The content of the invention
The embodiment of the present application provides a kind of voiceprint authentication method, during solving to carry out user authentication convenience compared withThe problem of low.
The embodiment of the present application uses following technical proposals：
A kind of voiceprint authentication method, including：
Receive voice signal to be certified；
Determine the first vocal print feature and the text information in the voice signal；
If the text information corresponds to default account identification, it is determined that first vocal print feature and default vocal print featureSimilarity, the default vocal print feature is the vocal print feature corresponding with the default account identification gathered in advance；
If the similarity of first vocal print feature and the default vocal print feature is higher than given threshold, it is determined that certification intoWork(, to carry out business operation to the default account identification.
The embodiment of the present application also provides a kind of account register method, to solve to user carry out authentication when convenienceThe problem of relatively low.
The embodiment of the present application uses following technical proposals：
A kind of account register method, including：
Determine account identification to be registered；
Gather the vocal print feature in voice signal input by user；
The account identification and the vocal print feature are corresponded to as the account information of registration and preserved, wherein, the vocal printThe vocal print feature and text information that feature is used in voice signal to be certified carry out authentication, the voice letter to be certifiedNumber it is the voice signal for asking certification.
The embodiment of the present application also provides a kind of method of payment, to solve to user carry out authentication when convenience it is relatively lowThe problem of.
The embodiment of the present application uses following technical proposals：
A kind of method of payment, including：
Beneficiary terminal receives paying party voice signal to be certified input by user, and the voice signal is uploaded to serviceDevice, the voice signal to be certified are used for the authentication of paying party user in payment process；
Server determines the first vocal print feature and text information in the voice signal；
Server when the definite text information corresponds to default account identification, determine first vocal print feature with it is pre-If the similarity of vocal print feature, the default vocal print feature is that the vocal print corresponding with the default account identification gathered in advance is specialSign；
Server when the similarity for determining first vocal print feature and the default vocal print feature is higher than given threshold,Determine that the paying party user identity is legal, and notify payment module to complete payment process.
The embodiment of the present application also provides a kind of voiceprint authentication apparatus, to solve to user carry out authentication when convenienceThe problem of relatively low.
The embodiment of the present application uses following technical proposals：
A kind of voiceprint authentication apparatus, including：
Receiving unit, receives voice signal to be certified；
First determination unit, determines the first vocal print feature and text information in the voice signal；
Second determination unit, if the text information corresponds to default account identification, it is determined that first vocal print featureWith the similarity of default vocal print feature, the default vocal print feature is the sound corresponding with the default account identification gathered in advanceLine feature；
3rd determination unit, if the similarity of first vocal print feature and the default vocal print feature is higher than setting thresholdValue, it is determined that certification success, to carry out business operation to the default account identification.
The embodiment of the present application also provides a kind of electronic equipment, to solve to user carry out authentication when convenience it is relatively lowThe problem of.
The embodiment of the present application uses following technical proposals：
A kind of electronic equipment, including：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the place when executedManage device and perform following operation：
Receive voice signal to be certified；
Determine the first vocal print feature and the text information in the voice signal；
If the text information corresponds to default account identification, it is determined that first vocal print feature and default vocal print featureSimilarity, the default vocal print feature is the vocal print feature corresponding with the default account identification gathered in advance；
If the similarity of first vocal print feature and the default vocal print feature is higher than given threshold, it is determined that certification intoWork(, to carry out business operation to the default account identification.
The embodiment of the present application also provides a kind of computer-readable recording medium, to solve to user carry out authentication whenThe problem of convenience is relatively low.
The embodiment of the present application uses following technical proposals：
A kind of computer-readable recording medium, the computer-readable recording medium storage one or more program are describedOne or more programs by the electronic equipment including multiple application programs when being performed so that the electronic equipment performs following behaviourMake：
Receive voice signal to be certified；
Determine the first vocal print feature and the text information in the voice signal；
If the text information corresponds to default account identification, it is determined that first vocal print feature and default vocal print featureSimilarity, the default vocal print feature is the vocal print feature corresponding with the default account identification gathered in advance；
If the similarity of first vocal print feature and the default vocal print feature is higher than given threshold, it is determined that certification intoWork(, to carry out business operation to the default account identification.
The embodiment of the present application also provides a kind of account register device, to solve to user carry out authentication when convenienceThe problem of relatively low.
The embodiment of the present application uses following technical proposals：
A kind of account register device, including：
Account number determination unit, determines account identification to be registered；
Collecting unit, gathers the vocal print feature in voice signal input by user；
Storage unit, the account identification and the vocal print feature are corresponded to as the account information of registration and preserved, wherein,The vocal print feature and text information that the vocal print feature is used in voice signal to be certified carry out authentication, described to wait to recognizeCard voice signal is the voice signal for asking certification.
The embodiment of the present application also provides a kind of electronic equipment, to solve to user carry out authentication when convenience it is relatively lowThe problem of.
The embodiment of the present application uses following technical proposals：
A kind of electronic equipment, including：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the place when executedManage device and perform following operation：
Determine account identification to be registered；
Gather the vocal print feature in voice signal input by user；
The account identification and the vocal print feature are corresponded to as the account information of registration and preserved, wherein, the vocal printThe vocal print feature and text information that feature is used in voice signal to be certified carry out authentication, the voice letter to be certifiedNumber it is the voice signal for asking certification.
The embodiment of the present application also provides a kind of computer-readable recording medium, to solve to user carry out authentication whenThe problem of convenience is relatively low.
The embodiment of the present application uses following technical proposals：
A kind of computer-readable recording medium, the computer-readable recording medium storage one or more program are describedOne or more programs by the electronic equipment including multiple application programs when being performed so that the electronic equipment performs following behaviourMake：
Determine account identification to be registered；
Gather the vocal print feature in voice signal input by user；
The account identification and the vocal print feature are corresponded to as the account information of registration and preserved, wherein, the vocal printThe vocal print feature and text information that feature is used in voice signal to be certified carry out authentication, the voice letter to be certifiedNumber it is the voice signal for asking certification.
The embodiment of the present application also provides a kind of payment system, to solve to user carry out authentication when convenience it is relatively lowThe problem of.
The embodiment of the present application uses following technical proposals：
A kind of payment system, including beneficiary terminal and server, wherein：
The beneficiary terminal, receives paying party voice signal to be certified input by user, the voice signal is uploadedTo server, the voice signal to be certified is used for the authentication of paying party user in payment process；
The server, determines the first vocal print feature and text information in the voice signal；
When the definite text information corresponds to default account identification, first vocal print feature and default vocal print are determinedThe similarity of feature, the default vocal print feature are the vocal print feature corresponding with the default account identification gathered in advance；
When the similarity for determining first vocal print feature and the default vocal print feature is higher than given threshold, institute is determinedIt is legal to state paying party user identity, and notifies payment module to complete payment process.
Above-mentioned at least one technical solution that the embodiment of the present application uses can reach following beneficial effect：
After voice signal to be certified is received, the first vocal print feature and text information in the voice signal are determined,If the text information corresponds to default account identification, show that the account number is had been provided with for carrying out voiceprintDefault vocal print feature, then the similarity of the first vocal print feature and default vocal print feature can be determined, if the first vocal print featureBe higher than given threshold with the similarity of default vocal print feature, it is determined that certification success, with to the default account identification into industryBusiness operation., can basis after user says the account identification of oneself as voice signal to be certified in whole verification processIn voice signal input by user text information positioning user account, then the vocal print feature in voice messaging toThe legitimacy at family is authenticated, and for a user, by saying the account identification of oneself, you can complete certification, convenience compared withIt is high.
Embodiment
To make the purpose, technical scheme and advantage of the application clearer, below in conjunction with the application specific embodiment andTechnical scheme is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the application oneSection Example, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not doingGo out all other embodiments obtained under the premise of creative work, shall fall in the protection scope of this application.
Below in conjunction with attached drawing, the technical solution that each embodiment of the application provides is described in detail.
With the development of Internet technology, the identity of user can be verified in more and more business scenarios, to protectHinder the legitimate rights and interests of user, such as account registering service described in background technology, payment transaction.However, body in the prior artThe process of part certification is cumbersome, and convenience is relatively low, below by taking payment transaction as an example, briefly describes authentication of the prior artJourney.
The scene graph provided is please referred to Fig.1, when carrying out payment transaction, paying party needs to log in payment on payment equipmentThe account of side, when logging in, paying party user can input account, login password on payment equipment, and then server authentication passes throughAfterwards, method, apparatus of paying the bill obtains the payment information (information such as shroff account number, amount of money) of beneficiary, and generation payment interface, then pays the billSquare user inputs payment cipher on payment equipment, and server authentication is by rear, completion payment transaction.In this process, useFamily needs information, the convenience such as input account, login password, payment cipher on payment equipment relatively low.
In this specification one or more embodiment, user identity can be authenticated by vocal print, improve bodyThe convenience of part certification, before voiceprint is carried out by vocal print, the voiceprint that can gather user in advance is recognized as vocal printAs the template compared during card, for ease of description, it is referred to as pre- that vocal print feature corresponding with account identification will be gathered in advance hereIf vocal print feature.So before the voiceprint process in this specification one or more embodiment is introduced in detailed annotation, below firstThe process gathered to the default vocal print feature in this specification one or more embodiment is described in detail.
For ease of describing, in this specification one or more embodiment, the executive agent of vocal print feature acquisition method is presetIt can be server, hereinafter by taking executive agent is server as an example, the embodiment of this method is introduced.It is appreciated thatThe executive agent of this method is a kind of exemplary explanation for server, is not construed as the restriction to this method.
When carrying out default vocal print feature collection, can be carried out when account is registered, vocal print is carried out when account is registeredCollection realizes flow diagram as shown in Fig. 2, comprising the following steps：
Step S100：Determine account identification to be registered；
Account identification can be used for the account for identifying user, and account identification is such as account, for example bank card number isThe account identification of user's bank account.
Account identification to be registered can be that user is manually entered by terminal device, for example user inputs the hand of oneselfMachine can input the word of account management system prescribed form as account mark as account identification to be registered, or userKnow.So the account management system of server can judge this after the account identification that user is inputted by terminal device is receivedWhether account identification has been registered, if be registered, prompts user to change account identification.If account mark input by userKnow for cell-phone number, then can also carry out short message verification to the cell-phone number, possess the cell-phone number to determine that user is actual.
Account identification to be registered can also be that the account management system of server distributes automatically, such as, noted in userDuring volume account, account management system can distribute a certain mark, the account mark as user for user automatically according to certain ruleKnow.
Step S102：Gather the vocal print feature in voice signal input by user；
In register account number, user can be registered by terminal device (such as mobile phone, tablet computer etc.), thenWhen gathering voice signal, the voice signal of user can be gathered by the microphone of subscriber terminal equipment, then terminal deviceVoice signal is uploaded onto the server, server has just obtained voice signal input by user.
After voice signal is collected, the vocal print feature in voice signal can be extracted, this specification is one or moreVocal print feature in embodiment, can include voice signal in acoustic feature, such as frequency spectrum, cepstrum, formant, fundamental tone,The features such as reflectance factor；Can also include voice signal in language lexical characteristics, such as in context word relevance, up and downThe relevance of phoneme in text；It can also include the prosodic features in voice signal；It can also include the language of language in voice signalThe features such as kind, dialect and accent, do not repeat one by one herein.
It should be noted that in practical application, user can be required to upload multiple voice signal, multiple voices letters are extractedVocal print feature in number, then takes the average value of multiple vocal print features to prevent from only extracting a voice as default vocal print featureVocal print feature in signal may be inaccurate.
Step S104：The account identification and the vocal print feature are corresponded to as the account information of registration and preserved, so as toVocal print feature in voice signal to be certified and text information carry out authentication, the voice signal to be certified be forAsk the voice signal of certification.
After the vocal print feature of voice signal has been extracted, server can be using the vocal print feature of extraction as default vocal printFeature, foundation during using as voiceprint, can be by account identification guarantor correspondings with the vocal print feature of extraction in order to facilitate certificationDeposit, for example same data record can be used as to preserve.
When account identification and vocal print feature are corresponded to preservation as the account information of registration, can be saved in for storing, can be according to account identification storehouse so after text information is received in the account identification storehouse of account identification and vocal print featureTo judge whether the text information is chartered account.
In this specification one or more embodiment, text information can be for note down specific matters, simplification figure picture andInto mark, in a computer, text information be typically it is existing in the form of text.Text information such as can be by the ChineseAt least one of information such as word, Arabic numerals, letter composition.
In addition, when carrying out vocal print collection, it can also be and carry out vocal print collection, such as some accounts for registered accountAlthough number having there is the authentication informations such as password, when user it is expected to add voiceprint information again, then at this time can alsoThe vocal print of user is gathered again, the foundation as voiceprint.Specific gatherer process can be found in the associated description in the application, hereinRepeat no more.
, below will be detailed after the gatherer process of the default vocal print feature in having introduced this specification one or more embodimentThe thin voiceprint process introduced in this specification one or more embodiment.
For ease of describing, in this specification one or more embodiment, the executive agent of voiceprint authentication method can be clothesBusiness device, hereinafter by taking executive agent is server as an example, is introduced the embodiment of this method.It is appreciated that this methodExecutive agent is a kind of exemplary explanation for server, is not construed as the restriction to this method.
In this specification one or more embodiment, voiceprint authentication method realizes flow diagram as shown in figure 3, bagInclude following step：
Step S200：Receive voice signal to be certified；
For ease of description, voice signal to be certified will be known as the voice signal for asking certification here.Such as Yong HuDuring login account, one section of voice signal can be inputted by terminal device, then the voice signal is just voice signal to be certified；WithFamily inputs one section of voice signal when asking to pay, with the legitimacy of request server verification user identity, then the voice is believedNumber also it is voice signal to be certified.
Voice signal to be certified can be that terminal device is gathered by microphone, and then terminal device will can collectVoice signal upload onto the server, the voice signal is authenticated with request server.For example user passes through smart mobile phoneLogin account, then smart mobile phone can gather voice signal by microphone, then upload onto the server, request server pairThe voice signal is authenticated.
Step S202：Determine the first vocal print feature and the text information in the voice signal；
During vocal print feature in the voice signal to be certified for determining to receive, the sound in the voice signal can be extractedLine feature, for the ease of being distinguished with the vocal print feature prestored before, here by the vocal print in voice signal to be certifiedFeature is known as the first vocal print feature.Specific vocal print feature can be found in the associated description in step S102, and details are not described herein again.
During text information in the voice signal to be certified for determining to receive, voice can be carried out to the voice signalIdentification, to identify the text information in the voice signal.Speech recognition can be by the spoken and written languages in voice input by userIdentify, such as, said in the voice of user " 123456 ", then by can obtain word after speech recognition“123456”。
Step S204：If the text information corresponds to default account identification, it is determined that first vocal print feature with it is pre-If the similarity of vocal print feature, the default vocal print feature is that the vocal print corresponding with the default account identification gathered in advance is specialSign；
After text information is identified, it can judge whether the text information corresponds to default account identification, specificallyFor, it can be determined that there is the account identification identical with the text information in default account identification storehouse, if default account identificationThere is the account identification identical with the text information in storehouse, it is determined that the text information corresponds to default account identification.Such as shouldText information is " 123456 ", then, if can think there is also account identification " 123456 " in default account identification storehouseThe text information corresponds to default account identification.
It should be noted that may be not belonging to the information of account identification in the text information there are some, this is probablySince user is when inputting voice signal to be certified, caused by also having said other contents, or since user's input is to be certifiedSurrounding environment is excessively noisy caused during voice signal, such as, text information is " 123456 is good ".Word can so be extractedBelong to the information of account identification form in information, then inquiry belongs to the information of account identification form and whether corresponds to default accountFamily identifies, if it is, it is also assumed that the text information corresponds to default account identification.
Such as if the information of account identification form is numeral, then can extract in " 123456 is good "" 123456 ", then inquire about whether " 123456 " correspond to default account identification, if it is, it is also assumed that " 123456It is good " correspond to default account identification
Account identification can be used for communicating, for example can be cell-phone number, mailbox etc..
If the word Asymmetry information should be sent and notify, it is desirable to which user is again in account identification to subscriber terminal equipmentInput voice signal to be certified.
If the text information corresponds to default account identification, then shows that the corresponding account of the text information has been pre-First gathered the account of default vocal print feature, then the voiceprint process that can be carried out., can be with when carrying out voiceprintThe similarity of the first vocal print feature and default vocal print feature is calculated, judges to input voice signal to be certified according to the similarityWhether user is legal.
Step S206：If the similarity of first vocal print feature and the default vocal print feature is higher than given threshold,Certification success is determined, to carry out business operation to the default account identification.
After the similarity of the first vocal print feature and default vocal print feature is obtained, can by by the similarity with setting in advanceFixed threshold value is compared, to determine whether certification success.If the similarity of the first vocal print feature and default vocal print feature is highIn given threshold, then it can be determined that certification is successful, if the similarity of the first vocal print feature and default vocal print feature is not highIn given threshold, then authentification failure is can be determined that.
For example, the similarity determined in step S204 is 99.45%, and given threshold is 90%, then can determine to recognizeDemonstrate,prove successfully.
In this specification one or more embodiment, the similarity of the first vocal print feature and default vocal print feature is being determinedWhen, can be come definite by advance trained Application on Voiceprint Recognition model.The Application on Voiceprint Recognition model can be by two vocal print spiesSign after being calculated by the parameter in model, obtains the similarity of two vocal print features as input.
When being trained to Application on Voiceprint Recognition model, the parameter in model can be adjusted, to allow model can be moreAdd and same user is accurately identified according to vocal print feature.The specific training process of Application on Voiceprint Recognition model is done below and is retouched in detailState.
Due to the vocal print feature of same user may be considered it is constant, then, by two of same user different languagesWhen the vocal print feature of sound signal is input in Application on Voiceprint Recognition model, obtained similarity should be 100%, certainly, actually shouldIn, being can be with existing for allowable error, therefore, as long as similarity is higher than the threshold value of some setting.It is possible to will be sameInput of the vocal print feature of two different phonetic signals of one user as the Application on Voiceprint Recognition model, then adjusts Application on Voiceprint RecognitionThe parameter of model so that the similarity of output is higher than given threshold.
Further, since the vocal print feature of different user may be considered it is different, then, by two languages of different userWhen the vocal print feature of sound signal is input in Application on Voiceprint Recognition model, obtained similarity should be no greater than given threshold.That, input that can be using the vocal print feature of two voice signals of different user as Application on Voiceprint Recognition model, adjusts Application on Voiceprint RecognitionThe parameter of model so that the similarity of output is not higher than given threshold.
Training Application on Voiceprint Recognition model when, substantial amounts of sample can be utilized, through the above way to Application on Voiceprint Recognition model intoRow training.The quantity of training sample is more, and the accuracy rate of Application on Voiceprint Recognition model also can be higher.
The voiceprint authentication method provided in this specification one or more embodiment, is receiving voice signal to be certifiedAfterwards, the first vocal print feature and the text information in the voice signal are determined, if the text information corresponds to default accountMark, then show that the account number has been provided with the default vocal print feature for carrying out voiceprint, then can determine firstThe similarity of vocal print feature and default vocal print feature, if the similarity of the first vocal print feature and default vocal print feature is higher than settingThreshold value, it is determined that certification success, to carry out business operation to the default account identification.In whole verification process, user says, can be according to the text information in voice signal input by user after going out the account identification of oneself as voice signal to be certifiedPosition user account, then the vocal print feature in voice messaging the legitimacy of user is authenticated, and to user andSpeech, by saying the account identification of oneself, you can complete certification, convenience is higher.
The identity identifying method that this specification one or more embodiment provides can be applied to following at least one businessIn：Payment transaction；Account Logon business.
It is described in detail only for both business, is not situated between in the implementation process of both business respectively belowThe ins and outs to continue, may be referred to associated description above.
The obvious identity identifying method can also be applied in other business, not enumerate herein.Ordinary skillPersonnel without making creative work, by the identity identifying method be applied to other business obtained in it is all itsIts embodiment, shall fall in the protection scope of this application.
It is applied to the detailed process in payment transaction to identity identifying method first to be described in detail, refers to Fig. 4 and provideScene graph, which realizes flow diagram as shown in figure 5, comprising the following steps：
Step S300：Beneficiary terminal receives paying party voice signal to be certified input by user, by the voice signalUpload onto the server, the voice signal to be certified is used for the authentication of paying party user in payment process；
Beneficiary terminal can receive paying party voice signal to be certified input by user by microphone, due to wanting rootThe account identification of user is obtained according to the text information in voice signal to be certified, therefore, user is inputting voice letter to be certifiedNumber when, can directly say the account identification of oneself.
Beneficiary terminal can show payment information (such as collection amount), so that paying party knows the letter that will be paid the billBreath.
The beneficiary terminal can be trade company line under cashier terminal, i.e., in this specification one or more embodimentIdentity identifying method, can be applied under line pay in scene.
Step S302：Server determines the first vocal print feature and text information in the voice signal；
Step S304：Server determines described when the definite text information corresponds to default account identification:First soundThe similarity of line feature and default vocal print feature, the default vocal print feature to be gathering with the default account identification pair in advanceThe vocal print feature answered；
Step S306：Server is higher than in the similarity of definite first vocal print feature and the default vocal print feature to be setWhen determining threshold value, determine that the paying party user identity is legal, and notify payment module to complete payment process.
After definite paying party user identity is legal, the business funds in paying party account can be transferred to beneficiary accountIn family, business funds here can be the fund completed needed for the payment transaction.Certainly the process for completing to pay can be by propping upModule is paid to perform, i.e., payment module by the fund in the corresponding account of default account identification, can be transferred to the account of beneficiaryIn family, whole payment process is completed.
After the identity identifying method for providing this specification one or more embodiment is applied to payment transaction, carrying outDuring payment, paying party may not need using terminal equipment, and need to only say the account identification of oneself payment account, serverAccording to the account identification and vocal print feature obtained in voice signal, to be authenticated to the identity of user, for paying party userFor, not only without using terminal device, and it is higher without inputting information, the conveniences such as account number cipher respectively.
It is described in detail in addition, being applied to the detailed process in account registering service to identity identifying method, the processFlow diagram is realized as shown in fig. 6, comprising the following steps：
Step S400：User terminal receives voice signal to be certified input by user, and the voice signal is uploaded to clothesBusiness device, the voice signal to be certified are used for the authentication of user during Account Logon；
Terminal device can receive voice signal to be certified input by user by microphone, due to will be according to be certifiedText information in voice signal obtains the account identification of user, and therefore, user, can be with when inputting voice signal to be certifiedDirectly say the account identification of oneself.
Step S402：Server determines the first vocal print feature and text information in the voice signal；
Step S404：Server determines first sound when the definite text information corresponds to default account identificationThe similarity of line feature and default vocal print feature, the default vocal print feature to be gathering with the default account identification pair in advanceThe vocal print feature answered；
Step S406：Server is higher than in the similarity of definite first vocal print feature and the default vocal print feature to be setWhen determining threshold value, determine that the paying party user identity is legal, there is provided the authority operated to the account.
After certification success, then user can be notified to log in success, provide a user the authority operated to the account.Certainly user terminal and server here can be same equipment.
After the identity identifying method for providing this specification one or more embodiment is applied to Account Logon business,When carrying out Account Logon, user may not need inputs account and password respectively, and need to only say the account for the account oneself to be logged inFamily identifies, and server can be recognized the identity of user according to the account identification and vocal print feature obtained in voice signalCard, the information such as account number cipher is inputted without user, convenience is higher respectively.
Based on voiceprint authentication method provided by the embodiments of the present application, the embodiment of the present application also provides corresponding voiceprint dressPut, as shown in fig. 7, the device specifically includes：
Receiving unit 501, receives voice signal to be certified；
First determination unit 502, determines the first vocal print feature and text information in the voice signal；
Second determination unit 503, if the text information corresponds to default account identification, it is determined that first vocal print is specialThe similarity of sign and default vocal print feature, the default vocal print feature are corresponding with the default account identification to gather in advanceVocal print feature；
3rd determination unit 504, if the similarity of first vocal print feature and the default vocal print feature is higher than settingThreshold value, it is determined that certification success, to carry out business operation to the default account identification.
In order to improve the accuracy rate of authentication result, in one embodiment, second determination unit 503, by pre-First trained Application on Voiceprint Recognition model, determines the similarity of first vocal print feature and default vocal print feature；
The Application on Voiceprint Recognition model is obtained by following module trainings：
First training unit 505, the vocal print feature of two different phonetic signals of same user is known as the vocal printThe input of other model, adjusts the parameter of the Application on Voiceprint Recognition model so that the similarity of output is higher than the given threshold；
Second training unit 506, using the vocal print feature of two voice signals of different user as the Application on Voiceprint Recognition mouldThe input of type, adjusts the parameter of the Application on Voiceprint Recognition model so that the similarity of output is not higher than the given threshold.
In one embodiment, the first determination unit 502, carries out speech recognition, described in identification to the voice signalText information in voice signal；
After determining the first vocal print feature and the text information in the voice signal, described device further includes：
4th determination unit 507, when there is the account identification identical with the text information in default account identification storehouse,Determine that the text information corresponds to default account identification.
In one embodiment, described device be applied to business in authentication, the business include it is following at leastIt is a kind of：Payment transaction；Account Logon business；
When the method is applied in payment transaction, business operation is carried out to the default account identification, is specifically included：
Business funds in the corresponding account of the default account identification is transferred in beneficiary account, the business moneyGold is the fund needed for the completion payment transaction；
When the method is applied to Account Logon business, business operation, specific bag are carried out to the default account identificationInclude：
The authority operated to the corresponding account of the default account identification is provided.
In one embodiment, the account identification can be used for communicating.
The embodiment of the present application also provides a kind of account register device, as shown in figure 8, the device specifically includes：
Account identification determination unit 601, determines account identification to be registered；
Collecting unit 602, gathers the vocal print feature in voice signal input by user；
Storage unit 603, the account identification and the vocal print feature are corresponded to as the account information of registration and preserved, itsIn, vocal print feature and text information that the vocal print feature is used in voice signal to be certified carry out authentication, describedVoice signal to be certified is the voice signal for asking certification.
The embodiment of the present application also provides a kind of payment system, including beneficiary terminal and server, wherein：
The beneficiary terminal, receives paying party voice signal to be certified input by user, the voice signal is uploadedTo server, the voice signal to be certified is used for the authentication of paying party user in payment process；
The server, determines the first vocal print feature and text information in the voice signal；
When the definite text information corresponds to default account identification, first vocal print feature and default vocal print are determinedThe similarity of feature, the default vocal print feature are the vocal print feature corresponding with the default account identification gathered in advance；
When the similarity for determining first vocal print feature and the default vocal print feature is higher than given threshold, institute is determinedIt is legal to state paying party user identity, and notifies payment module to complete payment process.
Payment system provided by the embodiments of the present application, when being paid, paying party may not need using terminal equipment, andThe account identification of oneself payment account need to be only said, server can be according to the account identification and vocal print obtained in voice signalFeature, is authenticated the identity of user, for paying party user, not only without using terminal device, but also need not divideNot Shu Ru information, the convenience such as account number cipher it is higher.
Fig. 9 is the structure diagram of one embodiment electronic equipment of the application.Fig. 9 is refer to, in hardware view, the electricitySub- equipment includes processor, alternatively further includes internal bus, network interface, memory.Wherein, memory may include interiorDeposit, such as high-speed random access memory (Random-Access Memory, RAM), it is also possible to further include non-volatile memoriesDevice (non-volatile memory), for example, at least 1 magnetic disk storage etc..Certainly, which is also possible that otherThe required hardware of business.
Processor, network interface and memory can be connected with each other by internal bus, which can be ISA(Industry Standard Architecture, industry standard architecture) bus, PCI (PeripheralComponent Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry StandardArchitecture, expanding the industrial standard structure) bus etc..The bus can be divided into address bus, data/address bus, control alwaysLine etc..For ease of representing, only represented in Fig. 9 with a four-headed arrow, it is not intended that an only bus or a type ofBus.
Memory, for storing program.Specifically, program can include program code, and said program code includes calculatingMachine operational order.Memory can include memory and nonvolatile memory, and provide instruction and data to processor.
Processor reads corresponding computer program into memory and then runs from nonvolatile memory, in logical layerVoiceprint authentication apparatus is formed on face.Processor, performs the program that memory is stored, and specifically for performing following operation：
Receive voice signal to be certified；
Determine the first vocal print feature and the text information in the voice signal；
If the text information corresponds to default account identification, it is determined that first vocal print feature and default vocal print featureSimilarity, the default vocal print feature is the vocal print feature corresponding with the default account identification gathered in advance；
If the similarity of first vocal print feature and the default vocal print feature is higher than given threshold, it is determined that certification intoWork(, to carry out business operation to the default account identification.
The method that voiceprint processing unit disclosed in the above-mentioned embodiment illustrated in fig. 7 such as the application performs can be applied to locateManage in device, or realized by processor.Processor is probably a kind of IC chip, has the disposal ability of signal.In realityDuring existing, each step of the above method can pass through the integrated logic circuit of the hardware in processor or the finger of software formOrder is completed.Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital SignalProcessor, DSP), it is application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), existingField programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, divideVertical door or transistor logic, discrete hardware components.It can realize or perform and is in the embodiment of the present application disclosed eachMethod, step and logic diagram.General processor can be microprocessor or the processor can also be any conventional placeManage device etc..The step of method with reference to disclosed in the embodiment of the present application, can be embodied directly in hardware decoding processor and performInto, or combined with the hardware in decoding processor and software module and perform completion.Software module can be located at random access memory,This area such as flash memory, read-only storage, programmable read only memory or electrically erasable programmable memory, register maturationIn storage medium.The storage medium is located at memory, and processor reads the information in memory, and above-mentioned side is completed with reference to its hardwareThe step of method.
The electronic equipment can also carry out the method that voiceprint authentication apparatus performs in Fig. 2, and realize voiceprint authentication apparatus in Fig. 2The function of illustrated embodiment, details are not described herein for the embodiment of the present application.
The embodiment of the present application also proposed a kind of computer-readable recording medium, the computer-readable recording medium storage oneA or multiple programs, the one or more program include instruction, which works as is held by the electronic equipment including multiple application programsDuring row, the electronic equipment can be made to perform the method that voiceprint authentication apparatus performs in embodiment illustrated in fig. 7, and specifically for holdingOK：
Receive voice signal to be certified；
Determine the first vocal print feature and the text information in the voice signal；
If the text information corresponds to default account identification, it is determined that first vocal print feature and default vocal print featureSimilarity, the default vocal print feature is the vocal print feature corresponding with the default account identification gathered in advance；
If the similarity of first vocal print feature and the default vocal print feature is higher than given threshold, it is determined that certification intoWork(, to carry out business operation to the default account identification.
The application also provides a kind of electronic equipment, including：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the place when executedManage device and perform following operation：
Determine account identification to be registered；
Gather the vocal print feature in voice signal input by user；
The account identification and the vocal print feature are corresponded to as the account information of registration and preserved, wherein, the vocal printThe vocal print feature and text information that feature is used in voice signal to be certified carry out authentication, the voice letter to be certifiedNumber it is the voice signal for asking certification.
The embodiment of the present application also proposed a kind of computer-readable recording medium, the computer-readable recording medium storageOne or more programs, one or more of programs by the electronic equipment including multiple application programs when being performed so that instituteState electronic equipment and perform following operation：
Determine account identification to be registered；
Gather the vocal print feature in voice signal input by user；
The account identification and the vocal print feature are corresponded to as the account information of registration and preserved, wherein, the vocal printThe vocal print feature and text information that feature is used in voice signal to be certified carry out authentication, the voice letter to be certifiedNumber it is the voice signal for asking certification.
In this specification one or more embodiment, after voice signal to be certified is received, the voice signal is determinedIn the first vocal print feature and text information, if the text information corresponds to default account identification, show the account markKnow the default vocal print feature having been provided with for carrying out voiceprint, then can determine that the first vocal print feature and default vocal print are specialThe similarity of sign, if the similarity of the first vocal print feature and default vocal print feature is higher than given threshold, it is determined that certification success,To carry out business operation to the default account identification.In whole verification process, user says the account identification conduct of oneselfAfter voice signal to be certified, the account of user can be positioned according to the text information in voice signal input by user, thenVocal print feature in voice messaging is authenticated the legitimacy of user, and for a user, by saying the account of oneselfFamily identifies, you can completes certification, convenience is higher.
It should be noted that in the 1990s, it is hardware that the improvement for a technology, which can be distinguished clearly,On improvement (for example, improvement to circuit structures such as diode, transistor, switches) or improvement on software (for methodThe improvement of flow).However, with the development of technology, the improvement of current many method flows can be considered as hardware circuitStructure directly improves.Designer is nearly all obtained corresponding by the way that improved method flow is programmed into hardware circuitHardware circuit.Therefore, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, canProgrammed logic device (Programmable Logic Device, PLD) (such as field programmable gate array (FieldProgrammable Gate Array, FPGA)) it is exactly such a integrated circuit, its logic function is by user to device programmingTo determine.Voluntarily programmed by designer a digital display circuit " integrated " on a piece of PLD, without asking chip manufacturingManufacturer designs and makes dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, thisProgramming also uses " logic compiler (logic compiler) " software instead to realize mostly, it is used when being write with program developmentSoftware compiler is similar, and the source code before compiling also write by handy specific programming language, this is referred to as hardPart description language (Hardware Description Language, HDL), and HDL is also not only a kind of, but have manyKind, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera HardwareDescription Language)、Confluence、CUPL(Cornell University ProgrammingLanguage)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM, RHDL (Ruby Hardware Description Language) etc., most generally use VHDL at present(Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art, which also will be apparent to the skilled artisan that, only needs that slightly programming in logic is simultaneously with above-mentioned several hardware description languages by method flowIt is programmed into integrated circuit, it is possible to be readily available the hardware circuit for realizing the logical method flow.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processingThe computer for the computer readable program code (such as software or firmware) that device and storage can be performed by (micro-) processor canRead medium, logic gate, switch, application-specific integrated circuit (Application Specific Integrated Circuit,ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller include but not limited to following microcontrollerDevice：ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are depositedMemory controller is also implemented as a part for the control logic of memory.It is also known in the art that except withPure computer readable program code mode is realized beyond controller, can be made completely by the way that method and step is carried out programming in logicController is obtained in the form of logic gate, switch, application-specific integrated circuit, programmable logic controller (PLC) and embedded microcontroller etc. to come in factExisting identical function.Therefore this controller is considered a kind of hardware component, and various to being used for realization for including in itThe device of function can also be considered as the structure in hardware component.Or even, the device for being used for realization various functions can be regardedFor either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates, can specifically be realized by computer chip or entity,Or realized by having the function of certain product.One kind typically realizes that equipment is computer.Specifically, computer for example may be usedThink personal computer, laptop computer, cell phone, camera phone, smart phone, personal digital assistant, media playIt is any in device, navigation equipment, electronic mail equipment, game console, tablet PC, wearable device or these equipmentThe combination of equipment.
For convenience of description, it is divided into various units during description apparatus above with function to describe respectively.Certainly, this is being implementedThe function of each unit can be realized in same or multiple softwares and/or hardware during application.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer programProduct.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardwareApply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or moreThe computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program productFigure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagramThe combination of flow and/or square frame in journey and/or square frame and flowchart and/or the block diagram.These computer programs can be providedThe processors of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produceA raw machine so that the instruction performed by computer or the processor of other programmable data processing devices, which produces, to be used in factThe device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spyDetermine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring toMake the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram orThe function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that countedSeries of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer orThe instruction performed on other programmable devices is provided and is used for realization in one flow of flow chart or multiple flows and/or block diagram oneThe step of function of being specified in a square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, netNetwork interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/orThe forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Memory is computer-readable mediumExample.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any methodOr technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), movesState random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasableProgrammable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatusOr any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to hereinMachine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludabilityComprising so that process, method, commodity or equipment including a series of elements not only include those key elements, but also wrappingInclude other elements that are not explicitly listed, or further include for this process, method, commodity or equipment it is intrinsic willElement.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including describedAlso there are other identical element in the process of element, method, commodity or equipment.
The application can be described in the general context of computer executable instructions, such as programModule.Usually, program module includes performing particular task or realizes routine, program, object, the group of particular abstract data typePart, data structure etc..The application can also be put into practice in a distributed computing environment, in these distributed computing environment, byTask is performed and connected remote processing devices by communication network.In a distributed computing environment, program module can be withIn the local and remote computer-readable storage medium including storage device.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodimentDivide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for systemFor applying example, since it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the methodPart explanation.
The foregoing is merely embodiments herein, is not limited to the application.For those skilled in the artFor, the application can have various modifications and variations.All any modifications made within spirit herein and principle, be equalReplace, improve etc., it should be included within the scope of claims hereof.