CN108650266A - Server, the method for voice print verification and storage medium - Google Patents
Server, the method for voice print verification and storage medium Download PDFInfo
- Publication number
- CN108650266A CN108650266A CN201810457267.1A CN201810457267A CN108650266A CN 108650266 A CN108650266 A CN 108650266A CN 201810457267 A CN201810457267 A CN 201810457267A CN 108650266 A CN108650266 A CN 108650266A
- Authority
- CN
- China
- Prior art keywords
- voice
- vocal print
- graphic code
- secret key
- verification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012795 verification Methods 0.000 title claims abstract description 151
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000001755 vocal effect Effects 0.000 claims abstract description 183
- 239000013598 vector Substances 0.000 claims abstract description 129
- 238000004458 analytical method Methods 0.000 claims description 46
- 238000012545 processing Methods 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 21
- 238000001228 spectrum Methods 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 238000009432 framing Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 2
- 238000012549 training Methods 0.000 description 14
- 239000000203 mixture Substances 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 241000638935 Senecio crassissimus Species 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- 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
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0807—Network architectures or network communication protocols for network security for authentication of entities using tickets, e.g. Kerberos
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/083—Network architectures or network communication protocols for network security for authentication of entities using passwords
- H04L63/0838—Network architectures or network communication protocols for network security for authentication of entities using passwords using one-time-passwords
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0876—Network architectures or network communication protocols for network security for authentication of entities based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Telephonic Communication Services (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of server, the method for voice print verification and storage medium, this method to include：After receiving authentication request, the graphic code parameter of graphic code corresponding with the User Identity is generated, and is sent to the client computer；After handheld terminal parses graphic code, receives handheld terminal and asked by the voice print verification for carrying random secret key that voice print database acquisition link address is sent, and whether analyze two random secret keys consistent；If so, establishing the data under voice channel with the handheld terminal, and the current voice print verification voice data of the user acquired from the handheld terminal is obtained based on the channel；Corresponding current vocal print discriminant vectors are built, the corresponding standard vocal print discriminant vectors of the User Identity is determined, calculates the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, the distance based on calculating generates authentication result.The present invention can improve the flexibility of voice print verification, avoid the occurrence of sound abduction.
Description
Technical field
The present invention relates to a kind of field of communication technology more particularly to server, the method for voice print verification and storage mediums.
Background technology
Currently, using voice print verification technology realize user identity verification have become each large power consumers company (for example,
Bank, insurance company, game company etc.) important verification means.Traditional realizes that user identity is tested using voice print verification technology
The operational program of card is：Using the interface of voice print verification server, corresponding client-side program exploitation is individually carried out, exploitation is passed through
Client-side program the voice of user is acquired and pre-processing, the voice print database after pre-processing is then transmitted to vocal print
Authentication server carries out authentication verification and operation processing for voice print verification server to being transmitted through the voice print database come.
However, the defect of this traditional voice print verification scheme is：User needs to pass through developed client-side program
The voice of user is acquired, in practical operation, using flexible is low, is easy by artificial sound intervention, and uses client meter
It is easy to be kidnapped by sound when calculation machine acquires sound, the authenticity of voice print verification can not accurately be controlled, safety obtains
Less than guarantee.
Invention content
The purpose of the present invention is to provide a kind of server, the method for voice print verification and storage mediums, it is intended to improve vocal print
The flexibility of verification avoids the occurrence of sound abduction.
To achieve the above object, the present invention provides a kind of server, the server include memory and with the storage
The processor of device connection, is stored with the processing system that can be run on the processor, the processing system in the memory
Following steps are realized when being executed by the processor：
Generation step, after receiving the authentication request of carrying User Identity of client computer transmission,
The graphic code parameter of graphic code corresponding with the User Identity is generated, and the graphic code parameter is sent to the client meter
Calculation machine generates for the client computer and shows that graphic code corresponding with the graphic code parameter, the graphic code parameter include
Random secret key and voice print database acquisition link address；
Analytical procedure connects after handheld terminal parsing graphic code obtains random secret key and voice print database acquisition link address
It receives handheld terminal to ask by the voice print verification for carrying random secret key that voice print database acquisition link address is sent, and analyzes hair
Whether give random secret key in the graphic code parameter of the client computer consistent with the random secret key that is received from handheld terminal；
Obtaining step if so, establishing the data under voice channel with the handheld terminal, and is adopted based on the voice data
Collection channel obtains the current voice print verification voice data of the user acquired from the handheld terminal；
Verification step builds the corresponding current vocal print discriminant vectors of the current voice print verification voice data, according to scheduled
The mapping relations of User Identity and standard vocal print discriminant vectors determine that the corresponding standard vocal print of the User Identity differentiates
Vector calculates the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, and the distance based on calculating generates identity
Verification result, and the authentication result is sent to the client computer.
Preferably, the analytical procedure, specifically includes：
The server receives handheld terminal and carries random secret key by what voice print database acquisition link address was sent
Voice print verification is asked, and whether the number that analysis receives the random secret key is more than preset times；
If being less than or equal to the preset times, analysis is sent to random secret in the graphic code parameter of the client computer
Whether key and the random secret key received from handheld terminal are consistent.
Preferably, the graphic code parameter further includes the effective time of graphic code, and the analytical procedure specifically includes：
The server receives handheld terminal and carries random secret key by what voice print database acquisition link address was sent
Voice print verification is asked, and whether the time that analysis receives the random secret key is within the scope of the effective time of the graphic code；
If within the scope of the effective time in the graphic code, whether the number that analysis receives the random secret key is more than in advance
If number；
If being less than or equal to the preset times, analysis is sent to random secret in the graphic code parameter of the client computer
Whether key and the random secret key received from handheld terminal are consistent.
Preferably, the step of described structure current voice print verification voice data corresponding current vocal print discriminant vectors, tool
Body includes：
Current voice print verification voice data is handled, to extract preset kind vocal print feature, and based on the default class
Type vocal print feature builds corresponding vocal print feature vector；
In the background channel model that vocal print feature vector input is trained in advance, to build the current voice print verification voice
The corresponding current vocal print discriminant vectors of data；
It is described to calculate the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, the distance life based on calculating
Include at the step of authentication result：
Calculate the COS distance between the current vocal print discriminant vectors and standard vocal print discriminant vectors： For the standard vocal print discriminant vectors,For current vocal print discriminant vectors；
If the COS distance is less than or equal to preset distance threshold, the information being verified is generated；
If the COS distance be more than preset distance threshold, generate verification not by information.
To achieve the above object, the present invention also provides a kind of method of voice print verification, the method for the voice print verification includes：
S1, after receiving the authentication request of carrying User Identity of client computer transmission, server
The graphic code parameter of graphic code corresponding with the User Identity is generated, and the graphic code parameter is sent to the client meter
Calculation machine generates for the client computer and shows that graphic code corresponding with the graphic code parameter, the graphic code parameter include
Random secret key and voice print database acquisition link address；
S2, after handheld terminal parsing graphic code obtains random secret key and voice print database acquisition link address, the service
Device receives handheld terminal and is asked by the voice print verification for carrying random secret key that voice print database acquisition link address is sent, and point
Whether analyse the random secret key that is sent in the graphic code parameter of the client computer and the random secret key received from handheld terminal
Unanimously；
S3 if so, the server establishes the data under voice channel with the handheld terminal, and is based on the voice number
The current voice print verification voice data of the user acquired from the handheld terminal is obtained according to acquisition channel；
S4 builds the corresponding current vocal print discriminant vectors of the current voice print verification voice data, according to scheduled user's body
The mapping relations of part mark and standard vocal print discriminant vectors, determine the corresponding standard vocal print discriminant vectors of the User Identity,
The distance between current vocal print discriminant vectors and standard vocal print discriminant vectors are calculated, the distance based on calculating generates authentication knot
Fruit, and the authentication result is sent to the client computer.
Preferably, the step S2, specifically includes：
The server receives handheld terminal and carries random secret key by what voice print database acquisition link address was sent
Voice print verification is asked, and whether the number that analysis receives the random secret key is more than preset times；
If being less than or equal to the preset times, analysis is sent to random secret in the graphic code parameter of the client computer
Whether key and the random secret key received from handheld terminal are consistent.
Preferably, the graphic code parameter further includes the effective time of graphic code, and the step S2 is specifically included：
The server receives handheld terminal and carries random secret key by what voice print database acquisition link address was sent
Voice print verification is asked, and whether the time that analysis receives the random secret key is within the scope of the effective time of the graphic code；
If within the scope of the effective time in the graphic code, whether the number that analysis receives the random secret key is more than in advance
If number；
If being less than or equal to the preset times, analysis is sent to random secret in the graphic code parameter of the client computer
Whether key and the random secret key received from handheld terminal are consistent.
Preferably, the step of described structure current voice print verification voice data corresponding current vocal print discriminant vectors, tool
Body includes：
Current voice print verification voice data is handled, to extract preset kind vocal print feature, and based on the default class
Type vocal print feature builds corresponding vocal print feature vector；
In the background channel model that vocal print feature vector input is trained in advance, to build the current voice print verification voice
The corresponding current vocal print discriminant vectors of data；
It is described to calculate the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, the distance life based on calculating
Include at the step of authentication result：
Calculate the COS distance between the current vocal print discriminant vectors and standard vocal print discriminant vectors： For the standard vocal print discriminant vectors,For current vocal print discriminant vectors；
If the COS distance is less than or equal to preset distance threshold, the information being verified is generated；
If the COS distance be more than preset distance threshold, generate verification not by information.
Preferably, described that current voice print verification voice data is handled, to extract preset kind vocal print feature, and base
The step of corresponding vocal print feature vector is built in the preset kind vocal print feature, is specifically included：
Preemphasis, framing and windowing process are carried out to the current voice print verification voice data, each adding window is carried out
Fourier transform obtains corresponding frequency spectrum, and the frequency spectrum is inputted Meier filter to export to obtain Meier frequency spectrum；
Cepstral analysis is carried out on Meier frequency spectrum to obtain mel-frequency cepstrum coefficient MFCC, is fallen based on the mel-frequency
Spectral coefficient MFCC forms corresponding vocal print feature vector.
The present invention also provides a kind of computer readable storage medium, processing is stored on the computer readable storage medium
The step of system, the processing system realizes the method for above-mentioned voice print verification when being executed by processor.
The beneficial effects of the invention are as follows：The present invention uses client computer, server and hand when carrying out voice print verification
The framework of terminal composition is held, client computer carries User Identity and made requests on to server, and server is generated and used
Identity corresponding graphic code parameter in family is simultaneously sent to client computer, and the corresponding figure of display graphic code parameter is carried out for it
Shape code, user are tested by chained address transmission random code to server using after the handheld terminal scanning figure shape code of carrying
Card, channel can be established with server by being verified, and obtain the voice data of the user of handheld terminal acquisition, carry out vocal print
Verification, the present invention do not need the voice data of developed client-side program acquisition user, and carrying out vocal print using handheld terminal tests
Card flexibility is high and is not easy to be disturbed, and binds server and client computer using User Identity, recycles random
Code again binds client computer, server and handheld terminal, avoids the occurrence of the case where sound is kidnapped, and improves vocal print and tests
The authenticity of card and safety.
Description of the drawings
Fig. 1 is each one optional application environment schematic diagram of embodiment of the present invention；
Fig. 2 is the flow diagram of one embodiment of method of voice print verification of the present invention.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
The every other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannot
It is interpreted as indicating or implying its relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claims
Protection domain within.
As shown in fig.1, being the application environment schematic diagram of the preferred embodiment of the method for voice print verification of the present invention.The application
Environment schematic includes 1, client computer 2 and handheld terminal 3 on server.1 can be led to by network, near field on server
The suitable technology such as letter technology carries out data interaction with client computer 2 and handheld terminal 3.
The client computer 2 include, but are not limited to any type can with user by keyboard, mouse, remote controler,
The modes such as touch tablet or voice-operated device carry out the electronic product of human-computer interaction, for example, personal computer, tablet computer, intelligence
Mobile phone, personal digital assistant (Personal Digital Assistant, PDA), game machine, Interactive Internet TV
The removable of (Internet Protocol Television, IPTV), intellectual Wearable, navigation device etc. sets
It is standby, or such as number TV, desktop computer, notebook, server etc. fixed terminal.The handheld terminal 3 can be
Tablet computer, smart mobile phone etc..
On the server 1 be it is a kind of can according to the instruction for being previously set or storing, it is automatic carry out numerical computations and/
Or the equipment of information processing.On the server 1 can be single network server, multiple network servers composition server
The group either cloud being made of a large amount of hosts or network server based on cloud computing, wherein cloud computing is the one of Distributed Calculation
Kind, a super virtual computer being made of the computer collection of a group loose couplings.
In the present embodiment, it 1 may include on server, but be not limited only to, connection can be in communication with each other by system bus
Memory 11, processor 12, network interface 13, memory 11 are stored with the processing system that can be run on the processor 12.It needs
, it is noted that Fig. 1 is illustrated only 1 on the server with component 11-13, it should be understood that being not required for implementing all
The component shown, the implementation that can be substituted is more or less component.
Wherein, memory 11 includes memory and the readable storage medium storing program for executing of at least one type.Inside save as on server 1 fortune
Row provides caching；Readable storage medium storing program for executing can be if flash memory, hard disk, multimedia card, card-type memory are (for example, SD or DX memories
Deng), random access storage device (RAM), static random-access memory (SRAM), read-only memory (ROM), electric erasable can compile
Journey read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, disk, CD etc. it is non-volatile
Storage medium.In some embodiments, readable storage medium storing program for executing can be on server 1 internal storage unit, such as the service
1 hard disk on device；In further embodiments, which can also be that on server 1 external storage is set
It is standby, for example, 1 on server on the plug-in type hard disk that is equipped with, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) blocks, flash card (Flash Card) etc..In the present embodiment, the readable storage medium storing program for executing of memory 11
It is installed in 1 operating system and types of applications software on server, such as storage one embodiment of the invention commonly used in storage
Processing system program code etc..It has exported or will export in addition, memory 11 can be also used for temporarily storing
Various types of data.
The processor 12 can be in some embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 12 is commonly used in the control clothes
1 overall operation on business device, such as execute and carry out data interaction with the client computer 2, handheld terminal 3 or communicate phase
Control and processing of pass etc..In the present embodiment, the processor 12 is for running the program code stored in the memory 11
Or processing data, such as operation processing system etc..
The network interface 13 may include radio network interface or wired network interface, which is commonly used in
Communication connection is established on the server between 1 and other electronic equipments.In the present embodiment, network interface 13 is mainly used for take
1 is connected with client computer 2, handheld terminal 3 on business device, on the server between 1 and client computer 2, handheld terminal 3
Establish data transmission channel and communication connection.
The processing system is stored in memory 11, including it is at least one be stored in it is computer-readable in memory 11
Instruction, at least one computer-readable instruction can be executed by processor device 12, the method to realize each embodiment of the application；With
And the function that at least one computer-readable instruction is realized according to its each section is different, can be divided into different logic moulds
Block.
In one embodiment, following steps are realized when above-mentioned processing system is executed by the processor 12：
Generation step, after receiving the authentication request of carrying User Identity of client computer transmission,
The graphic code parameter of graphic code corresponding with the User Identity is generated, and the graphic code parameter is sent to the client meter
Calculation machine generates for the client computer and shows graphic code corresponding with the graphic code parameter；
Wherein, User Identity is the mark of the identity for unique mark user, it is preferable that User Identity is
Identification card number.Graphic code is preferably Quick Response Code, however, not limited to this, such as can also be bar code.Graphic code parameter is used for
Corresponding graphic code is generated, such as Quick Response Code parameter generates corresponding Quick Response Code, bar code parameters generate corresponding bar code.Figure
Shape code parameter includes random secret key and voice print database acquisition link address, can also further comprise effective time, the figure of graphic code
The details of shape code, scene value ID of graphic code etc., random secret key can be random number word string or random string etc..
The authentication request for the carrying User Identity that client computer is sent to server, server receive
After the authentication request, generate corresponding with User Identity random secret key, the server voice print database acquisition link
It is grounded location and the effective time of graphic code, the details of graphic code, the graphic codes parameter such as scene value ID of graphic code, by this
Graphic code parameter is sent to the client computer, after client computer receives graphic code parameter, according to graphic code parameter
Corresponding graphic code is generated, and is shown, is scanned for handheld terminal.
Analytical procedure connects after handheld terminal parsing graphic code obtains random secret key and voice print database acquisition link address
It receives handheld terminal to ask by the voice print verification for carrying random secret key that voice print database acquisition link address is sent, and analyzes hair
Whether give random secret key in the graphic code parameter of the client computer consistent with the random secret key that is received from handheld terminal；
Handheld terminal carries out graphic code using the function module for parsing graphic code of itself after scanning figure shape code
Parsing obtains corresponding random secret key, the effective time of the voice print database acquisition link address of the server and graphic code, figure
Graphic codes parameter, the handheld terminals such as the details of shape code, the scene value ID of graphic code pass through voice print database acquisition link address
The voice print verification that transmission carries random secret key is asked into server.
After server receives voice print verification request, analysis is sent in the graphic code parameter of the client computer
Whether random secret key and the random secret key received from handheld terminal are consistent, other handheld terminals usurp the random of this in order to prevent
Voice print verification is carried out with server after secret key, improves the accuracy of voice print verification, in one embodiment, server receives hand-held whole
The voice print verification request for carrying random secret key that end is sent by voice print database acquisition link address, first analysis receive this
Whether the number of random secret key is more than preset times；If the number for receiving the random secret key is more than preset times, it is greater than 1
Secondary, then the server refusal respond voice print verification is asked, and can the relevant information of the handheld terminal be sent to server, for clothes
The reference frame whether business device is subsequently spoofed as voice print verification, if being less than or equal to the preset times, for example, 1 time, then again
Execute the random secret key that is sent in the graphic code parameter of the client computer of analysis with received from handheld terminal it is random secret
The whether consistent operation of key.
Other handheld terminals are usurped and carry out voice print verification with server after this random secret key in order to prevent, further carry
The accuracy of high voice print verification, in another embodiment, server receive handheld terminal and pass through voice print database acquisition link address
Whether the time that the voice print verification request for carrying random secret key sent, first analysis receive the random secret key is in the figure
Within the scope of the effective time of shape code, such as the effective time of the graphic code is 2018.03.01-2018.03.10, and server receives
The time of the random secret key of handheld terminal is 2018.03.08, then is within the scope of the effective time of the graphic code.If in should
Within the scope of the effective time of graphic code, then the number for receiving the random secret key is analyzed again whether more than preset times, for example, point
Whether the number that analysis receives the random secret key is more than 1 time；If the number for receiving the random secret key is more than preset times, take
Device refusal respond of being engaged in voice print verification request, and the relevant information of the handheld terminal can be sent to server, after server
The continuous reference frame whether being spoofed as voice print verification.It is last to execute analysis transmission again if being less than or equal to the preset times
It is whether consistent to the random secret key in the graphic code parameter of the client computer and the random secret key from handheld terminal reception
Operation.
Obtaining step if so, establishing the data under voice channel with the handheld terminal, and is adopted based on the voice data
Collection channel obtains the current voice print verification voice data of the user acquired from the handheld terminal；
If the random secret key being sent in the graphic code parameter of the client computer and received from handheld terminal with
Machine secret key is consistent, then establishes the data under voice channel with the handheld terminal.Handheld terminal passes through the voice collectings such as microphone
Equipment collects the current voice print verification voice data of user in real time.When acquiring current voice print verification voice data, should use up
Amount prevents the interference of ambient noise and handheld terminal.Handheld terminal keeps suitable distance with user, and does not have to be distorted big as possible
Handheld terminal, it is preferable to use alternating currents for power supply, and electric current is kept to stablize；Sensor should be used when being recorded.In framing and adopt
Before sample, noise treatment can be carried out to current voice print verification voice data, to be further reduced interference.In order to extract
The vocal print feature of current voice print verification voice data is obtained, the current voice print verification voice data acquired is preset data length
Voice data, or be the voice data more than preset data length.
Verification step builds the corresponding current vocal print discriminant vectors of the current voice print verification voice data, according to scheduled
The mapping relations of User Identity and standard vocal print discriminant vectors determine that the corresponding standard vocal print of the User Identity differentiates
Vector calculates the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, and the distance based on calculating generates identity
Verification result, and the authentication result is sent to the client computer.
In order to effectively reduce the calculation amount of Application on Voiceprint Recognition, the speed of Application on Voiceprint Recognition is improved, in one embodiment, above-mentioned structure
It the step of current voice print verification voice data corresponding current vocal print discriminant vectors, specifically includes：To current voice print verification language
Sound data are handled, and to extract preset kind vocal print feature, and build corresponding vocal print based on the preset kind vocal print feature
Feature vector；In the background channel model that vocal print feature vector input is trained in advance, to build the current voice print verification language
The corresponding current vocal print discriminant vectors of sound data.
Wherein, vocal print feature includes multiple types, such as broadband vocal print, narrowband vocal print, amplitude vocal print etc., and the present embodiment is pre-
If type vocal print feature is preferably mel-frequency cepstrum coefficient (the Mel Frequency of current voice print verification voice data
Cepstrum Coefficient, MFCC), Predetermined filter is Meier filter.When building corresponding vocal print feature vector,
By the vocal print feature composition characteristic data matrix of current voice print verification voice data, this feature data matrix is corresponding vocal print
Feature vector.
Specifically, preemphasis and windowing process are carried out to current voice print verification voice data, Fu is carried out to each adding window
Vertical leaf transformation obtains corresponding frequency spectrum, and the frequency spectrum is inputted Meier filter to export to obtain Meier frequency spectrum；In Meier frequency spectrum
Upper progress cepstral analysis is corresponded to obtaining mel-frequency cepstrum coefficient MFCC based on mel-frequency cepstrum coefficient MFCC compositions
Vocal print feature vector.
Wherein, preemphasis processing is really high-pass filtering processing, filters out low-frequency data so that current voice print verification voice number
High frequency characteristics in more highlights, and specifically, the transmission function of high-pass filtering is：H (Z)=1- α Z-1, wherein Z is voice number
According to α is constant factor, it is preferable that the value of α is 0.97；Since voice data deviates from original to a certain extent after framing
Beginning voice, therefore, it is necessary to carry out windowing process to voice data.On Meier frequency spectrum carry out cepstral analysis be, for example, take logarithm,
Inverse transformation is done, inverse transformation is realized generally by DCT discrete cosine transforms, takes the 2nd after DCT to the 13rd coefficient conduct
Mel-frequency cepstrum coefficient MFCC.Mel-frequency cepstrum coefficient MFCC is the vocal print feature of this frame voice data, by every frame
Mel-frequency cepstrum coefficient MFCC composition characteristic data matrixes, this feature data matrix is the vocal print feature of speech sample data
Vector.
The present embodiment takes the mel-frequency cepstrum coefficient MFCC of voice data to form corresponding vocal print feature vector, due to it
Than the frequency band for the linear interval in normal cepstrum more can subhuman auditory system, therefore body can be improved
The accuracy of part verification.
Then, it by above-mentioned vocal print feature vector input background channel model trained in advance, is tested with constructing current vocal print
The corresponding current vocal print discriminant vectors of voice data are demonstrate,proved, for example, calculating current sound using background channel model trained in advance
The corresponding eigenmatrix of line validating speech data, with determine the corresponding current vocal print of current voice print verification voice data differentiate to
Amount.
For high efficiency, the corresponding current vocal print discriminant vectors of current voice print verification voice data are constructed in high quality,
In a preferred embodiment, which is one group of gauss hybrid models, the training process of the background channel model
Include the following steps：1. obtaining the voice data sample of preset quantity, the voice data sample of each preset quantity is corresponding with mark
Accurate vocal print discriminant vectors；It is corresponded to 2. being handled respectively each voice data sample with extracting each voice data sample
Preset kind vocal print feature, and each voice number is built based on the corresponding preset kind vocal print feature of each voice data sample
According to the corresponding vocal print feature vector of sample；3. all preset kind vocal print feature vectors extracted are divided into the first percentage
The verification collection of training set and the second percentage, the sum of first percentage and the second percentage are less than or equal to 100%；4.
This group of gauss hybrid models are trained using the preset kind vocal print feature vector in training set, and the profit after the completion of training
It is verified with the accuracy rate of this group of gauss hybrid models after verification set pair training；If accuracy rate be more than predetermined threshold value (for example,
98.5%), then training terminates, using this group of gauss hybrid models after training as background channel model ready for use, if alternatively,
Accuracy rate is less than or equal to predetermined threshold value, then increases the quantity of voice data sample, and be trained again, until the group is high
The accuracy rate of this mixed model is more than predetermined threshold value.
The background channel model that the present embodiment is trained in advance is by excavation to a large amount of voice data and to compare trained
It arrives, this model can accurately portray background sound when user speaks while retaining the vocal print feature of user to greatest extent
Line feature, and can remove this feature in identification, and the inherent feature of user voice is extracted, it can significantly improve use
The accuracy rate and efficiency of family authentication.
In one embodiment, the distance between the current vocal print discriminant vectors of above-mentioned calculating and standard vocal print discriminant vectors, base
Include in the step of distance of calculating generates authentication result：
Calculate the COS distance between the current vocal print discriminant vectors and standard vocal print discriminant vectors： For the standard vocal print discriminant vectors,For current vocal print discriminant vectors；If the COS distance is small
In or equal to preset distance threshold, then the information being verified is generated；If the COS distance is more than preset apart from threshold
Value, then generate verification not by information.
Wherein, User Identity can be carried when storing the standard vocal print discriminant vectors of user, verification user's
When identity, corresponding standard vocal print discriminant vectors are obtained according to the identification information match of current vocal print discriminant vectors, and calculate and work as
COS distance between preceding vocal print discriminant vectors and the standard vocal print discriminant vectors matched verifies target with COS distance
The identity of user improves the accuracy of authentication.
Compared with prior art, the present invention using client computer, server and is held eventually when carrying out voice print verification
The framework of composition, client computer is held to carry User Identity and made requests on to server, server generates and user's body
Part identifies corresponding graphic code parameter and is sent to client computer, and the corresponding figure of display graphic code parameter is carried out for it
Code, user are verified by chained address transmission random code to server using after the handheld terminal scanning figure shape code of carrying,
Channel can be established with server by being verified, and obtain the voice data of the user of handheld terminal acquisition, carried out vocal print and tested
Card, the present invention do not need the voice data of developed client-side program acquisition user, voice print verification are carried out using handheld terminal
Flexibility is high and is not easy to be disturbed, and binds server and client computer using User Identity, recycles random code
Client computer, server and handheld terminal are bound again, avoid the occurrence of the case where sound is kidnapped, improves voice print verification
Authenticity and safety.
As shown in Fig. 2, Fig. 2 is the flow diagram of one embodiment of method of voice print verification of the present invention, the voice print verification
Method includes the following steps：
Step S1, after receiving the authentication request of carrying User Identity of client computer transmission, clothes
Business device generates the graphic code parameter of graphic code corresponding with the User Identity, and the graphic code parameter is sent to the client
Computer is held, graphic code corresponding with the graphic code parameter, the graphic code parameter are generated and shown for the client computer
Including random secret key and voice print database acquisition link address；
Wherein, User Identity is the mark of the identity for unique mark user, it is preferable that User Identity is
Identification card number.Graphic code is preferably Quick Response Code, however, not limited to this, such as can also be bar code.Graphic code parameter is used for
Corresponding graphic code is generated, such as Quick Response Code parameter generates corresponding Quick Response Code, bar code parameters generate corresponding bar code.Figure
Shape code parameter includes random secret key and voice print database acquisition link address, can also further comprise effective time, the figure of graphic code
The details of shape code, scene value ID of graphic code etc., random secret key can be random number word string or random string etc..
The authentication request for the carrying User Identity that client computer is sent to server, server receive
After the authentication request, generate corresponding with User Identity random secret key, the server voice print database acquisition link
It is grounded location and the effective time of graphic code, the details of graphic code, the graphic codes parameter such as scene value ID of graphic code, by this
Graphic code parameter is sent to the client computer, after client computer receives graphic code parameter, according to graphic code parameter
Corresponding graphic code is generated, and is shown, is scanned for handheld terminal.
Step S2, it is described after handheld terminal parsing graphic code obtains random secret key and voice print database acquisition link address
Server receives handheld terminal and is asked by the voice print verification for carrying random secret key that voice print database acquisition link address is sent,
And analyze the random secret key being sent in the graphic code parameter of the client computer and the random secret key received from handheld terminal
It is whether consistent；
Handheld terminal carries out graphic code using the function module for parsing graphic code of itself after scanning figure shape code
Parsing obtains corresponding random secret key, the effective time of the voice print database acquisition link address of the server and graphic code, figure
Graphic codes parameter, the handheld terminals such as the details of shape code, the scene value ID of graphic code pass through voice print database acquisition link address
The voice print verification that transmission carries random secret key is asked into server.
After server receives voice print verification request, analysis is sent in the graphic code parameter of the client computer
Whether random secret key and the random secret key received from handheld terminal are consistent, other handheld terminals usurp the random of this in order to prevent
Voice print verification is carried out with server after secret key, improves the accuracy of voice print verification, in one embodiment, server receives hand-held whole
The voice print verification request for carrying random secret key that end is sent by voice print database acquisition link address, first analysis receive this
Whether the number of random secret key is more than preset times；If the number for receiving the random secret key is more than preset times, it is greater than 1
Secondary, then the server refusal respond voice print verification is asked, and can the relevant information of the handheld terminal be sent to server, for clothes
The reference frame whether business device is subsequently spoofed as voice print verification, if being less than or equal to the preset times, for example, 1 time, then again
Execute the random secret key that is sent in the graphic code parameter of the client computer of analysis with received from handheld terminal it is random secret
The whether consistent operation of key.
Other handheld terminals are usurped and carry out voice print verification with server after this random secret key in order to prevent, further carry
The accuracy of high voice print verification, in another embodiment, server receive handheld terminal and pass through voice print database acquisition link address
Whether the time that the voice print verification request for carrying random secret key sent, first analysis receive the random secret key is in the figure
Within the scope of the effective time of shape code, such as the effective time of the graphic code is 2018.03.01-2018.03.10, and server receives
The time of the random secret key of handheld terminal is 2018.03.08, then is within the scope of the effective time of the graphic code.If in should
Within the scope of the effective time of graphic code, then the number for receiving the random secret key is analyzed again whether more than preset times, for example, point
Whether the number that analysis receives the random secret key is more than 1 time；If the number for receiving the random secret key is more than preset times, take
Device refusal respond of being engaged in voice print verification request, and the relevant information of the handheld terminal can be sent to server, after server
The continuous reference frame whether being spoofed as voice print verification.It is last to execute analysis transmission again if being less than or equal to the preset times
It is whether consistent to the random secret key in the graphic code parameter of the client computer and the random secret key from handheld terminal reception
Operation.
Step S3 if so, the server establishes the data under voice channel with the handheld terminal, and is based on the language
Sound data acquisition channel obtains the current voice print verification voice data of the user acquired from the handheld terminal；
If the random secret key being sent in the graphic code parameter of the client computer and received from handheld terminal with
Machine secret key is consistent, then establishes the data under voice channel with the handheld terminal.Handheld terminal passes through the voice collectings such as microphone
Equipment collects the current voice print verification voice data of user in real time.When acquiring current voice print verification voice data, should use up
Amount prevents the interference of ambient noise and handheld terminal.Handheld terminal keeps suitable distance with user, and does not have to be distorted big as possible
Handheld terminal, it is preferable to use alternating currents for power supply, and electric current is kept to stablize；Sensor should be used when being recorded.In framing and adopt
Before sample, noise treatment can be carried out to current voice print verification voice data, to be further reduced interference.In order to extract
The vocal print feature of current voice print verification voice data is obtained, the current voice print verification voice data acquired is preset data length
Voice data, or be the voice data more than preset data length.
Step S4 builds the corresponding current vocal print discriminant vectors of the current voice print verification voice data, according to scheduled use
The mapping relations of family identity and standard vocal print discriminant vectors, determine the corresponding standard vocal print of the User Identity differentiate to
Amount, calculates the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, and the distance based on calculating generates identity and tests
Card by the authentication result as a result, and be sent to the client computer.
In order to effectively reduce the calculation amount of Application on Voiceprint Recognition, the speed of Application on Voiceprint Recognition is improved, in one embodiment, above-mentioned structure
It the step of current voice print verification voice data corresponding current vocal print discriminant vectors, specifically includes：To current voice print verification language
Sound data are handled, and to extract preset kind vocal print feature, and build corresponding vocal print based on the preset kind vocal print feature
Feature vector；In the background channel model that vocal print feature vector input is trained in advance, to build the current voice print verification language
The corresponding current vocal print discriminant vectors of sound data.
Wherein, vocal print feature includes multiple types, such as broadband vocal print, narrowband vocal print, amplitude vocal print etc., and the present embodiment is pre-
If type vocal print feature is preferably mel-frequency cepstrum coefficient (the Mel Frequency of current voice print verification voice data
Cepstrum Coefficient, MFCC), Predetermined filter is Meier filter.When building corresponding vocal print feature vector,
By the vocal print feature composition characteristic data matrix of current voice print verification voice data, this feature data matrix is corresponding vocal print
Feature vector.
Specifically, preemphasis and windowing process are carried out to current voice print verification voice data, Fu is carried out to each adding window
Vertical leaf transformation obtains corresponding frequency spectrum, and the frequency spectrum is inputted Meier filter to export to obtain Meier frequency spectrum；In Meier frequency spectrum
Upper progress cepstral analysis is corresponded to obtaining mel-frequency cepstrum coefficient MFCC based on mel-frequency cepstrum coefficient MFCC compositions
Vocal print feature vector.
Wherein, preemphasis processing is really high-pass filtering processing, filters out low-frequency data so that current voice print verification voice number
High frequency characteristics in more highlights, and specifically, the transmission function of high-pass filtering is：H (Z)=1- α Z-1, wherein Z is voice number
According to α is constant factor, it is preferable that the value of α is 0.97；Since voice data deviates from original to a certain extent after framing
Beginning voice, therefore, it is necessary to carry out windowing process to voice data.On Meier frequency spectrum carry out cepstral analysis be, for example, take logarithm,
Inverse transformation is done, inverse transformation is realized generally by DCT discrete cosine transforms, takes the 2nd after DCT to the 13rd coefficient conduct
Mel-frequency cepstrum coefficient MFCC.Mel-frequency cepstrum coefficient MFCC is the vocal print feature of this frame voice data, by every frame
Mel-frequency cepstrum coefficient MFCC composition characteristic data matrixes, this feature data matrix is the vocal print feature of speech sample data
Vector.
The present embodiment takes the mel-frequency cepstrum coefficient MFCC of voice data to form corresponding vocal print feature vector, due to it
Than the frequency band for the linear interval in normal cepstrum more can subhuman auditory system, therefore body can be improved
The accuracy of part verification.
Then, it by above-mentioned vocal print feature vector input background channel model trained in advance, is tested with constructing current vocal print
The corresponding current vocal print discriminant vectors of voice data are demonstrate,proved, for example, calculating current sound using background channel model trained in advance
The corresponding eigenmatrix of line validating speech data, with determine the corresponding current vocal print of current voice print verification voice data differentiate to
Amount.
For high efficiency, the corresponding current vocal print discriminant vectors of current voice print verification voice data are constructed in high quality,
In a preferred embodiment, which is one group of gauss hybrid models, the training process of the background channel model
Include the following steps：1. obtaining the voice data sample of preset quantity, the voice data sample of each preset quantity is corresponding with mark
Accurate vocal print discriminant vectors；It is corresponded to 2. being handled respectively each voice data sample with extracting each voice data sample
Preset kind vocal print feature, and each voice number is built based on the corresponding preset kind vocal print feature of each voice data sample
According to the corresponding vocal print feature vector of sample；3. all preset kind vocal print feature vectors extracted are divided into the first percentage
The verification collection of training set and the second percentage, the sum of first percentage and the second percentage are less than or equal to 100%；4.
This group of gauss hybrid models are trained using the preset kind vocal print feature vector in training set, and the profit after the completion of training
It is verified with the accuracy rate of this group of gauss hybrid models after verification set pair training；If accuracy rate be more than predetermined threshold value (for example,
98.5%), then training terminates, using this group of gauss hybrid models after training as background channel model ready for use, if alternatively,
Accuracy rate is less than or equal to predetermined threshold value, then increases the quantity of voice data sample, and be trained again, until the group is high
The accuracy rate of this mixed model is more than predetermined threshold value.
The background channel model that the present embodiment is trained in advance is by excavation to a large amount of voice data and to compare trained
It arrives, this model can accurately portray background sound when user speaks while retaining the vocal print feature of user to greatest extent
Line feature, and can remove this feature in identification, and the inherent feature of user voice is extracted, it can significantly improve use
The accuracy rate and efficiency of family authentication.
In one embodiment, the distance between the current vocal print discriminant vectors of above-mentioned calculating and standard vocal print discriminant vectors, base
Include in the step of distance of calculating generates authentication result：
Calculate the COS distance between the current vocal print discriminant vectors and standard vocal print discriminant vectors： For the standard vocal print discriminant vectors,For current vocal print discriminant vectors；If the COS distance is small
In or equal to preset distance threshold, then the information being verified is generated；If the COS distance is more than preset apart from threshold
Value, then generate verification not by information.
Wherein, User Identity can be carried when storing the standard vocal print discriminant vectors of user, verification user's
When identity, corresponding standard vocal print discriminant vectors are obtained according to the identification information match of current vocal print discriminant vectors, and calculate and work as
COS distance between preceding vocal print discriminant vectors and the standard vocal print discriminant vectors matched verifies target with COS distance
The identity of user improves the accuracy of authentication.
Compared with prior art, the present invention using client computer, server and is held eventually when carrying out voice print verification
The framework of composition, client computer is held to carry User Identity and made requests on to server, server generates and user's body
Part identifies corresponding graphic code parameter and is sent to client computer, and the corresponding figure of display graphic code parameter is carried out for it
Code, user are verified by chained address transmission random code to server using after the handheld terminal scanning figure shape code of carrying,
Channel can be established with server by being verified, and obtain the voice data of the user of handheld terminal acquisition, carried out vocal print and tested
Card, the present invention do not need the voice data of developed client-side program acquisition user, voice print verification are carried out using handheld terminal
Flexibility is high and is not easy to be disturbed, and binds server and client computer using User Identity, recycles random code
Client computer, server and handheld terminal are bound again, avoid the occurrence of the case where sound is kidnapped, improves voice print verification
Authenticity and safety.
The present invention also provides a kind of computer readable storage medium, processing is stored on the computer readable storage medium
The step of system, the processing system realizes the method for above-mentioned voice print verification when being executed by processor.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of server, which is characterized in that the server includes memory and the processor that is connect with the memory, institute
The processing system that is stored with and can run on the processor in memory is stated, when the processing system is executed by the processor
Realize following steps：
Generation step generates after receiving the authentication request of carrying User Identity of client computer transmission
The graphic code parameter of graphic code corresponding with the User Identity, and the graphic code parameter is sent to the client and is calculated
Machine, generates for the client computer and shows corresponding with graphic code parameter graphic code, the graphic code parameter include with
Machine secret key and voice print database acquisition link address；
Analytical procedure receives hand after handheld terminal parsing graphic code obtains random secret key and voice print database acquisition link address
It holds terminal to ask by the voice print verification for carrying random secret key that voice print database acquisition link address is sent, and analyzes and be sent to
Whether random secret key in the graphic code parameter of the client computer and the random secret key received from handheld terminal are consistent；
Obtaining step if so, establishing the data under voice channel with the handheld terminal, and is believed based on the data under voice
Road obtains the current voice print verification voice data of the user acquired from the handheld terminal；
Verification step builds the corresponding current vocal print discriminant vectors of the current voice print verification voice data, according to scheduled user
The mapping relations of identity and standard vocal print discriminant vectors, determine the corresponding standard vocal print of the User Identity differentiate to
Amount, calculates the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, and the distance based on calculating generates identity and tests
Card by the authentication result as a result, and be sent to the client computer.
2. server according to claim 1, which is characterized in that the analytical procedure specifically includes：
The server receives the vocal print for carrying random secret key that handheld terminal is sent by voice print database acquisition link address
Whether checking request, the number that analysis receives the random secret key are more than preset times；
If being less than or equal to the preset times, analysis be sent to random secret key in the graphic code parameter of the client computer with
Whether the random secret key received from handheld terminal is consistent.
3. server according to claim 1, which is characterized in that the graphic code parameter further include graphic code it is effective when
Between, the analytical procedure specifically includes：
The server receives the vocal print for carrying random secret key that handheld terminal is sent by voice print database acquisition link address
Whether checking request, the time that analysis receives the random secret key are within the scope of the effective time of the graphic code；
If within the scope of the effective time in the graphic code, whether the number that analysis receives the random secret key is more than default time
Number；
If being less than or equal to the preset times, analysis be sent to random secret key in the graphic code parameter of the client computer with
Whether the random secret key received from handheld terminal is consistent.
4. server according to any one of claims 1 to 3, which is characterized in that described structure current voice print verification language
It the step of sound data corresponding current vocal print discriminant vectors, specifically includes：
Current voice print verification voice data is handled, to extract preset kind vocal print feature, and is based on the preset kind sound
The corresponding vocal print feature vector of line feature construction；
In the background channel model that vocal print feature vector input is trained in advance, to build the current voice print verification voice data
Corresponding current vocal print discriminant vectors；
Described to calculate the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, the distance based on calculating generates body
The step of part verification result includes：
Calculate the COS distance between the current vocal print discriminant vectors and standard vocal print discriminant vectors： For
The standard vocal print discriminant vectors,For current vocal print discriminant vectors；
If the COS distance is less than or equal to preset distance threshold, the information being verified is generated；
If the COS distance be more than preset distance threshold, generate verification not by information.
5. a kind of method of voice print verification, which is characterized in that the method for the voice print verification includes：
S1, after receiving the authentication request of carrying User Identity of client computer transmission, server generates
The graphic code parameter of graphic code corresponding with the User Identity, and the graphic code parameter is sent to the client and is calculated
Machine, generates for the client computer and shows corresponding with graphic code parameter graphic code, the graphic code parameter include with
Machine secret key and voice print database acquisition link address；
S2, after handheld terminal parsing graphic code obtains random secret key and voice print database acquisition link address, the server connects
It receives handheld terminal to ask by the voice print verification for carrying random secret key that voice print database acquisition link address is sent, and analyzes hair
Whether give random secret key in the graphic code parameter of the client computer consistent with the random secret key that is received from handheld terminal；
S3 if so, the server establishes the data under voice channel with the handheld terminal, and is adopted based on the voice data
Collection channel obtains the current voice print verification voice data of the user acquired from the handheld terminal；
S4 builds the corresponding current vocal print discriminant vectors of the current voice print verification voice data, according to scheduled user identity mark
Know the mapping relations with standard vocal print discriminant vectors, determine the corresponding standard vocal print discriminant vectors of the User Identity, calculates
Current the distance between vocal print discriminant vectors and standard vocal print discriminant vectors, the distance generation authentication based on calculating as a result,
And the authentication result is sent to the client computer.
6. the method for voice print verification according to claim 5, which is characterized in that the step S2 is specifically included：
The server receives the vocal print for carrying random secret key that handheld terminal is sent by voice print database acquisition link address
Whether checking request, the number that analysis receives the random secret key are more than preset times；
If being less than or equal to the preset times, analysis be sent to random secret key in the graphic code parameter of the client computer with
Whether the random secret key received from handheld terminal is consistent.
7. the method for voice print verification according to claim 5, which is characterized in that the graphic code parameter further includes graphic code
Effective time, the step S2 specifically includes：
The server receives the vocal print for carrying random secret key that handheld terminal is sent by voice print database acquisition link address
Whether checking request, the time that analysis receives the random secret key are within the scope of the effective time of the graphic code；
If within the scope of the effective time in the graphic code, whether the number that analysis receives the random secret key is more than default time
Number；
If being less than or equal to the preset times, analysis be sent to random secret key in the graphic code parameter of the client computer with
Whether the random secret key received from handheld terminal is consistent.
8. according to the method for claim 5 to 7 any one of them voice print verification, which is characterized in that described structure current sound
It the step of line validating speech data corresponding current vocal print discriminant vectors, specifically includes：
Current voice print verification voice data is handled, to extract preset kind vocal print feature, and is based on the preset kind sound
The corresponding vocal print feature vector of line feature construction；
In the background channel model that vocal print feature vector input is trained in advance, to build the current voice print verification voice data
Corresponding current vocal print discriminant vectors；
Described to calculate the distance between current vocal print discriminant vectors and standard vocal print discriminant vectors, the distance based on calculating generates body
The step of part verification result includes：
Calculate the COS distance between the current vocal print discriminant vectors and standard vocal print discriminant vectors： For
The standard vocal print discriminant vectors,For current vocal print discriminant vectors；
If the COS distance is less than or equal to preset distance threshold, the information being verified is generated；
If the COS distance be more than preset distance threshold, generate verification not by information.
9. the method for voice print verification according to claim 8, which is characterized in that described to current voice print verification voice data
Handled, to extract preset kind vocal print feature, and based on the preset kind vocal print feature build corresponding vocal print feature to
The step of amount, specifically includes：
Preemphasis, framing and windowing process are carried out to the current voice print verification voice data, Fourier is carried out to each adding window
Leaf transformation obtains corresponding frequency spectrum, and the frequency spectrum is inputted Meier filter to export to obtain Meier frequency spectrum；
Cepstral analysis is carried out on Meier frequency spectrum to obtain mel-frequency cepstrum coefficient MFCC, is based on mel-frequency cepstrum system
Number MFCC forms corresponding vocal print feature vector.
10. a kind of computer readable storage medium, which is characterized in that be stored with processing system on the computer readable storage medium
System, when the processing system is executed by processor the method for voice print verification of the realization as described in any one of claim 5 to 9
Step.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810457267.1A CN108650266B (en) | 2018-05-14 | 2018-05-14 | Server, voiceprint verification method and storage medium |
| PCT/CN2018/102049 WO2019218512A1 (en) | 2018-05-14 | 2018-08-24 | Server, voiceprint verification method, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810457267.1A CN108650266B (en) | 2018-05-14 | 2018-05-14 | Server, voiceprint verification method and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108650266A true CN108650266A (en) | 2018-10-12 |
| CN108650266B CN108650266B (en) | 2020-02-18 |
Family
ID=63755329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810457267.1A Active CN108650266B (en) | 2018-05-14 | 2018-05-14 | Server, voiceprint verification method and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108650266B (en) |
| WO (1) | WO2019218512A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109462482A (en) * | 2018-11-09 | 2019-03-12 | 深圳壹账通智能科技有限公司 | Method for recognizing sound-groove, device, electronic equipment and computer readable storage medium |
| CN113129903A (en) * | 2019-12-31 | 2021-07-16 | 深圳市航盛电子股份有限公司 | Automatic audio test method and device, computer equipment and storage medium |
| CN113973299A (en) * | 2020-07-22 | 2022-01-25 | 中国石油化工股份有限公司 | Wireless sensor with identity authentication function and identity authentication method |
| WO2022017452A1 (en) * | 2020-07-24 | 2022-01-27 | Giesecke+Devrient Mobile Security Gmbh | Identity authentication method, apparatus, devices and storage media |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050089172A1 (en) * | 2003-10-24 | 2005-04-28 | Aruze Corporation | Vocal print authentication system and vocal print authentication program |
| CN107610707A (en) * | 2016-12-15 | 2018-01-19 | 平安科技（深圳）有限公司 | A kind of method for recognizing sound-groove and device |
| CN107993071A (en) * | 2017-11-21 | 2018-05-04 | 平安科技（深圳）有限公司 | Electronic device, auth method and storage medium based on vocal print |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2519571A (en) * | 2013-10-25 | 2015-04-29 | Aplcomp Oy | Audiovisual associative authentication method and related system |
| CN105100123A (en) * | 2015-09-11 | 2015-11-25 | 深圳市亚略特生物识别科技有限公司 | Application registration method and system |
| CN107068154A (en) * | 2017-03-13 | 2017-08-18 | 平安科技（深圳）有限公司 | The method and system of authentication based on Application on Voiceprint Recognition |
-
2018
- 2018-05-14 CN CN201810457267.1A patent/CN108650266B/en active Active
- 2018-08-24 WO PCT/CN2018/102049 patent/WO2019218512A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050089172A1 (en) * | 2003-10-24 | 2005-04-28 | Aruze Corporation | Vocal print authentication system and vocal print authentication program |
| CN107610707A (en) * | 2016-12-15 | 2018-01-19 | 平安科技（深圳）有限公司 | A kind of method for recognizing sound-groove and device |
| CN107993071A (en) * | 2017-11-21 | 2018-05-04 | 平安科技（深圳）有限公司 | Electronic device, auth method and storage medium based on vocal print |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109462482A (en) * | 2018-11-09 | 2019-03-12 | 深圳壹账通智能科技有限公司 | Method for recognizing sound-groove, device, electronic equipment and computer readable storage medium |
| CN109462482B (en) * | 2018-11-09 | 2023-08-08 | 深圳壹账通智能科技有限公司 | Voiceprint recognition method, voiceprint recognition device, electronic equipment and computer readable storage medium |
| CN113129903A (en) * | 2019-12-31 | 2021-07-16 | 深圳市航盛电子股份有限公司 | Automatic audio test method and device, computer equipment and storage medium |
| CN113973299A (en) * | 2020-07-22 | 2022-01-25 | 中国石油化工股份有限公司 | Wireless sensor with identity authentication function and identity authentication method |
| CN113973299B (en) * | 2020-07-22 | 2023-09-29 | 中国石油化工股份有限公司 | Wireless sensor with identity authentication function and identity authentication method |
| WO2022017452A1 (en) * | 2020-07-24 | 2022-01-27 | Giesecke+Devrient Mobile Security Gmbh | Identity authentication method, apparatus, devices and storage media |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019218512A1 (en) | 2019-11-21 |
| CN108650266B (en) | 2020-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107517207A (en) | Server, auth method and computer-readable recording medium | |
| CN107527620B (en) | Electronic device, the method for authentication and computer readable storage medium | |
| CN107993071A (en) | Electronic device, auth method and storage medium based on vocal print | |
| CN108650266A (en) | Server, the method for voice print verification and storage medium | |
| CN107977776B (en) | Information processing method, device, server and computer readable storage medium | |
| US11862176B2 (en) | Reverberation compensation for far-field speaker recognition | |
| CN108805091A (en) | Method and apparatus for generating model | |
| CN108154371A (en) | Electronic device, the method for authentication and storage medium | |
| CN107393541A (en) | Information Authentication method and apparatus | |
| WO2021051572A1 (en) | Voice recognition method and apparatus, and computer device | |
| CN109086719A (en) | Method and apparatus for output data | |
| CN108281158A (en) | Voice biopsy method, server and storage medium based on deep learning | |
| CN112466314A (en) | Emotion voice data conversion method and device, computer equipment and storage medium | |
| CN108694952A (en) | Electronic device, the method for authentication and storage medium | |
| CN110473552A (en) | Speech recognition authentication method and system | |
| CN109146492A (en) | A kind of device and method of vehicle end mobile payment | |
| CN112037800A (en) | Voiceprint nuclear model training method and device, medium and electronic equipment | |
| CN108630208B (en) | Server, voiceprint-based identity authentication method and storage medium | |
| CN111933154A (en) | Method and device for identifying counterfeit voice and computer readable storage medium | |
| CN109165570A (en) | Method and apparatus for generating information | |
| CN108664610A (en) | Method and apparatus for handling data | |
| CN116975823A (en) | Data processing method, device, computer equipment, storage medium and product | |
| CN115910071A (en) | Identity authentication method and device, computer equipment and storage medium | |
| CN113393318A (en) | Bank card application wind control method and device, electronic equipment and medium | |
| CN117174094A (en) | Voiceprint recognition method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |