CN109036434A - A kind of method, device and equipment for assisting cracking of cases by vocal print - Google Patents
A kind of method, device and equipment for assisting cracking of cases by vocal print Download PDFInfo
- Publication number
- CN109036434A CN109036434A CN201810892417.1A CN201810892417A CN109036434A CN 109036434 A CN109036434 A CN 109036434A CN 201810892417 A CN201810892417 A CN 201810892417A CN 109036434 A CN109036434 A CN 109036434A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- voice
- identified
- original
- cracking
- 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
- 230000001755 vocal effect Effects 0.000 title claims abstract description 267
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000005336 cracking Methods 0.000 title claims abstract description 55
- 238000011840 criminal investigation Methods 0.000 claims abstract description 26
- 238000003860 storage Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 10
- 230000001815 facial effect Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification 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
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)
- Alarm Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of methods for assisting cracking of cases by vocal print, this method comprises: the voice to be identified collected；The voice to be identified is parsed, to generate corresponding vocal print；The vocal print of the voice to be identified and the original vocal print in vocal print library are compared, and determine the comparison result of the original vocal print to match with the vocal print of the voice to be identified, wherein, the vocal print library pre-establishes, is stored with multiple original vocal prints and the database of identification information corresponding with the original vocal print；According to the comparing result that matching obtains, the identity information of the corresponding criminal investigation object of the voice to be identified is determined.The method and device provided by the present invention that cracking of cases is assisted by vocal print, can be acquired using telephone microphone, mobile phone, microphone etc., be reduced costs, usage scenario is more extensive；And due to use vocal print library so that the storage of voice print database, search it is more convenient, improve the operational efficiency of public security system.
Description
Technical field
The present invention relates to public safety technical field, more particularly to it is a kind of by vocal print assist cracking of cases method,
Device, equipment and computer readable storage medium.
Background technique
In existing public safety field, in terms of cracking of cases is assisted especially by identification suspect's identity, usually
It is all to establish the personally identifiable information library based on personal facial information in advance, then pass through all parts of the country using face recognition technology
Camera, carry out real-time face detection, compared with the facial information of the suspect in library, can search crime dislike
People is doubted, or missing in Missing Persons and library by realizing that this technology of identity validation is applied to search by face recognition technology
Population facial information compares, and can search Missing Persons.
Existing facial recognition techniques scheme is main when implementing problem is encountered that face information acquisition difficulty is bigger,
If collecting a face picture clearly, lossless, to hardware device, such as camera own specifications require very
Height, and camera monitoring range is extremely limited, if thinking to cover on a large scale, needs a considerable amount of cameras, higher cost, and
Observed object blocks face, for example, put on a hat or mask in the case where, recognition of face is with regard to helpless.
Summary of the invention
Assist method, apparatus, equipment and the computer of cracking of cases can by vocal print the object of the present invention is to provide a kind of
Read storage medium, it is therefore intended that solve it is existing using recognition of face determine personal identification technological means usage scenario it is single, make
With condition the problem of harsh and higher cost.
In order to solve the above technical problems, the present invention provides a kind of method for assisting cracking of cases by vocal print, comprising:
The voice to be identified collected；
The voice to be identified is parsed, to generate corresponding vocal print；
The vocal print of the voice to be identified and the original vocal print in vocal print library are compared, and it is determining with it is described to be identified
The comparison result for the original vocal print that the vocal print of voice matches, wherein the vocal print library pre-establishes, is stored with multiple originals
The database of beginning vocal print and identification information corresponding with the original vocal print；
According to the comparing result that matching obtains, the identity information of the corresponding criminal investigation object of the voice to be identified is determined.
Optionally, pre-establishing the vocal print library includes:
When social insurance is added in user, the vocal print of the user is acquired, as the original vocal print, and is added corresponding
The identification information establishes the vocal print library.
Optionally, the corresponding identification information of the addition includes:
Acquisition time, collecting location, the identity information of the user and the corresponding case for adding the original vocal print are compiled
At least one in number is used as the corresponding identification information.
Optionally, after the identity information of the corresponding criminal investigation object of the determination voice to be identified further include:
Output acquires the geographical location information of the voice to be identified.
Optionally, the voice to be identified collected includes:
Receive the voice of the collected criminal investigation object being stored into public security database in advance；
Or receive the voice to be identified for the acquisition equipment acquisition placed from each public place；
Or receive the voice to be identified of the microphone acquisition from communicating terminal.
The present invention also provides a kind of devices that cracking of cases is assisted by vocal print, comprising:
Receiving module, the voice to be identified for collecting；
Parsing module, for parsing the voice to be identified, to generate corresponding vocal print；
Judgment module, for comparing the vocal print of the voice to be identified and the original vocal print in vocal print library, and really
The comparison result for the original vocal print that the fixed vocal print with the voice to be identified matches；
Determining module, the comparing result for being obtained according to matching, determines the corresponding criminal investigation object of the voice to be identified
Identity information；
Further include: module is established in vocal print library, for pre-establishing vocal print library, to multiple original vocal prints and with it is described original
The corresponding identification information of vocal print is stored.
Optionally, the vocal print library is established module and is specifically used for: when social insurance is added in user, acquiring the user's
Vocal print as the original vocal print, and adds corresponding identification information, establishes the vocal print library.
Optionally, the receiving module is specifically used for:
The voice of the preparatory collected criminal investigation object being stored into public security database；Or placed from each public place
Acquire the voice to be identified of equipment acquisition；Or the voice to be identified of the microphone acquisition from communicating terminal.
The present invention also provides a kind of equipment for assisting cracking of cases by vocal print, comprising:
Memory, for storing computer program；
Processor is realized when for executing the computer program and as described in any one of the above embodiments assists case by vocal print
The step of method of detection.
The present invention also provides a kind of computer readable storage mediums that cracking of cases is assisted by vocal print, and the computer can
It reads to be stored with computer program on storage medium, be realized as described in any of the above-described when the computer program is executed by processor
By vocal print assist cracking of cases method the step of.
The present invention provides a kind of method, apparatus, equipment and computer-readable storages that cracking of cases is assisted by vocal print
Medium generates corresponding vocal print, by the vocal print and vocal print of voice to be identified by receiving, parsing collected voice to be identified
Original vocal print in library compares, and obtains the comparison result of the original vocal print to match with the vocal print of voice to be identified, according to
Obtained comparing result is matched, determines the identity information of the corresponding criminal investigation object of voice to be identified.It is provided by the present invention to pass through
Vocal print assists the method and device of cracking of cases, can be acquired using telephone microphone, mobile phone, microphone etc., acquisition range is long-range
In the acquisition range of recognition of face in the prior art, the i.e. monitoring range of camera, also there is not the shadow of have no occluder before by face
It rings, therefore reduces acquisition difficulty, usage scenario is more extensive, while no longer needing the higher camera of great amount of cost, reduces
Cost.Further, due to use vocal print library so that the storage of voice print database, search it is more convenient, improve public security system
The operational efficiency of system.
Detailed description of the invention
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present invention or the prior art
Attached drawing needed in technical description is briefly described, it should be apparent that, the accompanying drawings in the following description is only this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of process of specific embodiment provided by the present invention that cracking of cases method is assisted by vocal print
Figure；
Fig. 2 is the process of another specific embodiment provided by the present invention that cracking of cases method is assisted by vocal print
Figure；
Fig. 3 is the process of another specific embodiment provided by the present invention that cracking of cases method is assisted by vocal print
Figure；
Fig. 4 is other a kind of streams of specific embodiment provided by the present invention that cracking of cases method is assisted by vocal print
Cheng Tu
Fig. 5 is the structural block diagram for assisting a kind of device of cracking of cases provided by the embodiment of the present invention by vocal print.
Specific embodiment
Core of the invention be to provide it is a kind of by vocal print assist cracking of cases method, apparatus, equipment and computer can
Storage medium is read, to solve the prior art with acquisition difficulty, the high problem of use cost during recognition of face.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiments are only a part of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
A kind of flow chart such as Fig. 1 of specific embodiment provided by the present invention that cracking of cases method is assisted by vocal print
It is shown, this method comprises:
Step S101: establishing vocal print library, the vocal print library be stored with multiple original vocal prints and with the original vocal print
The database of corresponding identification information；
It should be pointed out that this step not comparison vocal print the step of will doing every time, the only basis of below step,
In practice, public security system only needs to establish a vocal print library, and hereafter each vocal print comparison all transfers institute from vocal print library
The original vocal print needed.
After vocal print library is established, to satisfy the use demand, internal data need to be updated, the data in vocal print library update can be with
It is in real time, to be also possible to regularly, can be adjusted accordingly for different demands, for example, if corresponding storage crime is existing
The vocal print library of field voice evidence, needs evidence collection that can call in system after, demand is more urgent, can be set to reality
Shi Gengxin directly updates in vocal print library after that is, external typing；Or the population sound established in corresponding social insurance registration process
Line library, the demand called immediately after not collecting can choose regular (such as daily 24:00) and carry out data update, can be with
Internet resources are rationally utilized, system burden is mitigated.
Original vocal print can there are many, specific type can be described in detail below in association with specific embodiment.
Identification information corresponding with original vocal print can be understood as label, record this original vocal print collecting location,
The information such as acquisition time, acquisition target, corresponding docket, one of them original vocal print can correspond to multiple identification informations,
Can also an only corresponding identification information, in the same vocal print library, different original vocal prints can corresponding number, different types of mark believe
Breath.
Step S102: the voice to be identified collected；
Collected voice to be identified herein can be the voice for the acquisition equipment acquisition being arranged on each geographical location,
It can be to be collected the voice being stored in storage medium in advance.
Step S103: the parsing voice to be identified, to generate corresponding vocal print；
Before parsing voice to be identified, noise reduction process can be carried out to it, promote parsing accuracy, specific vocal print resolving
Please refer to the prior art, not reinflated detailed description in the application.
Step S104: the vocal print of the voice to be identified and the original vocal print in vocal print library are compared, and determine with
The comparison result for the original vocal print that the vocal print of the voice to be identified matches；
Difference as the case may be, herein can for multiple voices to be identified vocal print and an original vocal print successively into
Row comparison can also be compared with multiple original vocal prints in vocal print library for a voice to be identified, it is finally determining and it is described to
The comparison result for the original vocal print that the vocal print of identification voice matches.
Above-mentioned process by taking the original vocal print successful match in voice to be identified and vocal print library as an example, can only infer easily,
If step S104 not can determine that the voice to be identified to match with the original vocal print in vocal print library, it is aobvious that step S105 is changed to output
Show without matching object.
Step S105: the comparing result obtained according to matching determines the body of the corresponding criminal investigation object of the voice to be identified
Part information.
It should be pointed out that it is determined here that the method for the identity information of the corresponding criminal investigation object of voice to be identified is multiplicity
, three kinds of situations are enumerated below, respectively correspond three kinds of different identity information confirmation methods:
1. include the identity information of this vocal print owner in the correspondence identification information of the original vocal print in vocal print library: such as searching
When rope Missing Persons, original vocal print be Missing Persons' vocal print library in Missing Persons vocal print, and voice to be identified be then from
The voice acquired in the acquisition equipment that each department are placed, it is clear that the vocal print of above-mentioned Missing Persons is that it is recorded and is filed before missing
, such as in social insurance registration or when certificate examination registration, therefore the corresponding identification information of original vocal print in such cases
In there are corresponding identity information, then system is by will be after the speech analysis of the original vocal print of above-mentioned Missing Persons and each department acquisition
Obtained vocal print obtains the voice to match with original vocal print after successively comparing, system is by reading above-mentioned Missing Persons' at this time
The corresponding identification information of original vocal print, that is, can determine the identity information of Missing Persons.
2. voice to be identified is attached to identity information: when determining criminal such as from several suspects, the police criminal of possessing
The recording that guilty scene criminal leaves, while having several suspects, the identification vocal print of scene of a crime criminal recording at this time is original
Beginning vocal print, collected voice is voice to be identified from suspect, it is clear that raw tone does not include any body at this time
Part information, and every voice to be identified respectively corresponds the identity information of every suspect, then system is by by above-mentioned criminal
After vocal print after original vocal print and each suspect speech analysis to be identified successively compares, obtain matching with original vocal print
Voice, at this time system can determine the identity letter of criminal by reading the corresponding identity information of above-mentioned suspect's voice
Breath.
3. it is similar with situation 2, the difference is that suspect's voice does not include suspect's identity letter in input system
Breath, system cannot obtain related identification information after the determining suspect's voice to match with original vocal print at this time, can only
The unique corresponding label for exporting determining suspect's voice is determined by the label by personnel in charge of the case and is tired of such as voice serial number
People's identity information.The identity information of criminal investigation object can be before as identification information storage in vocal print library, be also possible to
It is stored in exterior.
The method provided by the invention that cracking of cases is assisted by vocal print, by receiving, parsing collected language to be identified
Sound generates corresponding vocal print, and the vocal print of voice to be identified and the original vocal print in vocal print library are compared, obtain with it is to be identified
The comparison result for the original vocal print that the vocal print of voice matches determines voice pair to be identified according to the comparing result that matching obtains
The identity information for the criminal investigation object answered.
The method and device provided by the present invention that cracking of cases is assisted by vocal print, uses telephone microphone, mobile phone, Mike
Wind etc. can acquire, and acquisition range is much larger than the acquisition range of recognition of face in the prior art, the i.e. monitoring range of camera,
There is not have no occluder to be influenced before by face, therefore reduce acquisition difficulty, usage scenario is more extensive, while no longer needing big
The camera for measuring higher cost, reduces costs.Further, due to using vocal print library, so that the storage of voice print database, looking into
It is more convenient to look for, and improves the operational efficiency of public security system.
Below by taking the lookup of Missing Persons as an example, to the reality provided by the present invention for assisting cracking of cases method by vocal print
The process of applying is described further.Assist the another kind of cracking of cases method specific by vocal print as Fig. 2 is provided by the present invention
Shown in the flow chart of embodiment, which includes:
Step S201: establishing Missing Persons' vocal print library, and Missing Persons' vocal print library is to be stored with multiple Missing Persons' originals
The database of beginning vocal print and identification information corresponding with the original vocal print of the Missing Persons；
The database of Missing Persons is established in advance, for example, can for from user when social insurance is added, adopt
The vocal print for collecting the user as the original vocal print, and adds corresponding identification information, establishes in the vocal print library, selects
The database of the vocal print composition of Missing Persons out.
Step S202: the voice to be identified collected；
Voice to be identified is different zones herein, the voice to be identified that the acquisition equipment of diverse geographic location acquires, every
Voice to be identified should be labeled with unique corresponding mark (such as device numbering) or the geographical location information of acquisition of acquisition equipment.
Specifically, collected voice is that each department acquire the collected voice to be identified of equipment herein, to realize to this
The large-range monitoring in area.
Step S203: the parsing voice to be identified, to generate corresponding vocal print；
Step S204: by the original vocal print of Missing Persons in the vocal print of the voice to be identified and Missing Persons' vocal print library into
Capable comparison, and determine the comparison result of the original vocal print of Missing Persons to match with the vocal print of the voice to be identified；
Step S205: the comparing result obtained according to matching determines that the corresponding criminal investigation object of the voice to be identified is
Missing Persons in this case；
The method of specific confirmation Missing Persons' identity information please refers to the explanation in first embodiment to step S105, this place
It repeats no more
Step S206: output acquires the geographical location information of the voice to be identified.
Specifically, the geography for collecting the acquisition equipment of the voice to be identified to match with Missing Persons' vocal print can be exported
Location information directly reads the information and obtains if having locality geographical location information in the corresponding mark of above-mentioned voice to be identified
Locality geographical location is obtained, to substantially determine the geographical location where Missing Persons, the next step of search and rescue is facilitated to be unfolded.
The present invention is after determining that vocal print matches, and further output acquires above-mentioned voice to be identified corresponding with original vocal print
Geographical location, realize and the position of specific objective positioned and tracked in a wide range of, technical solution of the present invention uses field
Scape is more, and business has intercommunity.Such as the present embodiment can also be used to deploying to ensure effective monitoring and control of illegal activities to suspect and its tracking of position, although
Use is different, but after procedural abstraction, will all be broadly divided into three links: obtaining various regions voice, target voice is found in identification, is exported
Obtain the position of target voice.The present embodiment is one such citing, and more application scenarios are in the application protection scope
It is interior.
Another specific embodiment provided by the present invention that cracking of cases method is assisted by vocal print referring to figure 3.
Flow chart, present embodiment determine that the process of criminal is with the voice left during detecing by skill according to scene of a crime
Example assists the implementation process of cracking of cases method to be described further, the process packet to provided by the present invention by vocal print
It includes:
Step S301: establishing material evidence vocal print library, and material evidence vocal print library is to be stored with multiple original sound of scene of a crime criminal
The database of line and identification information corresponding with the original vocal print of scene of a crime criminal；
Step S302: the suspect collected voice to be identified；
Specifically, suspect can be multiple herein, can also be one.
Step S303: parsing suspect voice to be identified, to generate corresponding vocal print；
Step S304: by the vocal print of suspect voice to be identified and violate the scene of a crime criminal original in material evidence vocal print library
Beginning vocal print compares, and the comparison of the determining suspect's vocal print to be identified to match with the original vocal print of scene of a crime criminal
As a result；
Step S305: the comparing result obtained according to matching determines the corresponding criminal investigation pair of suspect voice to be identified
Elephant is the criminal in this case.
The method of specific confirmation criminal's identity information please refers to the explanation in first embodiment to step S105, this place is no longer
It repeats.
In the present embodiment, the characteristic body that vocal print is different from as similar everyone of same fingerprint is played from suspect
The effect of the middle real criminal of determination.
Other a kind of specific embodiments provided by the present invention that cracking of cases method is assisted by vocal print referring to figure 4.
Flow chart, present embodiment is in public security system, for the Authority Verification of special object, to provided by the present invention
By vocal print assist cracking of cases method implementation process be described further, which includes
Step S401: establishing user's vocal print library, user's vocal print library be stored with the original vocal print of system user and with
The database of the corresponding identification information of the original vocal print of system user；
Step S402: the voice to be identified collected；
Voice that voice to be identified herein can be specified content, periodically converting is utilized to prevent criminal
Sound pick-up outfit records the case where authorized user's voice fraud system in advance.
Step S403: the parsing voice to be identified, to generate corresponding vocal print；
Step S404: the original vocal print of system user in the vocal print of the voice to be identified and user's vocal print library is carried out pair
Than, and the comparison result of the determining original vocal print of system user corresponding with the vocal print to be identified；
Uniquely voice to be identified in this step, system by the original vocal print of system user in user's vocal print library successively with
Voice to be identified compares.
Step S405: the comparing result obtained according to matching determines that the corresponding object of the voice to be identified is that this is
The authorized user of system.
Above-described embodiment is applied under line in actual scene, such as needs to confirm the field of visitor's identity at public security bureau's material evidence
Institute, by the way that visitor's voice (voice to be identified) and the original vocal print of system user in system user vocal print library are compared one by one,
To confirm visitor whether be system authorized user, further judge visitor whether there is or not access authority.
It can only think easily so that the corresponding object of voice to be identified belongs to the authorized user of this system as an example in above-mentioned steps
See, if step S404 not can determine that the original vocal print of system user corresponding with vocal print to be identified, it is aobvious that step S405 is changed to output
Showing that visitor is not is the authorized user of this system, and refuses to authorize access authority.
Above-described embodiment can also be used for the authentication in network system can also when user passes through network access data library
The confirmation to visiting subscriber's identity information is realized by the present embodiment.
Cracking of cases device is assisted to be introduced by vocal print to provided in an embodiment of the present invention below, it is described below logical
Crossing vocal print assists cracking of cases device to assist cracking of cases method that can correspond to each other reference by vocal print with above-described.
Fig. 5 is the structural block diagram provided in an embodiment of the present invention that cracking of cases device is assisted by vocal print, is passed through referring to Fig. 5
Vocal print assist cracking of cases device may include:
Module 100 is established in vocal print library, for pre-establishing vocal print library, to multiple original vocal prints and with the original vocal print
Corresponding identification information is stored；
Receiving module 200, the voice to be identified for collecting；
Parsing module 300, for parsing the voice to be identified, to generate corresponding vocal print；
Judgment module 400, for the vocal print of the voice to be identified and the original vocal print in vocal print library to be compared, and
The comparison result for the original vocal print that the determining vocal print with the voice to be identified matches；
Determining module 500, the comparing result for being obtained according to matching, determines the corresponding criminal investigation pair of the voice to be identified
The identity information of elephant.
It is provided by the present invention to assist to judge mould in cracking of cases device by vocal print as a kind of specific embodiment
Block 400 can be further used for:
When determining that the vocal print of current voice to be identified is not consistent with original vocal print, generation error prompt information,
Or it is not consistent in the vocal print of the current voice to be identified of judgement with original vocal print, and original vocal print is unique, language to be identified
When sound is not unique, automatically switches next voice to be identified and carry out voice print matching, until find with original vocal print match wait know
The vocal print of other voice；
Or be not consistent in the vocal print of the current voice to be identified of judgement with original vocal print, and original vocal print is not unique, it is to be identified
When voice is unique, automatically switches next original vocal print and carry out voice print matching, match until finding with the vocal print of voice to be identified
Original vocal print.
It is provided by the present invention to assist to determine mould in cracking of cases device by vocal print as a kind of specific embodiment
Block 500 can be further used for:
The identity information of criminal investigation object is obtained from the identification information of original vocal print,
Or the identity information of criminal investigation object is obtained from external system.
The present embodiment assists cracking of cases device to assist cracking of cases by vocal print for realizing above-mentioned by vocal print
Method, thus by vocal print assist cracking of cases device in specific embodiment it is visible hereinbefore case is assisted by vocal print
The embodiment part of detecting method, for example, module 100, receiving module 200, parsing module 300, judgment module are established in vocal print library
400, determining module 500 is respectively used to realize and assists step S101, S102, S103 in cracking of cases method above by vocal print,
S104 and S105 so, specific embodiment is referred to the description of corresponding various pieces embodiment, and details are not described herein.
The device provided by the present invention that cracking of cases is assisted by vocal print, passes through the voice to be identified collected；
The voice to be identified is parsed, to generate corresponding vocal print；By the original sound in the vocal print of the voice to be identified and vocal print library
Line compares, and determines the comparison result of the original vocal print to match with the vocal print of the voice to be identified, wherein the sound
Line library pre-establishes, is stored with multiple original vocal prints and the database of identification information corresponding with the original vocal print；
According to the comparing result that matching obtains, the identity information of the corresponding criminal investigation object of the voice to be identified is determined.The present invention is mentioned
What is supplied assists the device of cracking of cases by vocal print, instead of the identity for confirming criminal investigation object by recognition of face of the prior art
Acquisition criminal investigation subjects face image in the prior art is replaced with and obtains criminal investigation object voice to be identified by the technology of information, and
Voice to be identified using telephone microphone, mobile phone, microphone etc. acquisition equipment can acquire, and to above-mentioned each acquisition equipment and
Speech, the acquisition effective range of audio is significantly larger than the acquisition range of camera in recognition of face, and the acquisition of voice and face are schemed
The acquisition of picture is different, not will receive the influence of facial shelter, therefore acquisition difficulty is lower, acquisition is more convenient, and above-mentioned acquisition
The erection cost of equipment such as passes through suspicion manpower using existing equipment also much smaller than the camera in face recognition, or even also
Machine monitors suspect's message registration, therefore can substantially reduce cost using the device in the present invention, further, in the present invention
Device is due to using vocal print library, and vocal print has corresponding identification information in library, so that sorting out, lookup becomes more
It is convenient, greatly improve efficiency of public security system during criminal investigation.
The present invention also provides a kind of system, in the system, each component part, which can be shared out the work and helped one another, executes any of the above-described implementation
The method that cracking of cases is assisted by vocal print described in example.It can refer to the prior art with content, no longer be opened up herein
Open description.
Invention additionally provides a kind of computer readable storage medium, it is stored on the computer readable storage medium
Computer program, the computer program is realized when being executed by processor passes through sound described in any of the above-described inventive embodiments
The method of line assistance cracking of cases.Remaining content is referred to the prior art, no longer carries out expansion description herein.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part
Explanation.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The method, apparatus of cracking of cases, equipment and computer-readable are assisted by vocal print to provided by the present invention above
Storage medium is described in detail.Specific case used herein explains the principle of the present invention and embodiment
It states, the above description of the embodiment is only used to help understand the method for the present invention and its core ideas.It should be pointed out that for this skill
For the those of ordinary skill in art field, without departing from the principle of the present invention, several change can also be carried out to the present invention
Into and modification, these improvements and modifications also fall within the scope of protection of the claims of the present invention.
Claims (10)
1. a kind of method for assisting cracking of cases by vocal print characterized by comprising
The voice to be identified collected；
The voice to be identified is parsed, to generate corresponding vocal print；
The vocal print of the voice to be identified and the original vocal print in vocal print library are compared, and the determining and voice to be identified
The comparison result of original vocal print that matches of vocal print, wherein the vocal print library pre-establishes, is stored with multiple original sound
The database of line and identification information corresponding with the original vocal print；
According to the comparing result that matching obtains, the identity information of the corresponding criminal investigation object of the voice to be identified is determined.
2. the method as described in claim 1 for assisting cracking of cases by vocal print, which is characterized in that pre-establish the vocal print
Library includes:
When social insurance is added in user, the vocal print of the user is acquired, as the original vocal print, and adds corresponding mark
Information establishes the vocal print library.
3. the method as claimed in claim 2 for assisting cracking of cases by vocal print, which is characterized in that described to add corresponding mark
Knowing information includes:
Add the acquisition time of the original vocal print, collecting location, the user identity information and corresponding docket in
At least one of be used as described identification information.
4. passing through the method for vocal print assistance cracking of cases as described in claim 1, which is characterized in that described in the determination to
After the identity information for identifying the corresponding criminal investigation object of voice further include:
Output acquires the geographical location information of the voice to be identified.
5. the method according to any one of claims 1-4 for assisting cracking of cases by vocal print, which is characterized in that the reception
Collected voice to be identified includes:
Receive the voice of the collected criminal investigation object being stored into public security database in advance；
Or receive the voice to be identified for the acquisition equipment acquisition placed from each public place；
Or receive the voice to be identified of the microphone acquisition from communicating terminal.
6. a kind of device for assisting cracking of cases by vocal print characterized by comprising
Receiving module, the voice to be identified for collecting；
Parsing module, for parsing the voice to be identified, to generate corresponding vocal print；
Judgment module, for the vocal print of the voice to be identified and the original vocal print in vocal print library to be compared, and determine with
The comparison result for the original vocal print that the vocal print of the voice to be identified matches；
Determining module, the comparing result for being obtained according to matching, determines the body of the corresponding criminal investigation object of the voice to be identified
Part information；
Further include: module is established in vocal print library, for pre-establishing vocal print library, to multiple original vocal prints and with the original vocal print
Corresponding identification information is stored.
7. the device as claimed in claim 6 for assisting cracking of cases by vocal print, which is characterized in that mould is established in the vocal print library
Block is specifically used for: when social insurance is added in user, acquiring the vocal print of the user, as the original vocal print, and adds pair
The identification information answered establishes the vocal print library.
8. the device for assisting cracking of cases by vocal print as claimed in claims 6 or 7, which is characterized in that the receiving module
It is specifically used for:
The voice of the preparatory collected criminal investigation object being stored into public security database；Or the acquisition placed from each public place
The voice to be identified of equipment acquisition；Or the voice to be identified of the microphone acquisition from communicating terminal.
9. a kind of equipment for assisting cracking of cases by vocal print characterized by comprising
Memory, for storing computer program；
Processor is realized when for executing the computer program and is assisted as described in any one of claim 1 to 5 by vocal print
The step of method of cracking of cases.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program is realized when the computer program is executed by processor and assists case by vocal print as described in any one of claim 1 to 5
The step of method of part detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810892417.1A CN109036434A (en) | 2018-08-07 | 2018-08-07 | A kind of method, device and equipment for assisting cracking of cases by vocal print |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810892417.1A CN109036434A (en) | 2018-08-07 | 2018-08-07 | A kind of method, device and equipment for assisting cracking of cases by vocal print |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109036434A true CN109036434A (en) | 2018-12-18 |
Family
ID=64649978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810892417.1A Pending CN109036434A (en) | 2018-08-07 | 2018-08-07 | A kind of method, device and equipment for assisting cracking of cases by vocal print |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109036434A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110010134A (en) * | 2019-04-17 | 2019-07-12 | 伍劲松 | A kind of security system based on speech recognition |
| CN110795771A (en) * | 2019-10-08 | 2020-02-14 | 支付宝(杭州)信息技术有限公司 | Information processing and verifying method, device and system based on block chain |
| CN110933100A (en) * | 2019-12-06 | 2020-03-27 | 广州国音智能科技有限公司 | Authority verification method, system and computer readable storage medium |
| CN110970035A (en) * | 2019-12-06 | 2020-04-07 | 广州国音智能科技有限公司 | Single-machine voice recognition method, device and computer readable storage medium |
| CN111597362A (en) * | 2020-05-19 | 2020-08-28 | 深圳蝙蝠声学科技有限公司 | Target searching system, method and storage medium based on movable identity recognition |
| CN112684999A (en) * | 2020-12-23 | 2021-04-20 | 中国人民解放军战略支援部队信息工程大学 | Follow-reading mode voice acquisition method, system, equipment and storage medium |
| CN112802482A (en) * | 2021-04-15 | 2021-05-14 | 北京远鉴信息技术有限公司 | Voiceprint serial-parallel identification method, individual soldier system and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5608784A (en) * | 1994-01-24 | 1997-03-04 | Miller; Joel F. | Method of personnel verification using voice recognition |
| US6089284A (en) * | 1998-09-24 | 2000-07-18 | Marconi Commerce Systems Inc. | Preconditioning a fuel dispensing system using a transponder |
| US6445775B1 (en) * | 1996-06-28 | 2002-09-03 | Distributed Software Development, Inc. | Computer-based system and method for identifying an unidentified caller |
| CN103337100A (en) * | 2013-06-20 | 2013-10-02 | 汉王科技股份有限公司 | Biological characteristic attendance checking method and mobile equipment |
| CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
| CN103915096A (en) * | 2014-04-15 | 2014-07-09 | 胡上杰 | Police service voiceprint recognition method |
| CN105244031A (en) * | 2015-10-26 | 2016-01-13 | 北京锐安科技有限公司 | Speaker identification method and device |
| CN105512535A (en) * | 2016-01-08 | 2016-04-20 | 广东德生科技股份有限公司 | User authentication method and user authentication device |
| CN106297806A (en) * | 2016-08-22 | 2017-01-04 | 安徽工程大学机电学院 | Intelligent stereomicrophone system based on vocal print |
| CN106384478A (en) * | 2016-11-30 | 2017-02-08 | 南京小脚印网络科技有限公司 | Voiceprint identification device and method using the same to protect children |
| CN108347512A (en) * | 2018-01-22 | 2018-07-31 | 维沃移动通信有限公司 | A kind of personal identification method and mobile terminal |
-
2018
- 2018-08-07 CN CN201810892417.1A patent/CN109036434A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5608784A (en) * | 1994-01-24 | 1997-03-04 | Miller; Joel F. | Method of personnel verification using voice recognition |
| US6445775B1 (en) * | 1996-06-28 | 2002-09-03 | Distributed Software Development, Inc. | Computer-based system and method for identifying an unidentified caller |
| US6089284A (en) * | 1998-09-24 | 2000-07-18 | Marconi Commerce Systems Inc. | Preconditioning a fuel dispensing system using a transponder |
| CN103337100A (en) * | 2013-06-20 | 2013-10-02 | 汉王科技股份有限公司 | Biological characteristic attendance checking method and mobile equipment |
| CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
| CN103915096A (en) * | 2014-04-15 | 2014-07-09 | 胡上杰 | Police service voiceprint recognition method |
| CN105244031A (en) * | 2015-10-26 | 2016-01-13 | 北京锐安科技有限公司 | Speaker identification method and device |
| CN105512535A (en) * | 2016-01-08 | 2016-04-20 | 广东德生科技股份有限公司 | User authentication method and user authentication device |
| CN106297806A (en) * | 2016-08-22 | 2017-01-04 | 安徽工程大学机电学院 | Intelligent stereomicrophone system based on vocal print |
| CN106384478A (en) * | 2016-11-30 | 2017-02-08 | 南京小脚印网络科技有限公司 | Voiceprint identification device and method using the same to protect children |
| CN108347512A (en) * | 2018-01-22 | 2018-07-31 | 维沃移动通信有限公司 | A kind of personal identification method and mobile terminal |
Non-Patent Citations (1)
| Title |
|---|
| 邱林 等著: "《滦河下游水库群联合调度研究》", 31 May 2009, 郑州：黄河水利出版社 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110010134A (en) * | 2019-04-17 | 2019-07-12 | 伍劲松 | A kind of security system based on speech recognition |
| CN110795771A (en) * | 2019-10-08 | 2020-02-14 | 支付宝(杭州)信息技术有限公司 | Information processing and verifying method, device and system based on block chain |
| CN110933100A (en) * | 2019-12-06 | 2020-03-27 | 广州国音智能科技有限公司 | Authority verification method, system and computer readable storage medium |
| CN110970035A (en) * | 2019-12-06 | 2020-04-07 | 广州国音智能科技有限公司 | Single-machine voice recognition method, device and computer readable storage medium |
| CN111597362A (en) * | 2020-05-19 | 2020-08-28 | 深圳蝙蝠声学科技有限公司 | Target searching system, method and storage medium based on movable identity recognition |
| CN112684999A (en) * | 2020-12-23 | 2021-04-20 | 中国人民解放军战略支援部队信息工程大学 | Follow-reading mode voice acquisition method, system, equipment and storage medium |
| CN112802482A (en) * | 2021-04-15 | 2021-05-14 | 北京远鉴信息技术有限公司 | Voiceprint serial-parallel identification method, individual soldier system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109036434A (en) | A kind of method, device and equipment for assisting cracking of cases by vocal print | |
| US9064160B2 (en) | Meeting room participant recogniser | |
| CN109214276A (en) | A kind of system and method for the target person track following based on face recognition technology | |
| CN108038948A (en) | Verification method and device, the computer-readable recording medium of passenger identity | |
| CN105185121B (en) | A kind of method of virtual bayonet socket parallelism recognition car plate | |
| CN108446681B (en) | Pedestrian analysis method, device, terminal and storage medium | |
| CN110516672A (en) | Card card information identifying method, device and terminal | |
| CN110555918A (en) | Attendance management method and attendance management equipment | |
| CN108540757B (en) | Monitoring system and monitoring method | |
| WO2022216020A1 (en) | Image/audio acquisition or editing apparatus for generating original image/audio file or deepfake-modulated file including metadata associated with generation history of image/audio, hash bank server for receiving and storing hash value related to original image/audio file or deepfake-modulated file, and server and method for receiving and processing original image/audio file or deepfake-modulated file | |
| CN111277788A (en) | Monitoring method and monitoring system based on MAC address | |
| CN110033532A (en) | A kind of unmanned foreground visitor's concierge system | |
| CN108694246A (en) | A kind of mask method and system of video-with-audio recording instrument record file | |
| CN110460886A (en) | A kind of method and system of the real-time cochain of video data | |
| CN112509586A (en) | Method and device for recognizing voice print of telephone channel | |
| CN109859426A (en) | A kind of community security protection management system | |
| CN111915755A (en) | Rapid classroom attendance checking method and system based on artificial intelligence image prediction | |
| CN114333005A (en) | Object recognition method, system and storage medium | |
| CN208384625U (en) | Car networking system based on police service scene | |
| CN101524277A (en) | Biological type identity-acquiring recognizer and application method thereof | |
| CN109167749A (en) | A kind of identity identifying method and device | |
| CN110969738A (en) | Control system and method of intelligent security entrance guard based on 5G architecture | |
| CN113450117A (en) | Face recognition method, device, equipment and medium | |
| CN112019337A (en) | Method, device and equipment for processing emergency based on block chain | |
| CN109117765A (en) | Video investigation device and method |
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: 20181218 |