voiceprint characteristics of the intelligent audio sensor are calculated, then the voiceprint characteristics of the audio data are compared with the voiceprint characteristics in a locally stored community-level voiceprint characteristic database, if the comparison is successful, the data are returned to an audio security control center according to a return strategy, otherwise, the data are not returned.
Example three:
as shown in fig. 3, another embodiment of the audio monitoring method based on smart community of the present application includes the following steps:
step 302: the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to the intelligent audio sensor of the monitored community, and determines a return strategy according to the types of the dangerous sounds.
In one embodiment, the dangerous sound includes the sound of the monitored person in the monitored community and/or abnormal sound, and the abnormal sound mainly includes the sound generated when natural disaster occurs or the sound generated when dangerous accident occurs, and the like, and the sound of people fighting, calling and/or asking for help, and the like.
The audio security control center creates a control center level voiceprint feature database based on various sound materials, such as voice materials of personnel needing to be monitored, abnormal sound materials and the like. The voiceprint features can be characterized by using Mel frequency cepstrum coefficients MFCC, i-vector identification vectors and the like. According to a preset identification rule, a unique identification is given to any voiceprint characteristic data in the voiceprint characteristic database, and the unique identification is called a voiceprint characteristic identification. The personnel that different communities need to monitor may be different, so the audio security control center supports the establishment of community-level voiceprint feature databases for different communities, and voiceprint feature identifiers in the community-level voiceprint feature databases are obtained from the control center-level voiceprint feature database, so that the unique identification of voiceprint features in the global range of the control center is guaranteed. The voiceprint feature identification is expressed by 16bit binary, and can support 65536 sounds with different features at most.
The audio security control center takes a community as a target unit, distributes the community-level voiceprint feature database to all intelligent audio sensors in the community, after the intelligent audio sensors receive the community-level voiceprint feature database, if the local community-level voiceprint feature database does not exist, the received community-level voiceprint feature database is used as a local community-level voiceprint feature database to be stored, otherwise, the received community-level voiceprint feature database is compared with the locally-stored community-level voiceprint feature database, and if the difference exists, the received community-level voiceprint feature database is updated.
The audio security control center distributes the community-level voiceprint feature database to the intelligent audio sensor in a periodic distribution mode under normal conditions, so that the newly-accessed intelligent audio sensor can obtain the latest community-level voiceprint feature database in time.
In the system operation process, when new sound materials needing monitoring personnel and new abnormal sound materials are added, the audio security control center needs to calculate the voiceprint characteristics of the new sound materials, and the new voiceprint characteristics are added into the control center level voiceprint characteristic database and the community level voiceprint characteristic database. So that the next dispensing cycle can be dispensed to the intelligent audio sensor.
In one embodiment, the MFCC calculation process is as follows:
sampling and quantizing an analog signal S (t) of input sound into S (n);
s (n) after pre-emphasis is S' (n), using a first-order high-pass pre-emphasis network 1-yZ-1Compensating for high frequency downtilt of the speech spectrum;
s '(n) zero-crossing detection and framing to be S'm(n), m represents a frame number;
S’m(n) S after windowing "m(n), using a hamming window:
S”m(n) short-time Fourier transform
Xm(k) Calculating mel frequency MFm(r)：
MFm(r) calculating the mfcc coefficient mfccm(j)：
mfccm(j) Calculate its first order difference:
in one embodiment, the backhaul strategy includes:
if the voiceprint of the monitored person in the monitored community is identified, returning the voiceprint characteristic identification and the original audio data information of the monitored person;
and if the voiceprint of the abnormal sound in the monitored community is identified, returning the voiceprint characteristic identification of the abnormal sound.
The audio security control center can set different return strategies according to different sounds, for example, it is recognized that a person needing to be monitored in a community needs to return voiceprint feature identification and original information of audio data, and it is recognized that abnormal sounds only need to return voiceprint feature identification. The backhaul strategy is represented according to predefined backhaul strategy bits.
Step 304: the intelligent audio sensor collects audio data and calculates the voiceprint characteristics of the collected audio data.
Step 306: and the intelligent audio sensor compares the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, the intelligent audio sensor transmits the monitoring data related to the dangerous sound back to the audio security control center according to the feedback strategy.
When the intelligent audio sensor collects audio data, the MFCC coefficient representation voiceprint characteristics of the intelligent audio sensor are calculated, then the voiceprint characteristics of the audio data are compared with the voiceprint characteristics in a locally stored community-level voiceprint characteristic database, if the comparison is successful, the data are returned to an audio security control center according to a return strategy, otherwise, the data are not returned.
Step 308: and the audio security control center receives the monitoring data.
In an embodiment, the audio monitoring method based on the smart community of the present application may further include the following steps:
step 310: when the audio security control center judges that a dangerous event occurs according to the monitoring data, the audio security control center selects a region linkage mode and commands the communities with the dangerous event and the intelligent audio sensors of the nearby communities in the range of the audio security control center to carry out emergency monitoring.
When the audio security control center receives a specific voiceprint feature identifier returned by an intelligent audio sensor of a certain community and judges that a dangerous event occurs, the audio security control center selects a region linkage mode to command the intelligent audio sensors of the community and nearby communities in the control center range to perform emergency monitoring, namely, the security control center needs to update an emergency voiceprint feature database according to the currently detected dangerous event in the emergency response processing process, and distributes the emergency voiceprint feature database to the intelligent audio sensors in an emergency command mode as soon as possible so that the intelligent audio sensors participating in the emergency response can quickly obtain the emergency voiceprint feature database, the intelligent audio sensors receiving the emergency voiceprint feature database need to preferentially identify the sound in the emergency voiceprint feature database, and if the emergency voiceprint feature database is identified, the data are returned to the audio control center in real time according to a security return strategy, and otherwise, identifying the sound in the community-level voiceprint feature database, if the sound is identified, returning the data to the audio security control center according to the return strategy, and otherwise, not returning the data.
In another embodiment, the audio monitoring method based on the smart community may further include the following steps:
step 312: the audio security control center sets the intelligent audio sensor which transmits the monitoring data back to a specific color, and according to the color of the intelligent audio sensor, the moving track of the dangerous sound is defended and tracked.
The large screen of the audio security control center can display the states of all installed intelligent audio sensors in the jurisdiction range of the control center. For example, a specific color is given to the intelligent audio sensor which transmits back a specific voiceprint feature identifier in the emergency response processing process, so that the audio security control center controls the motion track of the dangerous sound to perform targeted defense and tracking.
Example four:
as shown in fig. 4 and 5, an embodiment of the audio security control center based on the smart community of the present application includes: the device comprises a first processing module and a receiving module.
The first processing module is used for creating a voiceprint feature database of dangerous sounds, distributing the voiceprint feature database to an intelligent audio sensor of a monitored community, and determining a return strategy according to the types of the dangerous sounds;
and the receiving module is used for receiving the monitoring data which are returned by the intelligent audio sensor according to the return strategy and are related to the dangerous sound.
In an implementation manner, the audio security control center of the application can further comprise an emergency module. And the emergency module is used for selecting a regional linkage mode when judging that the dangerous event occurs according to the monitoring data, and commanding the intelligent audio sensor of the community in which the dangerous event occurs and the nearby community within the monitoring range to carry out emergency monitoring.
In another embodiment, the audio security control center of the present application may further include a second processing module:
and the second processing module is used for setting the intelligent audio sensor which transmits the monitoring data back to a specific color, and performing defense and tracking on the movement track of the dangerous sound according to the color of the intelligent audio sensor.
Example five:
as shown in fig. 6, an embodiment of the intelligent audio sensor based on smart community of the present application includes an acquisition module and a comparison module.
The acquisition module is used for acquiring audio data and calculating the voiceprint characteristics of the acquired audio data;
and the comparison module is used for comparing the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, returning the monitoring data to the audio security control center according to a returning strategy determined by the audio security control center.
Example six:
as shown in fig. 7 and 8, an embodiment of the audio monitoring system based on the smart community of the present application includes an audio security control center and an intelligent audio sensor.
The audio security control center comprises a first processing module and a receiving module, and the intelligent audio sensor comprises an acquisition module and a comparison module;
the first processing module is used for creating a voiceprint feature database of dangerous sounds, distributing the voiceprint feature database to an intelligent audio sensor of a monitored community, and determining a return strategy according to the types of the dangerous sounds;
the acquisition module is used for acquiring audio data and calculating the voiceprint characteristics of the acquired audio data;
the comparison module is used for comparing the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the voiceprint characteristic database, and if the comparison is successful, the monitoring data are transmitted back to the audio security control center according to the feedback strategy determined by the audio security control center;
and the receiving module is used for receiving the monitoring data.
In an implementation manner, the audio security control center of the application can further comprise an emergency module. And the emergency module is used for selecting a regional linkage mode when judging that the dangerous event occurs according to the monitoring data, and commanding the intelligent audio sensor of the community in which the dangerous event occurs and the nearby community within the monitoring range to carry out emergency monitoring.
In another embodiment, the audio security control center of the present application may further include a second processing module:
and the second processing module is used for setting the intelligent audio sensor which transmits the monitoring data back to a specific color, and performing defense and tracking on the movement track of the dangerous sound according to the color of the intelligent audio sensor.
Example seven:
a computer-readable storage medium comprising a program executable by a processor to implement the method of embodiments one through three.
Those skilled in the art will appreciate that all or part of the steps of the various methods in the above embodiments may be implemented by instructions associated with hardware via a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read-only memory, random access memory, magnetic or optical disk, and the like. The foregoing is a more detailed description of the present application in connection with specific embodiments thereof, and it is not intended that the present application be limited to the specific embodiments thereof. It will be apparent to those skilled in the art from this disclosure that many more simple derivations or substitutions can be made without departing from the spirit of the disclosure.
Claims (10)
1. An audio monitoring method based on a smart community is characterized by comprising the following steps:
the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to an intelligent audio sensor of a monitored community, and determines a return strategy according to the types of the dangerous sounds; the audio security control center establishes a control center level voiceprint feature database, assigns a unique identifier to any voiceprint feature data in the voiceprint feature database according to a preset identification rule, establishes a community level voiceprint feature database for different communities, and obtains the voiceprint feature identifier in the community level voiceprint feature database from the control center level voiceprint feature database; the audio security control center takes a community as a target unit and distributes the community-level voiceprint feature database to all intelligent audio sensors in the community;
and the audio security control center receives the monitoring data related to the dangerous sound returned by the intelligent audio sensor according to the return strategy.
2. The method of claim 1, wherein the backhaul policy comprises:
if the voiceprint of the monitored person in the monitored community is identified, returning the voiceprint characteristic identification and the original information of the audio data of the monitored person;
and if the voiceprint of the abnormal sound in the monitored community is identified, returning the voiceprint characteristic identification of the abnormal sound.
3. The method of claim 1 or 2, further comprising:
the audio security control center sets the intelligent audio sensor which transmits the monitoring data back to a specific color;
and the audio security control center performs defense and tracking on the movement track of the dangerous sound according to the color of the intelligent audio sensor.
4. An audio monitoring method based on a smart community is characterized by comprising the following steps:
the intelligent audio sensor receives a community-level voiceprint feature database distributed by an audio security control center by taking a community as a target unit, if the local community-level voiceprint feature database does not exist, the received community-level voiceprint feature database is used as a local community-level voiceprint feature database to be stored, otherwise, the received community-level voiceprint feature database is compared with the locally stored community-level voiceprint feature database, and if the difference exists, the received community-level voiceprint feature database is updated; the audio security control center assigns a unique identifier to any voiceprint feature data in the voiceprint feature database according to a preset identification rule and establishes a community-level voiceprint feature database for different communities, and the voiceprint feature identifier in the community-level voiceprint feature database is obtained from the control center-level voiceprint feature database;
the intelligent audio sensor collects audio data and calculates the voiceprint characteristics of the collected audio data;
the intelligent audio sensor compares the voiceprint characteristics of the collected audio data with voiceprint characteristics in a community-level voiceprint characteristic database of dangerous sounds distributed by an audio security control center, and if the comparison is successful, the intelligent audio sensor transmits back monitoring data to the audio security control center according to a back transmission strategy determined by the audio security control center, wherein the back transmission strategy is determined according to the types of the dangerous sounds.
5. An audio monitoring method based on a smart community is characterized by comprising the following steps:
the audio security control center creates a voiceprint feature database of dangerous sounds, distributes the voiceprint feature database to an intelligent audio sensor of a monitored community, and determines a return strategy according to the types of the dangerous sounds; the audio security control center establishes a control center level voiceprint feature database, assigns a unique identifier to any voiceprint feature data in the voiceprint feature database according to a preset identification rule, establishes a community level voiceprint feature database for different communities, and obtains the voiceprint feature identifier in the community level voiceprint feature database from the control center level voiceprint feature database; the audio security control center takes a community as a target unit and distributes the community-level voiceprint feature database to all intelligent audio sensors in the community;
the intelligent audio sensor receives a community-level voiceprint feature database distributed by an audio security control center, if the local community-level voiceprint feature database does not exist, the received community-level voiceprint feature database is used as a local community-level voiceprint feature database to be stored, otherwise, the received community-level voiceprint feature database is compared with the locally-stored community-level voiceprint feature database, and if the difference exists, the received community-level voiceprint feature database is updated;
the intelligent audio sensor collects audio data and calculates the voiceprint characteristics of the collected audio data;
the intelligent audio sensor compares the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the community-level voiceprint characteristic database, and if the comparison is successful, the intelligent audio sensor transmits monitoring data related to dangerous sounds back to the audio security control center according to the feedback strategy;
and the audio security control center receives the monitoring data.
6. The utility model provides an audio security protection control center based on wisdom community which characterized in that includes:
the first processing module is used for creating a voiceprint feature database of dangerous sounds, distributing the voiceprint feature database to an intelligent audio sensor of a monitored community, and determining a return strategy according to the types of the dangerous sounds; the first processing module establishes a control center level voiceprint feature database, assigns a unique identifier to any voiceprint feature data in the voiceprint feature database according to a preset identification rule, establishes a community level voiceprint feature database for different communities, and obtains the voiceprint feature identifier in the community level voiceprint feature database from the control center level voiceprint feature database; distributing the community-level voiceprint feature database to all intelligent audio sensors in the community by taking the community as a target unit;
and the receiving module is used for receiving the monitoring data which are related to the dangerous sounds and transmitted back by the intelligent audio sensor according to the back transmission strategy.
7. The audio security control center of claim 6, further comprising:
and the second processing module is used for setting the intelligent audio sensor which transmits the monitoring data back to a specific color, and performing defense and tracking on the motion trail of the dangerous sound according to the color of the intelligent audio sensor.
8. The utility model provides an intelligence audio sensor based on wisdom community which characterized in that includes:
a module for receiving a community-level voiceprint feature database distributed by an audio security control center by taking a community as a target unit, wherein if the local community-level voiceprint feature database is absent, the module stores the received community-level voiceprint feature database as the local community-level voiceprint feature database, otherwise, the received community-level voiceprint feature database is compared with the locally-stored community-level voiceprint feature database, and if the difference exists, the comparison is carried out; the audio security control center assigns a unique identifier to any voiceprint feature data in the voiceprint feature database according to a preset identification rule and establishes a community-level voiceprint feature database for different communities, and the voiceprint feature identifier in the community-level voiceprint feature database is obtained from the control center-level voiceprint feature database;
the acquisition module is used for acquiring audio data and calculating the voiceprint characteristics of the acquired audio data;
and the comparison module is used for comparing the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the community-level voiceprint characteristic database of the dangerous sounds distributed by the audio security control center, and if the comparison is successful, returning the monitoring data to the audio security control center according to a return strategy determined by the audio security control center, wherein the return strategy is determined according to the types of the dangerous sounds.
9. An audio monitoring system based on an intelligent community is characterized by comprising an audio security control center and an intelligent audio sensor; the audio security control center comprises a first processing module and a receiving module, and the intelligent audio sensor comprises an acquisition module and a comparison module;
the first processing module is used for creating a voiceprint feature database of dangerous sounds, distributing the voiceprint feature database to an intelligent audio sensor of a monitored community, and determining a return strategy according to the types of the dangerous sounds; the first processing module establishes a control center level voiceprint feature database, assigns a unique identifier to any voiceprint feature data in the voiceprint feature database according to a preset identification rule, establishes a community level voiceprint feature database for different communities, and obtains the voiceprint feature identifier in the community level voiceprint feature database from the control center level voiceprint feature database; distributing the community-level voiceprint feature database to all intelligent audio sensors in the community by taking the community as a target unit;
the intelligent audio sensor also comprises a module for receiving a community-level voiceprint feature database distributed by the audio security control center, wherein if the local community-level voiceprint feature database is absent, the module stores the received community-level voiceprint feature database as the local community-level voiceprint feature database, otherwise, the received community-level voiceprint feature database is compared with the locally-stored community-level voiceprint feature database, and if the difference exists, the received community-level voiceprint feature database is updated;
the acquisition module is used for acquiring audio data and calculating the voiceprint characteristics of the acquired audio data;
the comparison module is used for comparing the voiceprint characteristics of the collected audio data with the voiceprint characteristics in the community-level voiceprint characteristic database, and if the comparison is successful, the monitoring data are transmitted back to the audio security control center according to a feedback strategy determined by the audio security control center;
the receiving module is used for receiving the monitoring data.
10. A computer-readable storage medium, characterized by comprising a program which is executable by a processor to implement the method of any one of claims 1-5.
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 CN109524012A (en) | 2019-03-26 |
| CN109524012B true 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) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712629B (en) * | 2020-12-29 | 2022-06-17 | 浙江广维通信有限公司 | Intelligent community security monitoring device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Family Cites Families (4)
| 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 |
| 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 |
| CN107590439B (en) * | 2017-08-18 | 2020-12-15 | 湖南文理学院 | Target person identification and tracking method and device based on monitoring video |
-
2018
- 2018-11-28 CN CN201811469371.9A patent/CN109524012B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109524012A (en) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102036158B (en) | sound monitoring system and speech collection system | |
| US9953517B2 (en) | Risk early warning method and apparatus | |
| CN102752574B (en) | Video monitoring system and method | |
| WO2011041977A1 (en) | Cross monitoring method and system based on voiceprint identification and location tracking | |
| US20150120291A1 (en) | Scene Recognition Method, Device and Mobile Terminal Based on Ambient Sound | |
| CN101364408A (en) | Sound image combined monitoring method and system | |
| CN110311812B (en) | Network analysis method, device and storage medium | |
| CN111294812A (en) | Method and system for resource capacity expansion planning | |
| CN107179995A (en) | A kind of performance test methods of application program of computer network | |
| CN105869226A (en) | Face-recognition-based automatic roll-call system and method for prisons | |
| KR102151272B1 (en) | Method, apparatus and computer program for analyzing data using prediction model | |
| KR102315699B1 (en) | Method, apparatus and computer program for determining event occurrence of video data using artificial intelligence | |
| CN109524012B (en) | Audio security control center, intelligent audio sensor, monitoring method and system | |
| EP4040764A2 (en) | Method and apparatus for in-vehicle call, device, computer readable medium and product | |
| CN106502856B (en) | A kind of information processing method and device | |
| CN111310647A (en) | Generation method and device for automatic identification falling model | |
| CN114413409A (en) | Detection method and device for air conditioner fault probability and intelligent air conditioner | |
| CN111901134A (en) | Method and device for predicting network quality based on recurrent neural network model (RNN) | |
| CN112203135B (en) | Intelligent double-recording method, system and server | |
| CN113691483B (en) | Method, device and equipment for detecting abnormal user equipment and storage medium | |
| CN105528578A (en) | Online training monitoring method based on sound image process tracking | |
| CN113158835A (en) | Traffic accident intelligent detection method based on deep learning | |
| CN112365520A (en) | Pedestrian target real-time tracking system and method based on video big data resource efficiency evaluation | |
| CN115664006B (en) | Intelligent management and control integrated platform for incremental power distribution network | |
| CN110708370A (en) | Data processing method and terminal |
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 |