CN109410955A - A kind of time slot scrambling of voice data, system, device and storage medium - Google Patents
A kind of time slot scrambling of voice data, system, device and storage medium Download PDFInfo
- Publication number
- CN109410955A CN109410955A CN201811495704.5A CN201811495704A CN109410955A CN 109410955 A CN109410955 A CN 109410955A CN 201811495704 A CN201811495704 A CN 201811495704A CN 109410955 A CN109410955 A CN 109410955A
- Authority
- CN
- China
- Prior art keywords
- voice data
- target
- voiceprint
- data
- secrecy
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 claims abstract description 96
- 238000012806 monitoring device Methods 0.000 claims abstract description 39
- 230000001755 vocal effect Effects 0.000 claims description 33
- 238000000034 method Methods 0.000 claims description 23
- 239000012634 fragment Substances 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000000638 solvent extraction Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Storage Device Security (AREA)
Abstract
This application discloses a kind of time slot scramblings of voice data, it is different from the mode for directly directly transferring to monitoring device to store original, untreated voice data, the application is after collecting primary voice data, before transferring to monitoring device to store, can also secrecy processing be carried out to primary voice data, so that monitoring device storage is the secure voice data for being clearly distinguishable from primary voice data.Even if database is dragged library or is stolen, stealer can only also access the voice data by secrecy processing, since there are significant differences with primary voice data for it, it cannot achieve purpose of the counterfeit real user by Application on Voiceprint Recognition, store the voice data of user in safer mode.The application further simultaneously discloses the secrecy system, device and computer readable storage medium of a kind of voice data, has above-mentioned beneficial effect.
Description
Technical field
This application involves language data process technical field, in particular to a kind of time slot scrambling of voice data, system, dress
It sets and computer readable storage medium.
Background technique
With the fast development of sound groove recognition technology in e, use sound that is unique, belonging to individual subscriber as being by application
The mode at family is gradually used in various fields, such as mobile payment, remote validation, remote authorization etc..
It in public and inherently safe is ensured, safeguards that collective and individual interest are inviolable, setting prison is widely used now
The mode of equipment is controlled to record image and voice data (being referred to as voice data, voice data etc.), in order to see in real time
It examines or the later period calls to account.
It is directly by collected raw tone number since existing monitoring device is when recording the voice data of target scene
According to being stored, once the database that the monitoring device manufacturer saves these voice data is dragged library or is stolen, raw tone
Data will counterfeit true user be by way of playback come by some verifyings or identification, and then to individual subscriber property
It threatens or heavy losses.
Therefore, how to overcome existing monitoring device saving voice data is existing technological deficiency, provides and a kind of more pacifies
Full voice data processing method is this field so that cannot counterfeit real user database is dragged library or is stolen
Technical staff's urgent problem to be solved.
Summary of the invention
The main purpose of the application is to provide a kind of time slot scrambling of voice data, be different from directly by it is original, without
The mode that the voice data of processing directly transfers to monitoring device to be stored, the application collect primary voice data it
Afterwards, before transferring to monitoring device to be stored, can also secrecy processing be carried out to primary voice data, so that monitoring device storage
It is the secure voice data for being clearly distinguishable from primary voice data.Even if database is dragged library or is stolen, stealer also can only
The voice data by secrecy processing is accessed, since there are significant differences with primary voice data for it, cannot achieve counterfeit true
Real user stores the voice data of user in safer mode by the purpose of Application on Voiceprint Recognition.
The another object of the application is the provision of the secrecy system, device and computer-readable storage of a kind of voice data
Medium.
To achieve the above object, this application provides a kind of time slot scramblings of voice data, comprising:
Acquire the voice data under target scene；
Secrecy processing is carried out to the target speech data in the voice data, obtains secure voice data；
The secure voice data are sent to the monitoring device under the target scene, so that the monitoring device stores
Be carry out secrecy processing after target speech data.
Optionally, secrecy processing is carried out to the target speech data in the voice data, obtains secure voice data, wrapped
It includes:
Extract the voiceprint for including in the voice data；
Determine the target voiceprint in the voiceprint according to preset secrecy processing vocal print library, and obtain with it is described
The corresponding target speech data of target voiceprint；Wherein, in need protected is stored in advance in secrecy processing vocal print library
The voiceprint of close processing；
Secrecy processing is carried out to the target speech data, obtains the secure voice data.
Optionally, the voiceprint for including in the voice data is extracted, comprising:
Divide the voice data, obtains multiple audio fragments；
Voiceprint wherein included is extracted from each audio fragment respectively.
Optionally, it after the voiceprint for including in extracting the voice data, is obtaining believing with the target vocal print
Before ceasing corresponding target speech data, further includes:
The voice data is split by the type for extracting obtained voiceprint, obtains believing with vocal print described in every kind
Cease corresponding sound bite；
It is corresponding, obtain target speech data corresponding with the target voiceprint, comprising:
Target voice segment corresponding with the target voiceprint is obtained, and using the target voice segment as described in
Target speech data.
Optionally, the mode of secrecy processing is carried out, comprising:
It adjusts the sound characteristic of the target speech data predetermined time, be more than default feature by the target speech data
The sound characteristic of threshold value reduced, be added in the target speech data in random noise at least one of；Wherein, described
Sound characteristic includes at least one in tone color, tone and loudness of a sound.
To achieve the above object, present invention also provides a kind of secrecy systems of voice data, comprising:
Primary voice data acquisition unit, for acquiring the voice data under target scene；
Voice data secrecy processing unit, for carrying out secrecy processing to the target speech data in the voice data,
Obtain secure voice data；
Secure voice data transmission unit, the monitoring for being sent to the secure voice data under the target scene
Equipment, so that monitoring device storage is the target speech data carried out after secrecy processing.
Optionally, the voice data secrecy processing unit includes:
Voiceprint extracts subelement, for extracting the voiceprint for including in the voice data；
Target voiceprint and target speech data determine subelement, for being determined according to preset secrecy processing vocal print library
Target voiceprint in the voiceprint, and obtain target speech data corresponding with the target voiceprint；Wherein,
The voiceprint in need for carrying out secrecy processing is stored in advance in secrecy processing vocal print library；
Secrecy processing subelement obtains the secure voice number for carrying out secrecy processing to the target speech data
According to.
Optionally, the voiceprint extraction subelement includes:
Voice data divides module and obtains multiple audio fragments for dividing the voice data；
Voiceprint distinguishes extraction module, for extracting vocal print letter wherein included from each audio fragment respectively
Breath.
Optionally, the secrecy system of the voice data further include:
By type split cells, after the voiceprint for including in extracting the voice data, obtaining and institute
Before stating the corresponding target speech data of target voiceprint, by the voice data by the type for extracting obtained voiceprint
It is split, obtains sound bite corresponding with voiceprint described in every kind；
Corresponding, the target voiceprint and target speech data determine that subelement includes:
Target voice segment determining module, for obtaining target voice segment corresponding with the target voiceprint, and
Using the target voice segment as the target speech data.
To achieve the above object, present invention also provides a kind of privacy devices of voice data, comprising:
Memory, for storing computer program；
Processor realizes the secrecy side of the voice data as described in above content when for executing the computer program
Method.
To achieve the above object, described computer-readable to deposit present invention also provides a kind of computer readable storage medium
It is stored with computer program on storage media, the language as described in above content is realized when the computer program is executed by processor
The time slot scrambling of sound data.
Obviously, the time slot scrambling of voice data provided herein is different from original, untreated language directly
The mode that sound data directly transfer to monitoring device to be stored, the application after collecting primary voice data, transfer to supervise
Before control equipment is stored, can also secrecy processing be carried out to primary voice data, so that monitoring device storage is obvious area
Not in the secure voice data of primary voice data.Even if database is dragged library or is stolen, stealer can only also access through
It is logical to cannot achieve counterfeit real user since there are significant differences with primary voice data for it for the voice data for crossing secrecy processing
The purpose for crossing Application on Voiceprint Recognition stores the voice data of user in safer mode.
The application additionally provides the secrecy system, device and computer readable storage medium of a kind of voice data simultaneously, tool
There is above-mentioned beneficial effect, details are not described herein.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of application for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of the time slot scrambling of voice data provided by the embodiments of the present application；
Fig. 2 is the method that a kind of pair of target speech data carries out secrecy processing in time slot scrambling provided by the embodiments of the present application
Flow chart；
Fig. 3 is the side that another kind carries out secrecy processing to target speech data in time slot scrambling provided by the embodiments of the present application
The flow chart of method；
Fig. 4 is a kind of structural block diagram of the secrecy system of voice data provided by the embodiments of the present application；
Fig. 5 is the company between a kind of privacy device and sound pick-up and monitoring device of voice data provided by the embodiments of the present application
Connect relation schematic diagram.
Specific embodiment
The core of the application is to provide time slot scrambling, system, device and the computer-readable storage medium of a kind of voice data
Matter is different from the mode for directly directly transferring to monitoring device to store original, untreated voice data, the application
After collecting original voice data, before transferring to monitoring device to be stored, can also to original voice data into
Row secrecy processing, so that monitoring device storage is the secure voice data for being clearly distinguishable from primary voice data.Even if data
Library is dragged library or is stolen, and stealer can only also access the voice data by secrecy processing, due to itself and original voice
There are significant differences for data, cannot achieve counterfeit real user by the purpose of identification, make the voice data of user more to pacify
Full mode stores.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
All other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Embodiment one
Referring to Figure 1, Fig. 1 is a kind of flow chart of the time slot scrambling of voice data provided by the embodiments of the present application, packet
Include following steps:
S101: the voice data under acquisition target scene；
This step is intended to obtain voice data original, without any processing, i.e., user is under target scene with a voice
The language that sound is said.To be different from the secure voice data that subsequent progress secrecy processing obtains, the application will illustrate to solve subsequent
Part is released, it is unified that " primary voice data " is used to indicate the voice data that this step collects.
S102: secrecy processing is carried out to the target speech data in voice data, obtains secure voice data；
On the basis of S101, this step is intended to carry out secrecy processing to the target speech data in primary voice data,
To obtain differing markedly from the secure voice data of primary voice data.
Wherein, due under many scenes monitoring device be mainly used for recording the sound of user, and usually may include more
A respective sound of user, therefore target speech data both can simply refer to the voice of all users under scene, can also refer to
The voice of some special user under scene.When monitoring device is also used to record such as equipment sound, the target speech data is also
What is issued when can be in special state with certain equipment has the sound of identification meaning, herein and is not specifically limited, can root
According to the demand flexible choice under practical application scene.
When target speech data is the part of speech data in full dose primary voice data, it is also necessary to which screening step is come
The target speech data for needing to be encrypted accurately is filtered out from full dose primary voice data.By taking specific voice as an example,
The voiceprint of specific voice usually can be used as screening foundation, i.e., extract and wrapped from full dose primary voice data first
In the vocal print type contained, then vocal print type in judging to extract whether include specific voice vocal print, if comprising will be corresponding special
The voice data of vocal print is determined as target speech data, and secrecy processing is carried out to it.
Further, in order to increase screening efficiency, can with side acquire just carry out voiceprint extraction and with specific sound
Comparison between line.In order to further increase efficiency, collected primary voice data can also be pressed to default partitioning scheme point
Multiple audio fragments are cut into, in order to extract the vocal print for including letter respectively from multiple audio fragments simultaneously in a parallel fashion
Breath, in order to obtain all audio fragments comprising specific vocal print.Wherein, partitioning scheme can be for by the progress of certain file size
Divide (such as 20KB), can also be split by certain segment clip durations (such as 10 seconds) or other same or similar
Partitioning scheme is subject to and is more in line with actually located application scenarios or meets existing particular/special requirement, do not do specific limit herein
It is fixed.
Specifically, the mode for carrying out secrecy processing may include:
The sound characteristic for adjusting target speech data predetermined time (may include at least one in tone color, tone and loudness of a sound
), the sound characteristic that target speech data is more than default characteristic threshold value reduced, be added in target speech data it is random
At least one of in noise.It certainly, further include that the voice data in some period is subjected to entirety other than several above-mentioned
Condition, and the introducing of noise be also possible to made noise can preset interference noise etc., do not do specific limit herein
Fixed, the purpose for carrying out secrecy processing is to change the voiceprint that can be extracted from secure voice data, so that secrecy
Voice data cannot be extracted voiceprint identical with primary voice data by application on voiceprint recognition equipment by way of playback,
To achieve the purpose that also cannot counterfeit real user after data are stolen passes through Application on Voiceprint Recognition.
S103: being sent to the monitoring device under target scene for secure voice data so that monitoring device storage be into
Target speech data after row secrecy processing.
On the basis of S102, the secure voice data that this step is intended to obtain after the completion of secrecy processing are sent to target
Monitoring device under scene, so that monitoring device storage is the target speech data carried out after secrecy processing.
It should be noted that when the target speech data for being performed secrecy processing is only a part of full dose voice data
When, illustrate that the voice data of remaining part does not need to carry out secrecy processing, but not encrypted voice data also will together can
It is sent to the monitoring device, to guarantee the integrality of voice data storage.But due to just for property to target voice number
According to having carried out secrecy processing, it is thus possible to the secure voice data for also needing to obtain and remaining do not carry out the original of secrecy processing
Beginning voice data does scene merging so that the voice content being stored in monitoring device be it is consistent with actual scene, only
When reading again out, wherein the voice of someone is different from its true voice, similar to be in news interview
The case where protection has done voice change process to its sound by the privacy of interviewer.
It grabs the voice data with specific vocal print and is replaced using the secure voice data after progress secrecy processing,
This portion of techniques belongs to well-known to those skilled in the art, conventional content, and present invention point is also not and how to grab
It takes and replaces, therefore details are not described herein again.
Based on the above-mentioned technical proposal, the time slot scrambling of voice data provided by the embodiments of the present application, being different from directly will be former
The mode that voice data begin, untreated directly transfers to monitoring device to be stored, the application are collecting original language
After sound data, before transferring to monitoring device to be stored, can also secrecy processing be carried out to primary voice data, so that monitoring is set
Standby storage is the secure voice data for being clearly distinguishable from primary voice data.Even if database is dragged library or is stolen, steal
Person can only also access the voice data by secrecy processing, since there are significant difference, Wu Fashi with primary voice data for it
Existing purpose of the counterfeit real user by Application on Voiceprint Recognition, stores the voice data of user in safer mode.
Embodiment two
Fig. 2 is referred to, Fig. 2 is that a kind of pair of target speech data maintains secrecy in time slot scrambling provided by the embodiments of the present application
The flow chart of the method for processing, the present embodiment give a kind of concrete implementation mode for the S102 in embodiment one, utilize
The mesh for needing to carry out secrecy processing in full dose primary voice data is screened to obtain in the secrecy processing vocal print library pre-established
Voiceprint is marked, in order to targetedly carry out secrecy processing to target speech data corresponding with target voiceprint.I.e. originally
The voice data for being used for some or certain high user of several security classifications under target scene is carried out secrecy processing by example,
Specifically includes the following steps:
S201: the voiceprint for including in voice data is extracted；
This step, which is intended to extract from full dose primary voice data, obtains all voiceprints wherein included, it is assumed that one
Segment length has recorded altogether the dialog procedure of 10 people up in 50 minutes full dose primary voice datas, that is to say, that passes through this step
Rapid extraction will access 10 kinds of different voiceprints.
S202: determining the target voiceprint in voiceprint according to preset secrecy processing vocal print library, and obtains and mesh
Mark the corresponding target speech data of voiceprint；
On the basis of S201, this step is intended to determine the target in voiceprint according to preset secrecy processing vocal print library
Voiceprint continues above example, it is assumed that the number of corresponding 10 users of 10 kinds of voiceprints extracted above is
01,02 ..., 09,10, and 02 user in numbering and 09 user have been previously-completed the registration of its voiceprint, and are added
The secrecy processing vocal print library, therefore the processing Jing Guo this step are added, is exactly 02 use by be identified as target voiceprint
The corresponding voiceprint in family and the corresponding voiceprint of 09 user.
After determining target voiceprint, just only need to obtain target speech data corresponding with target voiceprint
The secrecy processing carried out for subsequent step.
S203: secrecy processing is carried out to target speech data, obtains secure voice data.
Embodiment three
Fig. 3 is referred to, Fig. 3 is that another kind protects target speech data in time slot scrambling provided by the embodiments of the present application
The flow chart of the method for close processing, in order on the basis of example 2, it is further provided one kind can quickly obtain target language
The method of sound data, the present embodiment provide a kind of concrete implementation mode by S302 and S304, include the following steps:
S301: the voiceprint for including in voice data is extracted；
S302: voice data is split by the type for extracting obtained voiceprint, is obtained and every kind of voiceprint
Corresponding sound bite；
On the basis of S301, full dose primary voice data is torn open according to the type for extracting obtained voiceprint
Point, to obtain sound bite corresponding with every kind of voiceprint.Continue above example, that is to say, that can be each by this 10 users
From voice data peel away, formed only include respective voice data sound bite.
S303: the target voiceprint in voiceprint is determined according to preset secrecy processing vocal print library；
S304: target voice segment corresponding with target voiceprint is obtained, and using target voice segment as target language
Sound data；
On the basis of S302 and S303, once it is determined that target voiceprint, can also directly obtain and target vocal print
The corresponding sound bite of information, so that it may quickly obtain needing to carry out the complete voice of secrecy processing.
S305: secrecy processing is carried out to target speech data, obtains secure voice data.
It should be noted that implementation provided in this embodiment, it is more suitable for can be disposably to full dose voice data
Under the scene being uniformly processed, i.e., under scene not high to the requirement of real-time of processing, system can be made full use of in this scenario
The advantage of one processing, speed up processing increase efficiency.
It is higher for requirement of real-time, need to extract in acquisition, side is screened, the scene of Bian Jinhang secrecy processing, this Shen
Please also directed to another embodiment of offer of property:
The primary voice data collected in real time is divided into multiple audio pieces with default partitioning scheme in chronological order
Section；
Successively extract the voiceprint for including in the audio fragment that each is partitioned into；
Successively judge in each audio fragment whether to include the spy for needing to carry out secrecy processing according to secrecy processing vocal print library
Determine vocal print；
Voice data corresponding with specific vocal print in audio fragment comprising specific vocal print is subjected to secrecy processing, remaining sound
The corresponding voice data of line is without any processing, obtains audio fragment after secrecy processing, and by audio fragment after the secrecy processing
Monitoring device is sent to be saved；
The audio fragment for not including specific vocal print is directly sent to monitoring device to save.
Through the above technical solutions, being satisfied scene to the high request of real-time, and since monitoring device is by acquisition
The audio fragment that sequence successively obtains, it is only necessary to which the later period is successively integrated in storage, quite convenient for operation.
Because situation is complicated, it can not enumerate and be illustrated, those skilled in the art should be able to recognize according to the application
The basic skills principle combination actual conditions of offer may exist many examples, in the case where not paying enough creative works,
It should within the scope of protection of this application.
Example IV
Fig. 4 is referred to below, and Fig. 4 is a kind of structural frames of the secrecy system of voice data provided by the embodiments of the present application
Figure, the system may include:
Primary voice data acquisition unit 100, for acquiring the voice data under target scene；
Voice data secrecy processing unit 200 is obtained for carrying out secrecy processing to the target speech data in voice data
To secure voice data；
Secure voice data transmission unit 300, the monitoring device for being sent to secure voice data under target scene,
So that monitoring device storage is the target speech data carried out after secrecy processing.
Wherein, which may include:
Voiceprint extracts subelement, for extracting the voiceprint for including in voice data；
Target voiceprint and target speech data determine subelement, for being determined according to preset secrecy processing vocal print library
Target voiceprint in voiceprint, and obtain target speech data corresponding with target voiceprint；Wherein, secrecy processing
The voiceprint in need for carrying out secrecy processing is stored in advance in vocal print library；
Secrecy processing subelement obtains secure voice data for carrying out secrecy processing to target speech data.
Wherein, voiceprint extraction subelement may include:
Voice data divides module and obtains multiple audio fragments for dividing voice data；
Voiceprint distinguishes extraction module, for extracting voiceprint wherein included from each audio fragment respectively.
Further, which can also include:
By type split cells, after the voiceprint for including in extracting voice data, obtaining and target sound
Before the corresponding target speech data of line information, voice data is split by the type for extracting obtained voiceprint, is obtained
To sound bite corresponding with every kind of voiceprint；
Corresponding, the target voiceprint and target speech data determine that subelement may include:
Target voice segment determining module, for obtaining target voice segment corresponding with target voiceprint, and by mesh
Sound bite is marked as target speech data.
The corresponding time slot scrambling with voice data of the secrecy system of the voice data, the present embodiment as with embodiment of the method
Corresponding system embodiment exists, and has beneficial effect identical with embodiment of the method, no longer repeats one by one herein.
Based on the above embodiment, present invention also provides a kind of privacy devices of voice data, which can
To include memory and processor, wherein have computer program in the memory, which calls the meter in the memory
When calculation machine program, step provided by above-described embodiment may be implemented.Certainly, the secrecy processing device can also include it is various must
Network interface, power supply and other components for wanting etc..
Specifically, the function component that the privacy device of the voice data can integrate in original monitoring device,
It is also contemplated that being integrated by monitoring device producer so that the problem of security process reverse reduction that may be present, by the guarantor
The accessory that close device can be individually attached in monitoring device as one, the accessory can voluntarily carry out secrecy processing side by user
The configuration of formula, so that safety is higher.It is a kind of include but is not limited to connection type can be found in Fig. 5.
Present invention also provides a kind of computer readable storage mediums, have computer program thereon, the computer program
Step provided by above-described embodiment may be implemented when being performed terminal or processor execution.The storage medium may include: U
Disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), the various media that can store program code such as magnetic or disk.
Specific examples are used herein to illustrate the principle and implementation manner of the present application, and between each embodiment
For progressive relationship, each embodiment focuses on the differences from other embodiments, identical between each embodiment
Similar portion may refer to each other.For the device disclosed in the embodiment, reference can be made to corresponding method part illustration.The above reality
The explanation for applying example is merely used to help understand the present processes and its core concept.For the ordinary skill people of the art
Member for, under the premise of not departing from the application principle, can also to the application, some improvement and modification can also be carried out, these improve and
Modification is also fallen into the protection scope of the claim of this application.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also other elements including being not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or equipment for including element.
Claims (10)
1. a kind of time slot scrambling of voice data characterized by comprising
Acquire the voice data under target scene；
Secrecy processing is carried out to the target speech data in the voice data, obtains secure voice data；
The secure voice data are sent to the monitoring device under the target scene, so that monitoring device storage is
Target speech data after carrying out secrecy processing.
2. time slot scrambling according to claim 1, which is characterized in that the target speech data in the voice data into
Row secrecy processing obtains secure voice data, comprising:
Extract the voiceprint for including in the voice data；
The target voiceprint in the voiceprint is determined according to preset secrecy processing vocal print library, and is obtained and the target
The corresponding target speech data of voiceprint；Wherein, in need carry out at secrecy is stored in advance in secrecy processing vocal print library
The voiceprint of reason；
Secrecy processing is carried out to the target speech data, obtains the secure voice data.
3. time slot scrambling according to claim 2, which is characterized in that extract the vocal print letter for including in the voice data
Breath, comprising:
Divide the voice data, obtains multiple audio fragments；
Voiceprint wherein included is extracted from each audio fragment respectively.
4. time slot scrambling according to claim 2, which is characterized in that the vocal print letter for including in extracting the voice data
After breath, before obtaining target speech data corresponding with the target voiceprint, further includes:
The voice data is split by the type for extracting obtained voiceprint, is obtained and voiceprint pair described in every kind
The sound bite answered；
It is corresponding, obtain target speech data corresponding with the target voiceprint, comprising:
Target voice segment corresponding with the target voiceprint is obtained, and using the target voice segment as the target
Voice data.
5. time slot scrambling according to any one of claims 1 to 4, which is characterized in that carry out the mode of secrecy processing, wrap
It includes:
It adjusts the sound characteristic of the target speech data predetermined time, be more than default characteristic threshold value by the target speech data
Sound characteristic reduced, in the target speech data be added random noise at least one of；Wherein, the sound
Feature includes at least one in tone color, tone and loudness of a sound.
6. a kind of secrecy system of voice data characterized by comprising
Primary voice data acquisition unit, for acquiring the voice data under target scene；
Voice data secrecy processing unit is obtained for carrying out secrecy processing to the target speech data in the voice data
Secure voice data；
Secure voice data transmission unit, the monitoring for the secure voice data to be sent under the target scene are set
It is standby, so that monitoring device storage is the target speech data carried out after secrecy processing.
7. secrecy system according to claim 6, which is characterized in that the voice data secrecy processing unit includes:
Voiceprint extracts subelement, for extracting the voiceprint for including in the voice data；
Target voiceprint and target speech data determine subelement, for according to the determination of preset secrecy processing vocal print library
Target voiceprint in voiceprint, and obtain target speech data corresponding with the target voiceprint；Wherein, described
The voiceprint in need for carrying out secrecy processing is stored in advance in secrecy processing vocal print library；
Secrecy processing subelement obtains the secure voice data for carrying out secrecy processing to the target speech data.
8. secrecy system according to claim 6, which is characterized in that further include:
By type split cells, after the voiceprint for including in extracting the voice data, obtaining and the mesh
Before marking the corresponding target speech data of voiceprint, the voice data is carried out by the type for extracting obtained voiceprint
It splits, obtains sound bite corresponding with voiceprint described in every kind；
Corresponding, the target voiceprint and target speech data determine that subelement includes:
Target voice segment determining module, for obtaining target voice segment corresponding with the target voiceprint, and by institute
Target voice segment is stated as the target speech data.
9. a kind of privacy device of voice data characterized by comprising
Memory, for storing computer program；
Processor realizes the guarantor such as voice data described in any one of claim 1 to 5 when for executing the computer program
Decryption method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the secrecy such as voice data described in any one of claim 1 to 5 when the computer program is executed by processor
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811495704.5A CN109410955A (en) | 2018-12-07 | 2018-12-07 | A kind of time slot scrambling of voice data, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811495704.5A CN109410955A (en) | 2018-12-07 | 2018-12-07 | A kind of time slot scrambling of voice data, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109410955A true CN109410955A (en) | 2019-03-01 |
Family
ID=65457819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811495704.5A Pending CN109410955A (en) | 2018-12-07 | 2018-12-07 | A kind of time slot scrambling of voice data, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109410955A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428844A (en) * | 2019-07-31 | 2019-11-08 | 歌尔科技有限公司 | Speech verification method, electronic equipment, audio frequency apparatus and the medium of electronic equipment |
| CN111935153A (en) * | 2020-08-11 | 2020-11-13 | 北京天融信网络安全技术有限公司 | CAN bus-based target message extraction method and device and storage medium |
| CN115378980A (en) * | 2022-10-20 | 2022-11-22 | 广州万协通信息技术有限公司 | Directional storage method and device for driving monitoring data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096937A (en) * | 2015-05-26 | 2015-11-25 | 努比亚技术有限公司 | Voice data processing method and terminal |
| CN105279447A (en) * | 2014-06-23 | 2016-01-27 | 中兴通讯股份有限公司 | Method and device for data encryption, and method and device for data decryption |
| US20170092276A1 (en) * | 2014-07-31 | 2017-03-30 | Tencent Technology (Shenzhen) Company Limited | Voiceprint Verification Method And Device |
| CN107978320A (en) * | 2017-11-28 | 2018-05-01 | 上海与德科技有限公司 | One kind call method of adjustment, device, equipment and medium |
| CN108806701A (en) * | 2018-06-11 | 2018-11-13 | 广州势必可赢网络科技有限公司 | Voice data method for scrambling and device, voice data de-scrambling method and device |
-
2018
- 2018-12-07 CN CN201811495704.5A patent/CN109410955A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279447A (en) * | 2014-06-23 | 2016-01-27 | 中兴通讯股份有限公司 | Method and device for data encryption, and method and device for data decryption |
| US20170092276A1 (en) * | 2014-07-31 | 2017-03-30 | Tencent Technology (Shenzhen) Company Limited | Voiceprint Verification Method And Device |
| CN105096937A (en) * | 2015-05-26 | 2015-11-25 | 努比亚技术有限公司 | Voice data processing method and terminal |
| CN107978320A (en) * | 2017-11-28 | 2018-05-01 | 上海与德科技有限公司 | One kind call method of adjustment, device, equipment and medium |
| CN108806701A (en) * | 2018-06-11 | 2018-11-13 | 广州势必可赢网络科技有限公司 | Voice data method for scrambling and device, voice data de-scrambling method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428844A (en) * | 2019-07-31 | 2019-11-08 | 歌尔科技有限公司 | Speech verification method, electronic equipment, audio frequency apparatus and the medium of electronic equipment |
| CN111935153A (en) * | 2020-08-11 | 2020-11-13 | 北京天融信网络安全技术有限公司 | CAN bus-based target message extraction method and device and storage medium |
| CN111935153B (en) * | 2020-08-11 | 2022-04-26 | 北京天融信网络安全技术有限公司 | CAN bus-based target message extraction method and device and storage medium |
| CN115378980A (en) * | 2022-10-20 | 2022-11-22 | 广州万协通信息技术有限公司 | Directional storage method and device for driving monitoring data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111385283B (en) | Double-recording video synthesis method and double-recording system of self-service equipment | |
| US10135818B2 (en) | User biological feature authentication method and system | |
| CN107239954B (en) | Method and device for increasing block generation speed | |
| CN109410955A (en) | A kind of time slot scrambling of voice data, system, device and storage medium | |
| US7346472B1 (en) | Method and device for monitoring and analyzing signals | |
| CN105337928B (en) | Method for identifying ID, safety protection problem generation method and device | |
| CN102142254A (en) | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method | |
| JP2004310117A (en) | Method for embedding and detecting watermark by quantization of characteristic value of signal | |
| CN103310139A (en) | Input validation method and input validation device | |
| CN106302534A (en) | A kind of detection and the method and system of process disabled user | |
| CN105872749A (en) | Video processing method and device | |
| CN102567657A (en) | Digital work ownership authentication system and digital work ownership authentication method | |
| WO2015196642A1 (en) | Data encryption method, decryption method and device | |
| CN113256288B (en) | Bank card unhooking method and device | |
| CN114786038A (en) | Low-custom live broadcast behavior monitoring method based on deep learning | |
| CN104346547A (en) | Intelligent identity identification system | |
| CN106528696B (en) | A method of extracting android system QQ account | |
| CN113299016A (en) | Service timing method and system of self-service terminal, self-service equipment and storage medium | |
| CN117235406B (en) | Information content security management and control method and device based on block chain | |
| CN107393054A (en) | Drive recorder and its method for data protection and identification | |
| CN101872512A (en) | Display method and equipment of overlaid transaction data | |
| CN112241541A (en) | Community security application method based on block chain and portrait recognition technology | |
| CN116415236A (en) | Distributed storage data safety state identification and protection method | |
| CN113365100A (en) | Video processing method and device | |
| CN116049797A (en) | Intelligent storage system based on data classification 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |