WO2019085575A1

WO2019085575A1 - Voiceprint authentication method and apparatus, and account registration method and apparatus

Info

Publication number: WO2019085575A1
Application number: PCT/CN2018/099559
Authority: WO
Inventors: 黄良洪
Original assignee: 阿里巴巴集团控股有限公司; 黄良洪
Priority date: 2017-11-02
Filing date: 2018-08-09
Publication date: 2019-05-09
Also published as: CN108040032A; TW201918920A; TWI759536B

Abstract

Disclosed is a voiceprint authentication method. The method comprises: after a voice signal to be authenticated is received, determining a first voiceprint feature and character information in the voice signal; determining the similarity between the first voiceprint feature and a pre-set voiceprint feature if the character information corresponds to a pre-set account identifier, which indicates that the account identifier has been provided with a pre-set voiceprint feature for voiceprint authentication; and determining that the authentication is successful if the similarity between the first voiceprint feature and the pre-set voiceprint feature is greater than a set threshold, so as to perform a service operation on the pre-set account identifier. Also disclosed are a voiceprint authentication apparatus, and an account registration method and apparatus.

Description

Voiceprint authentication method, account registration method and device

Technical field

The present invention relates to the field of computer technology, and in particular, to a voiceprint authentication method and device, an account registration method and device, a payment method and system, and to an electronic device and a computer readable storage medium.

Background technique

In many business scenarios, the identity of the user needs to be authenticated to determine that the user is a legitimate user. For example, when the account is logged in, the user needs to input the account password to determine whether the user has the operation authority. In the payment service, the user needs to input the payment password to determine that the user is a legitimate user.

When performing identity authentication, you need to obtain the user's account ID and authentication information. For example, when the account is logged in, the user needs to enter the account ID and password separately, and then check whether the account ID and password match. When paying, the user needs to first You can complete the payment by logging in to the account on the terminal device and then entering the payment password for identity authentication.

That is to say, in the prior art, when the user is authenticated, the user needs to perform operations such as inputting an account and a password, and the convenience is low.

Summary of the invention

The embodiment of the present application provides a voiceprint authentication method for solving the problem of low convenience when authenticating a user.

The embodiments of the present application adopt the following technical solutions:

A method of voiceprint authentication, comprising:

Receiving a voice signal to be authenticated;

Determining a first voiceprint feature and text information in the voice signal;

If the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired corresponding to the preset account identifier Voiceprint characteristics;

If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the authentication is successful, performing a service operation on the preset account identifier.

The embodiment of the present application further provides an account registration method for solving the problem of low convenience when authenticating a user.

An account registration method, including:

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

And correspondingly storing the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is configured to perform identity authentication according to voiceprint features and text information in a voice signal to be authenticated, the voice to be authenticated The signal is a voice signal used to request authentication.

The embodiment of the present application further provides a payment method for solving the problem of low convenience when authenticating a user.

A payment method comprising:

The payee terminal receives the to-be-authenticated voice signal input by the payer user, and uploads the voice signal to the server, where the to-be-authenticated voice signal is used for identity authentication of the payer user in the payment process;

The server determines a first voiceprint feature and text information in the voice signal;

And determining, by the server, the similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired with the preset account. Identify corresponding voiceprint features;

When determining that the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, the server determines that the payer user identity is legal, and notifies the payment module to complete the payment process.

The embodiment of the present application further provides a voiceprint authentication device, which is used to solve the problem of low convenience when authenticating a user.

A voiceprint authentication device comprising:

Receiving unit, receiving a voice signal to be authenticated;

a first determining unit, configured to determine a first voiceprint feature and text information in the voice signal;

a second determining unit, if the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, the preset voiceprint feature being pre-captured and The voiceprint feature corresponding to the preset account identifier;

And a third determining unit, if the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the authentication is successful, to perform a service operation on the preset account identifier.

The embodiment of the present application further provides an electronic device, which solves the problem of low convenience when authenticating a user.

An electronic device comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to perform the following operations:

Receiving a voice signal to be authenticated;

The embodiment of the present application further provides a computer readable storage medium, which solves the problem of low convenience when authenticating a user.

A computer readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including a plurality of applications, causing the electronic device to perform the following operations :

Receiving a voice signal to be authenticated;

The embodiment of the present application further provides an account registration device for solving the problem of low convenience when authenticating a user.

An account registration device, comprising:

An account identifier determining unit that determines an account identifier to be registered;

The collecting unit collects the voiceprint feature in the voice signal input by the user;

a storage unit, configured to store the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is configured to perform identity authentication according to voiceprint features and text information in a voice signal to be authenticated, The voice signal to be authenticated is a voice signal for requesting authentication.

An electronic device comprising:

Processor;

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

The embodiment of the present application further provides a payment system for solving the problem of low convenience when authenticating a user.

A payment system comprising a payee terminal and a server, wherein:

Receiving, by the payee terminal, a voice signal to be authenticated input by a user of the paying party, and uploading the voice signal to a server, where the voice signal to be authenticated is used for identity authentication of a payer user in the payment process;

Determining, by the server, a first voiceprint feature and text information in the voice signal;

When determining that the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, the preset voiceprint feature being pre-acquired and the preset account identifier Corresponding voiceprint features;

When it is determined that the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the payer user identity is legal, and notifying the payment module to complete the payment process.

The above at least one technical solution adopted by the embodiment of the present application can achieve the following beneficial effects:

After receiving the to-be-authenticated speech signal, determining a first voiceprint feature and text information in the voice signal, if the text information corresponds to a preset account identifier, indicating that the account identifier has been set for voiceprint authentication The preset voiceprint feature can determine the similarity between the first voiceprint feature and the preset voiceprint feature. If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, the authentication is determined to be successful. To perform a business operation on the preset account identifier. During the entire authentication process, after the user utters his or her account identifier as the voice signal to be authenticated, the user can locate the user's account according to the text information in the voice signal input by the user, and then legally authenticate the user according to the voiceprint feature in the voice information. Sexually authenticated, and for the user, by saying his or her account ID, the authentication can be completed, and the convenience is high.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the present application, and are intended to be a part of this application. In the drawing:

1 is a schematic diagram of an interaction process of an authentication method provided by the present application;

2 is a schematic flowchart of an implementation process of an account registration method provided by the present application;

3 is a schematic diagram of an implementation process of a voiceprint authentication method provided by the present application;

4 is a schematic diagram of an implementation scenario of a voiceprint authentication method provided by the present application;

FIG. 5 is a schematic diagram of an implementation process of a voiceprint authentication method provided by the present application; FIG.

6 is a schematic diagram of an implementation process of a voiceprint authentication method provided by the present application;

FIG. 7 is a schematic structural diagram of a voiceprint authentication apparatus provided by the present application; FIG.

FIG. 8 is a schematic structural diagram of an account registration apparatus provided by the present application;

FIG. 9 is a schematic structural diagram of an electronic device of an account voiceprint authentication apparatus provided by the present application.

Detailed ways

The technical solutions of the present application will be clearly and completely described in the following with reference to the specific embodiments of the present application and the corresponding drawings. It is apparent that the described embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

With the development of the Internet technology, the identity of the user is verified in more and more business scenarios to protect the legitimate rights and interests of the user, such as the account login service and the payment service mentioned in the background art. However, the process of identity authentication in the prior art is cumbersome and has low convenience. The payment service is taken as an example to briefly describe the identity authentication process in the prior art.

Please refer to the scenario diagram shown in Figure 1. When making a payment service, the payer needs to log in to the payer's account on the payment device. When logging in, the payer user will enter the account and login password on the payment device, and then the server passes the authentication. After that, the payer device obtains the payment information (receipt account number, amount, etc.) of the payee, generates a payment interface, and then the payer user inputs the payment password on the payment device, and after the server passes the authentication, the payment service is completed. In this process, the user needs to input the account number, login password, payment password and other information on the payment device, which is less convenient.

In one or more embodiments of the present specification, the user identity can be authenticated by voiceprint, which improves the convenience of identity authentication. Before voiceprint authentication through voiceprint, the voiceprint information of the user can be pre-acquired as voiceprint. As a template for comparison during authentication, for ease of description, the voiceprint feature corresponding to the account identifier collected in advance is referred to as a preset voiceprint feature. Before the detailed description of the voiceprint authentication process in one or more embodiments of the present specification, the process of the preset voiceprint feature collection in one or more embodiments of the present specification will be described in detail below.

For convenience of description, in one or more embodiments of the present specification, the execution body of the preset voiceprint feature collection method may be a server, and the implementation manner of the method is described by taking the execution entity as a server as an example. It can be understood that the execution subject of the method is only an exemplary description of the server, and should not be construed as limiting the method.

When the preset voiceprint feature is collected, it may be performed when the account is registered, and the implementation flow diagram of the voiceprint collection during the account registration is as shown in FIG. 2, and includes the following steps:

Step S100: determining an account identifier to be registered;

The account identifier can be used to identify the user's account, such as an account number, such as a bank card number, which is an account identifier of the user's bank account.

The account identifier to be registered may be manually input by the user through the terminal device, for example, the user inputs his mobile phone number as the account identifier to be registered, or the user may input the text in the format specified by the account management system as the account identifier. Then, after receiving the account identifier input by the user through the terminal device, the account management system of the server determines whether the account identifier has been registered, and if it has been registered, prompts the user to change the account identifier. If the account identifier input by the user is the mobile phone number, the mobile phone number may also be verified by SMS to determine that the user actually owns the mobile phone number.

The account identifier to be registered may also be automatically assigned by the account management system of the server. For example, when the user registers an account, the account management system may automatically assign a certain identifier to the user according to a certain rule as the account identifier of the user.

Step S102: collecting voiceprint features in the voice signal input by the user;

When registering an account, the user can register through a terminal device (such as a mobile phone, a tablet, etc.), then when collecting a voice signal, the user's voice signal can be collected through the microphone of the user terminal device, and then the terminal device uploads the voice signal to The server, the server gets the voice signal input by the user.

After the voice signal is acquired, the voiceprint feature in the voice signal can be extracted. The voiceprint feature in one or more embodiments of the present specification may include acoustic features in the voice signal, such as spectrum, cepstrum, formant, Features such as pitch and reflection coefficient; may also include lexical features of the language in the speech signal, such as the relevance of words in the context, the association of phonemes in the context; may also include prosodic features in the speech signal; may also include the language in the speech signal The characteristics of the language, dialect and accent are not repeated here.

It should be noted that, in practical applications, the user may be required to upload multiple voice signals, extract voiceprint features in multiple voice signals, and then take the average of multiple voiceprint features as preset voiceprint features to prevent extraction only. Voiceprint features in a speech signal may be inaccurate.

Step S104: Corresponding the account identifier and the voiceprint feature as registered account information, so as to perform identity authentication according to the voiceprint feature and the text information in the voice signal to be authenticated, where the voice signal to be authenticated is used for requesting Certified voice signal.

After extracting the voiceprint feature of the voice signal, the server can use the extracted voiceprint feature as the preset voiceprint feature as the basis for the voiceprint authentication. For the convenience of authentication, the account identifier and the extracted voiceprint feature can be selected. Corresponding to save, for example, can be saved as the same data record.

When the account identifier and the voiceprint feature are saved as registered account information, they may be saved in an account identifier library for storing the account identifier and the voiceprint feature, so that after receiving the text information, the account identifier library may be used. Determine whether the text message is an already registered account.

In one or more embodiments of the present specification, the text information may be a written symbol for recording a specific thing and simplifying an image. In a computer, the text information is usually in the form of text. The text information may be composed of, for example, at least one of Chinese characters, Arabic numerals, letters, and the like.

In addition, when performing voiceprint collection, voice recording can also be performed on registered accounts. For example, although some accounts already have authentication information such as passwords, but the user desires to add voiceprint authentication information, then The user's voiceprint can be collected again as the basis for voiceprint authentication. For the specific collection process, refer to the related description in this application, and details are not described herein again.

After introducing the acquisition process of the preset voiceprint features in one or more embodiments of the present specification, the voiceprint authentication process in one or more embodiments of the present specification will be described in detail below.

For convenience of description, in one or more embodiments of the present specification, the execution body of the voiceprint authentication method may be a server, and the implementation manner of the method is described by taking the execution subject as a server as an example. It can be understood that the execution subject of the method is only an exemplary description of the server, and should not be construed as limiting the method.

In one or more embodiments of the present specification, a schematic diagram of an implementation process of a voiceprint authentication method is shown in FIG. 3, and includes the following steps:

Step S200: Receive a voice signal to be authenticated;

For convenience of description, a voice signal for requesting authentication is referred to herein as a voice signal to be authenticated. For example, when a user logs in an account, a voice signal is input through the terminal device, and the voice signal is a voice signal to be authenticated; when the user requests payment, a voice signal is input to request the server to verify the validity of the user identity. Then the voice signal is also the voice signal to be authenticated.

The voice signal to be authenticated may be collected by the terminal device through the microphone, and then the terminal device may upload the collected voice signal to the server to request the server to authenticate the voice signal. For example, if a user logs in an account through a smart phone, the smart phone can collect the voice signal through the microphone and then upload it to the server, requesting the server to authenticate the voice signal.

Step S202: determining a first voiceprint feature and text information in the voice signal;

When determining the voiceprint feature in the received voice signal to be authenticated, the voiceprint feature in the voice signal can be extracted, and in order to facilitate distinguishing from the previously stored voiceprint feature, the voice in the voice signal to be authenticated here The pattern feature is referred to as the first voiceprint feature. For details of the voiceprint feature, refer to the related description in step S102, and details are not described herein again.

When determining the received text information in the to-be-authenticated speech signal, the speech signal may be speech-recognized to identify the text information in the speech signal. Speech recognition can recognize the language characters in the voice input by the user. For example, if the user's voice says "123456", the text "123456" can be obtained by voice recognition.

Step S204: If the text information corresponds to the preset account identifier, determine a similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired and the preset The voiceprint feature corresponding to the account identifier;

After the text information is recognized, it can be determined whether the text information corresponds to the preset account identifier. Specifically, it can be determined that the account identifier in the preset account identifier library is the same as the text information, if the account identifier library is preset. If there is an account identifier that is the same as the text information, it is determined that the text information corresponds to the preset account identifier. For example, if the text information is “123456”, then if the account identifier “123456” is also present in the preset account identifier library, the text information may be considered to correspond to the preset account identifier.

It should be noted that some information that does not belong to the account identifier may exist in the text information, which may be caused by the user saying other content when inputting the voice signal to be authenticated, or because the user inputs the voice signal to be authenticated. When the surrounding environment is too noisy, for example, the text message is "123456 is good". Then, the information belonging to the account identification format in the text information may be extracted, and then the information belonging to the account identification format is compared to the preset account identifier. If yes, the text information may also be considered to correspond to the preset account identifier.

For example, if the information in the account identification format is a number, then you can extract "123456" in "123456 is good", and then query whether "123456" corresponds to the default account identifier. If it is, you can also think that "123456 is good. "corresponds to the default account identifier

The account identifier can be used for communication, such as a mobile phone number, a mailbox, and the like.

If the text information does not correspond to the account identifier, a notification is sent to the user terminal device, requesting the user to re-enter the voice signal to be authenticated.

If the text information corresponds to the preset account identifier, it indicates that the account corresponding to the text information is already an account in which the preset voiceprint feature is pre-collected, and then the voiceprint authentication process can be performed. When the voiceprint authentication is performed, the similarity between the first voiceprint feature and the preset voiceprint feature may be calculated, and according to the similarity, whether the user who inputs the voice signal to be authenticated is legal is determined.

Step S206: If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determine that the authentication is successful, to perform a service operation on the preset account identifier.

After the similarity between the first voiceprint feature and the preset voiceprint feature is obtained, whether the authentication is successful can be determined by comparing the similarity with a preset threshold. If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, it may be determined that the authentication is successful, if the similarity between the first voiceprint feature and the preset voiceprint feature is not higher than a set threshold. , you can be sure that the authentication failed.

For example, if the similarity determined in step S204 is 99.45% and the set threshold is 90%, then the authentication success can be determined.

In one or more embodiments of the present specification, when determining the similarity between the first voiceprint feature and the preset voiceprint feature, it may be determined by a pre-trained voiceprint recognition model. The voiceprint recognition model can take two voiceprint features as input, and obtain the similarity of the two voiceprint features after calculating the parameters in the model.

When training the voiceprint recognition model, the parameters in the model are adjusted so that the model can more accurately identify the same user based on the voiceprint feature. The specific training process of the voiceprint recognition model is described in detail below.

Since the voiceprint feature of the same user can be considered to be constant, when the voiceprint feature of two different voice signals of the same user is input into the voiceprint recognition model, the similarity should be 100%, of course, In practical applications, errors can be allowed to exist, so as long as the similarity is higher than a certain threshold. Then, the voiceprint feature of the two different voice signals of the same user can be used as the input of the voiceprint recognition model, and then the parameters of the voiceprint recognition model are adjusted such that the similarity of the output is higher than the set threshold.

In addition, since the voiceprint features of different users can be considered different, when the voiceprint features of two voice signals of different users are input into the voiceprint recognition model, the similarity obtained should be no higher than the setting. Threshold. Then, the voiceprint feature of the two voice signals of different users can be used as the input of the voiceprint recognition model, and the parameters of the voiceprint recognition model can be adjusted so that the similarity of the output is not higher than the set threshold.

When training the voiceprint recognition model, a large number of samples can be used to train the voiceprint recognition model in the above manner. The greater the number of training samples, the higher the accuracy of the voiceprint recognition model.

The voiceprint authentication method provided in one or more embodiments of the present specification determines a first voiceprint feature and text information in the voice signal after receiving the voice signal to be authenticated, if the text information corresponds to a preset The account identifier indicates that the account identifier has been set with a preset voiceprint feature for performing voiceprint authentication, and then the similarity between the first voiceprint feature and the preset voiceprint feature can be determined, if the first voiceprint feature and the preset If the similarity of the voiceprint feature is higher than the set threshold, it is determined that the authentication is successful, and the business operation is performed on the preset account identifier. During the entire authentication process, after the user utters his or her account identifier as the voice signal to be authenticated, the user can locate the user's account according to the text information in the voice signal input by the user, and then legally authenticate the user according to the voiceprint feature in the voice information. Sexually authenticated, and for the user, by saying his or her account ID, the authentication can be completed, and the convenience is high.

The identity authentication method provided by one or more embodiments of the present specification may be applied to at least one of the following services: a payment service; an account login service.

The following is a detailed description of the two services separately. The technical details that are not introduced in the implementation of these two services can be referred to the related descriptions above.

Obviously, the identity authentication method can also be applied to other businesses, which are not enumerated here. It is within the scope of the present application to enable any other embodiment obtained by the person skilled in the art to apply the identity authentication method to other services without creative work.

First, the specific process of applying the identity authentication method to the payment service is described in detail. Please refer to the scenario diagram shown in Figure 4. The implementation process of the process is shown in Figure 5, including the following steps:

Step S300: The payee terminal receives the to-be-authenticated voice signal input by the payer user, and uploads the voice signal to the server, where the to-be-authenticated voice signal is used for identity authentication of the payer user in the payment process;

The payee terminal can receive the voice signal to be authenticated input by the user of the paying party through the microphone. Since the user's account identifier is obtained according to the text information in the voice signal to be authenticated, the user can directly input the voice signal to be authenticated. Say your own account ID.

The payee terminal can display payment information (such as the amount of the payment) so that the payer knows the information to be paid.

The payee terminal may be an offline cashier terminal of the merchant, that is, an identity authentication method in one or more embodiments of the present specification, which may be applied to an offline payment scenario.

Step S302: The server determines a first voiceprint feature and text information in the voice signal.

Step S304: The server determines, when the text information corresponds to the preset account identifier, the similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is a pre-collected relationship. Describe the voiceprint feature corresponding to the preset account identifier;

Step S306: When determining that the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, the server determines that the payer user identity is legal, and notifies the payment module to complete the payment process.

After determining that the payer user identity is legal, the business funds in the payer account can be transferred to the payee account, where the business funds can be the funds needed to complete the payment service. Of course, the process of completing the payment can be performed by the payment module, that is, the payment module can transfer the funds in the account corresponding to the preset account identifier to the account of the payee to complete the entire payment process.

After the identity authentication method provided by one or more embodiments of the present specification is applied to the payment service, when the payment is made, the payer can use the terminal device without saying the account identifier of the payment account, and the server can The account identifier and the voiceprint feature obtained in the voice signal authenticate the user's identity. For the payer user, not only does it need to use the terminal device, but also does not need to input the account password and other information separately, and the convenience is high.

In addition, the specific process of applying the identity authentication method to the account login service is described in detail. The process flow of the process is shown in FIG. 6 and includes the following steps:

Step S400: The user terminal receives the voice signal to be authenticated input by the user, and uploads the voice signal to the server, where the voice signal to be authenticated is used for identity authentication of the user in the account login process;

The terminal device can receive the voice signal to be authenticated input by the user through the microphone. Since the user's account identifier is obtained according to the text information in the voice signal to be authenticated, the user can directly speak his/her own voice when inputting the voice signal to be authenticated. Account ID.

Step S402: The server determines a first voiceprint feature and text information in the voice signal.

Step S404: The server determines a similarity between the first voiceprint feature and the preset voiceprint feature when the text information is determined to correspond to the preset account identifier, where the preset voiceprint feature is pre-acquired and The voiceprint feature corresponding to the preset account identifier;

Step S406: When determining that the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, the server determines that the payer user identity is legal, and provides permission to operate the account.

After the authentication is successful, the user can be notified that the login is successful, and the user is provided with the right to operate the account. Of course, the user terminal and the server here can be the same device.

After the identity authentication method provided by one or more embodiments of the present specification is applied to the account login service, when the account is logged in, the user does not need to input the account and password separately, but only needs to say the account identifier of the account that he wants to log in. The server can authenticate the identity of the user according to the account identifier and the voiceprint feature obtained in the voice signal, and the user does not need to input the account password and other information separately, and the convenience is high.

Based on the voiceprint authentication method provided by the embodiment of the present application, the embodiment of the present application further provides a corresponding voiceprint authentication device. As shown in FIG. 7, the device specifically includes:

The receiving unit 501 receives the voice signal to be authenticated;

The first determining unit 502 is configured to determine a first voiceprint feature and text information in the voice signal;

a second determining unit 503, if the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is a pre-collected Describe the voiceprint feature corresponding to the preset account identifier;

The third determining unit 504 determines that the authentication is successful if the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, to perform a service operation on the preset account identifier.

In order to improve the accuracy of the authentication result, in an implementation manner, the second determining unit 503 determines the similarity between the first voiceprint feature and the preset voiceprint feature by using the pre-trained voiceprint recognition model. ;

The voiceprint recognition model is obtained by training the following units:

The first training unit 505 adjusts the parameters of the voiceprint recognition model by using voiceprint features of two different voice signals of the same user as input of the voiceprint recognition model, so that the similarity of the output is higher than the setting. Threshold value

The second training unit 506 uses the voiceprint features of the two voice signals of different users as the input of the voiceprint recognition model, and adjusts the parameters of the voiceprint recognition model so that the similarity of the output is not higher than the setting. Threshold.

In an embodiment, the first determining unit 502 performs voice recognition on the voice signal to identify text information in the voice signal;

After determining the first voiceprint feature and the text information in the voice signal, the device further includes:

The fourth determining unit 507 determines that the text information corresponds to the preset account identifier when the same account identifier as the text information exists in the preset account identifier library.

In an embodiment, the apparatus is applied to identity authentication in a service, where the service includes at least one of the following: a payment service; an account login service;

When the method is applied to the payment service, performing a service operation on the preset account identifier, specifically:

Transferring the business funds in the account corresponding to the preset account identifier to the payee account, where the business funds are funds required to complete the payment service;

When the method is applied to the account login service, performing the service operation on the preset account identifier, specifically:

Providing permission to operate an account corresponding to the preset account identifier.

In one embodiment, the account identification is available for communication.

The embodiment of the present application further provides an account registration device, as shown in FIG. 8 , the device specifically includes:

The account identifier determining unit 601 determines an account identifier to be registered;

The collecting unit 602 is configured to collect voiceprint features in the voice signal input by the user;

The storage unit 603 saves the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is used for identity authentication according to voiceprint features and text information in the voice signal to be authenticated. The authentication voice signal is referred to as a voice signal for requesting authentication.

The embodiment of the present application further provides a payment system, including a payee terminal and a server, where:

In the payment system provided by the embodiment of the present application, when the payment is made, the paying party may not need to use the terminal device, but only the account identifier of the payment account, and the server may obtain the account identifier and the voiceprint feature obtained in the voice signal. To authenticate the user's identity, the payer user does not need to use the terminal device, and does not need to input the account password and other information separately, and the convenience is high.

FIG. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to FIG. 9, at the hardware level, the electronic device includes a processor, optionally including an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Of course, the electronic device may also include hardware required for other services.

The processor, the network interface, and the memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended) Industry Standard Architecture, extending the industry standard structure) bus. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one double-headed arrow is shown in Figure 9, but it does not mean that there is only one bus or one type of bus.

Memory for storing programs. In particular, the program can include program code, the program code including computer operating instructions. The memory can include both memory and non-volatile memory and provides instructions and data to the processor.

The processor reads the corresponding computer program from the non-volatile memory into memory and then runs to form a voiceprint authentication device at a logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

Receiving a voice signal to be authenticated;

The method performed by the voiceprint authentication processing apparatus disclosed in the embodiment shown in FIG. 7 of the present application may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or an instruction in a form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or may be a digital signal processor (DSP), dedicated integration. Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component. The methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor. The software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.

The electronic device can also perform the method performed by the voiceprint authentication device in FIG. 2, and implement the functions of the voiceprint authentication device in the embodiment shown in FIG. 2, which is not described herein again.

The embodiment of the present application further provides a computer readable storage medium storing one or more programs, the one or more programs including instructions that are executed by an electronic device including a plurality of applications The electronic device can be caused to perform the method performed by the voiceprint authentication apparatus in the embodiment shown in FIG. 7, and is specifically configured to perform:

Receiving a voice signal to be authenticated;

The application also provides an electronic device, including:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to:

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

The embodiment of the present application further provides a computer readable storage medium storing one or more programs, when the one or more programs are executed by an electronic device including a plurality of applications, The electronic device performs the following operations:

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

In one or more embodiments of the present specification, after receiving the to-be-authenticated speech signal, determining a first voiceprint feature and text information in the voice signal, and if the text information corresponds to a preset account identifier, indicating that the The account identifier has been set with a preset voiceprint feature for voiceprint authentication, and then the similarity between the first voiceprint feature and the preset voiceprint feature can be determined, if the similarity between the first voiceprint feature and the preset voiceprint feature If the threshold is exceeded, it is determined that the authentication is successful, and the business operation is performed on the preset account identifier. During the entire authentication process, after the user utters his or her account identifier as the voice signal to be authenticated, the user can locate the user's account according to the text information in the voice signal input by the user, and then legally authenticate the user according to the voiceprint feature in the voice information. Sexually authenticated, and for the user, by saying his or her account ID, the authentication can be completed, and the convenience is high.

It should be noted that in the 1990s, the improvement of a technology can be clearly distinguished by hardware improvements (for example, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (for method flow). improvement of). However, as technology advances, many of today's method flow improvements can be seen as direct improvements in hardware circuit architecture. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented by hardware entity modules. For example, a Programmable Logic Device (PLD) (e.g., Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers program themselves to "integrate" a digital system on a single PLD without having to ask the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, today, instead of manually making integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in programming development, but before compiling The original code has to be written in a specific programming language. This is called the Hardware Description Language (HDL). HDL is not the only one, but there are many kinds, such as ABEL (Advanced Boolean Expression Language). AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., are currently the most commonly used VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be apparent to those skilled in the art that the hardware flow for implementing the logic method flow can be easily obtained by simply programming the method flow into the integrated circuit with a few hardware description languages.

The controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor. In the form of logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic. Those skilled in the art will also appreciate that in addition to implementing the controller in purely computer readable program code, the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding. The form of a microcontroller or the like to achieve the same function. Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component. Or even a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.

The system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

For the convenience of description, the above devices are described separately by function into various units. Of course, the functions of each unit may be implemented in the same software or software and/or hardware when implementing the present application.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device including the element.

The application can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The above description is only an embodiment of the present application and is not intended to limit the application. Various changes and modifications can be made to the present application by those skilled in the art. Any modifications, equivalents, improvements, etc. made within the spirit and scope of the present application are intended to be included within the scope of the appended claims.

Claims

A method of voiceprint authentication, comprising:

Receiving a voice signal to be authenticated;

Determining a first voiceprint feature and text information in the voice signal;

If the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired corresponding to the preset account identifier Voiceprint characteristics;

If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the authentication is successful, performing a service operation on the preset account identifier.
The method of claim 1, determining the similarity between the first voiceprint feature and the preset voiceprint feature, comprising:

Determining the similarity between the first voiceprint feature and the preset voiceprint feature by using a pre-trained voiceprint recognition model;

The voiceprint recognition model is trained by the following methods:

Using the voiceprint feature of two different voice signals of the same user as an input of the voiceprint recognition model, adjusting parameters of the voiceprint recognition model such that the similarity of the output is higher than the set threshold;

The voiceprint features of the two voice signals of different users are used as inputs of the voiceprint recognition model, and the parameters of the voiceprint recognition model are adjusted such that the similarity of the output is not higher than the set threshold.
The method of claim 1, determining a first voiceprint feature and text information in the voice signal, comprising:

Performing voice recognition on the voice signal to identify text information in the voice signal;

After determining the first voiceprint feature and the text information in the voice signal, the method further includes:

If the account identifier in the preset account identifier library is the same as the text information, it is determined that the text information corresponds to the preset account identifier.
The method according to any one of claims 1 to 3, wherein the method is applied to identity authentication in a service, the service comprising at least one of the following:

Payment service; account login service;

When the method is applied to the payment service, performing a service operation on the preset account identifier, specifically:

Transferring the business funds in the account corresponding to the preset account identifier to the payee account, where the business funds are funds required to complete the payment service;

When the method is applied to the account login service, performing the service operation on the preset account identifier, specifically:

Providing permission to operate an account corresponding to the preset account identifier.
The method of claim 1 wherein said account identification is available for communication.
An account registration method, including:

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

And correspondingly storing the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is configured to perform identity authentication according to voiceprint features and text information in a voice signal to be authenticated, the voice to be authenticated The signal is a voice signal used to request authentication.
A payment method comprising:

The payee terminal receives the to-be-authenticated voice signal input by the payer user, and uploads the voice signal to the server, where the to-be-authenticated voice signal is used for identity authentication of the payer user in the payment process;

The server determines a first voiceprint feature and text information in the voice signal;

And determining, by the server, the similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired with the preset account. Identify corresponding voiceprint features;

When determining that the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, the server determines that the payer user identity is legal, and notifies the payment module to complete the payment process.
The method of claim 7 wherein said payee terminal is a merchant offline cashier terminal.
A voiceprint authentication device comprising:

Receiving unit, receiving a voice signal to be authenticated;

a first determining unit, configured to determine a first voiceprint feature and text information in the voice signal;

a second determining unit, if the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, the preset voiceprint feature being pre-captured and The voiceprint feature corresponding to the preset account identifier;

And a third determining unit, if the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the authentication is successful, to perform a service operation on the preset account identifier.
An electronic device comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to perform the following operations:

Receiving a voice signal to be authenticated;

Determining a first voiceprint feature and text information in the voice signal;

If the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired corresponding to the preset account identifier Voiceprint characteristics;

If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the authentication is successful, performing a service operation on the preset account identifier.
A computer readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including a plurality of applications, causing the electronic device to perform the following operations :

Receiving a voice signal to be authenticated;

Determining a first voiceprint feature and text information in the voice signal;

If the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, where the preset voiceprint feature is pre-acquired corresponding to the preset account identifier Voiceprint characteristics;

If the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the authentication is successful, performing a service operation on the preset account identifier.
An account registration device, comprising:

An account identification determining unit that determines an account identifier to be registered;

The collecting unit collects the voiceprint feature in the voice signal input by the user;

a storage unit, configured to store the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is configured to perform identity authentication according to voiceprint features and text information in a voice signal to be authenticated, The voice signal to be authenticated is a voice signal for requesting authentication.
An electronic device comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to perform the following operations:

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

And correspondingly storing the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is configured to perform identity authentication according to voiceprint features and text information in a voice signal to be authenticated, the voice to be authenticated The signal is a voice signal used to request authentication.
A computer readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including a plurality of applications, causing the electronic device to perform the following operations :

Determining the account identifier to be registered;

Acquiring a voiceprint feature in a voice signal input by a user;

And correspondingly storing the account identifier and the voiceprint feature as registered account information, wherein the voiceprint feature is configured to perform identity authentication according to voiceprint features and text information in a voice signal to be authenticated, the voice to be authenticated The signal is a voice signal used to request authentication.
A payment system comprising a payee terminal and a server, wherein:

Receiving, by the payee terminal, a voice signal to be authenticated input by a user of the paying party, and uploading the voice signal to a server, where the voice signal to be authenticated is used for identity authentication of a payer user in the payment process;

Determining, by the server, a first voiceprint feature and text information in the voice signal;

When determining that the text information corresponds to the preset account identifier, determining a similarity between the first voiceprint feature and the preset voiceprint feature, the preset voiceprint feature being pre-acquired and the preset account identifier Corresponding voiceprint features;

When it is determined that the similarity between the first voiceprint feature and the preset voiceprint feature is higher than a set threshold, determining that the payer user identity is legal, and notifying the payment module to complete the payment process.