Voiceprint information processing method and device

Abstract

This application provides a voiceprint information processing method and device, which relates to the field of voiceprint payment technology and can also be used in the financial field. The method comprises: generating an original signal sequence based on the voiceprint signal to be identified; performing convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and sending it to a voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal based on the signal convolution sequence. This application can accurately verify the user's voiceprint information to complete legal voiceprint payment.

Description

Technical Field

[0001] The present application relates to the field of voiceprint payment technology and can be used in the financial field. Specifically, it is a method and device for processing voiceprint information. Background Art

[0002] Financial institutions' unified payment platforms can provide payment and clearing services to their customers. Before making payments, these platforms typically authenticate the customer's account. Existing authentication methods include voiceprint verification.

[0003] However, the channel coding technology currently used to transmit voiceprint information over the channel is linear block code. Linear block code has relatively simple encoding and decoding and good closedness, but relatively poor error control. In harsh environments, the signal may be affected and changed, ultimately affecting the authentication effect. Summary of the Invention

[0004] In response to the problems in the prior art, the present application provides a voiceprint information processing method and device that can accurately verify the user's voiceprint information so as to complete legal voiceprint payment.

[0005] To solve the above technical problems, this application provides the following technical solutions:

[0006] In a first aspect, the present application provides a method for processing voiceprint information, comprising:

[0007] Generate an original signal sequence according to the voiceprint signal to be identified;

[0008] The original signal sequence is convolved to obtain a corresponding signal convolution sequence and sent to a voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal according to the signal convolution sequence.

[0009] Furthermore, generating an original signal sequence according to the voiceprint signal to be identified includes:

[0010] Perform analog-to-digital conversion on the voiceprint signal to obtain the original signal sequence.

[0011] Furthermore, performing convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence includes:

[0012] Determine a corresponding sub-generator polynomial according to the original sequence of the signal;

[0013] Determine a corresponding sub-generator according to the sub-generator polynomial;

[0014] Determine a subgenerator polynomial matrix according to the subgenerator;

[0015] The signal convolution sequence is determined according to the original signal sequence and the sub-generator polynomial matrix.

[0016] Furthermore, determining the corresponding sub-generator polynomial according to the original signal sequence includes:

[0017] Inputting the original signal sequence into an adder to obtain a corresponding addition expression;

[0018] The addition expression is input into an encoder to obtain the sub-generator polynomial.

[0019] Furthermore, determining the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix includes:

[0020] The signal original sequence is multiplied by the sub-generator polynomial matrix to obtain the signal convolution sequence.

[0021] In a second aspect, the present application provides a voiceprint information processing method, comprising:

[0022] Receive a signal convolution sequence corresponding to the voiceprint signal to be identified from the client;

[0023] performing voiceprint authentication on the voiceprint signal according to the signal convolution sequence;

[0024] Send an authentication success notification or a re-authentication instruction to the client according to the voiceprint authentication result.

[0025] Furthermore, performing voiceprint authentication on the voiceprint signal according to the signal convolution sequence includes:

[0026] Searching a voiceprint information database for a legal voiceprint signal corresponding to the voiceprint signal;

[0027] The signal convolution sequence is compared with the legal voiceprint signal to obtain the voiceprint authentication result.

[0028] Furthermore, the comparing the signal convolution sequence with the legal voiceprint signal to obtain the voiceprint authentication result includes:

[0029] Comparing the signal convolution sequence with the legal voiceprint signal to obtain the number of difference bits;

[0030] Determine an authentication score based on the number of digits of the difference and a preset threshold;

[0031] The voiceprint authentication result is determined according to the score.

[0032] In a third aspect, the present application provides a voiceprint information processing device, comprising:

[0033] An original sequence generating unit, configured to generate an original signal sequence according to the voiceprint signal to be identified;

[0034] The convolution processing unit is used to perform convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and send it to the voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication according to the signal convolution sequence.

[0035] Furthermore, the original sequence generating unit is used to:

[0036] Perform analog-to-digital conversion on the voiceprint signal to obtain the original signal sequence.

[0037] Furthermore, the convolution processing unit includes:

[0038] A polynomial determination module, configured to determine a corresponding sub-generator polynomial according to the original signal sequence;

[0039] A generator determination module, configured to determine a corresponding sub-generator according to the sub-generator polynomial;

[0040] a matrix determination module, configured to determine a subgenerator polynomial matrix according to the subgenerator;

[0041] The convolution sequence determination module is used to determine the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix.

[0042] Furthermore, the polynomial determination module includes:

[0043] An expression generation submodule, used for inputting the original signal sequence into an adder to obtain a corresponding addition expression;

[0044] The polynomial determination submodule is used to input the addition expression into the encoder to obtain the sub-generator polynomial.

[0045] Furthermore, the convolution sequence determination module is used to:

[0046] The signal original sequence is multiplied by the sub-generator polynomial matrix to obtain the signal convolution sequence.

[0047] In a fourth aspect, the present application provides a voiceprint information processing device, comprising:

[0048] A convolution sequence receiving unit, configured to receive a signal convolution sequence corresponding to a voiceprint signal to be identified from a client;

[0049] a voiceprint authentication unit, configured to perform voiceprint authentication on the voiceprint signal according to the signal convolution sequence;

[0050] The authentication result sending unit is used to send an authentication success notification or a re-authentication instruction to the client according to the voiceprint authentication result.

[0051] Furthermore, the voiceprint authentication unit includes:

[0052] A legal signal search module, configured to search a voiceprint information database for a legal voiceprint signal corresponding to the voiceprint signal;

[0053] The authentication result generating module is used to compare the signal convolution sequence with the legal voiceprint signal to obtain the voiceprint authentication result.

[0054] Furthermore, the voiceprint authentication unit includes:

[0055] A difference bit determination module is used to compare the signal convolution sequence with the legal voiceprint signal to obtain the difference bit number;

[0056] An authentication score determination module, configured to determine an authentication score based on the number of digits of the difference and a preset threshold;

[0057] The voiceprint authentication module is configured to determine the voiceprint authentication result according to the score.

[0058] In a fifth aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the voiceprint information processing method when executing the program.

[0059] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the voiceprint information processing method when executed by a processor.

[0060] In a seventh aspect, the present application provides a computer program product, comprising a computer program / instruction, which implements the steps of the voiceprint information processing method when executed by a processor.

[0061] To address the problems in the existing technology, the voiceprint information processing method and device provided in this application can, after obtaining the voiceprint signal of the user to be identified, perform convolution processing on the voiceprint signal, improving its transmission reliability during channel transmission, reducing the bit error rate, and thus optimizing error control. The convolution-processed voiceprint signal is then compared with the user's legitimate voiceprint signal stored in the database, and a score is scored to determine whether the voiceprint signal of the user to be identified is legitimate, thereby achieving the purpose of accurately verifying the voiceprint in different environmental noise environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 This is one of the flow charts of the voiceprint information processing method in an embodiment of the present application;

[0064] Figure 2 A flow chart of obtaining a signal convolution sequence in an embodiment of the present application;

[0065] Figure 3 This is a flowchart for determining a sub-generator polynomial in an embodiment of the present application;

[0066] Figure 4 This is the second flow chart of the voiceprint information processing method in the embodiment of this application;

[0067] Figure 5 This is one of the flow charts for voiceprint authentication in an embodiment of this application;

[0068] Figure 6 This is the second flow chart of voiceprint authentication in the embodiment of this application;

[0069] Figure 7 This is one of the structural diagrams of the voiceprint information processing device in the embodiment of this application;

[0070] Figure 8 This is a structural diagram of a convolution processing unit in an embodiment of the present application;

[0071] Figure 9 This is a structural diagram of a polynomial determination module in an embodiment of the present application;

[0072] Figure 10 This is the second structural diagram of the voiceprint information processing device in the embodiment of this application;

[0073] Figure 11 This is one of the structural diagrams of the voiceprint authentication unit in the embodiment of this application;

[0074] Figure 12 This is the second structural diagram of the voiceprint authentication unit in the embodiment of this application;

[0075] Figure 13 A schematic diagram of the structure of an electronic device in an embodiment of the present application;

[0076] Figure 14 This is a schematic diagram of an application scenario in an embodiment of the present application;

[0077] Figure 15 This is one of the convolutional coding diagrams in the embodiment of this application;

[0078] Figure 16 This is the second convolutional coding diagram in the embodiment of this application;

[0079] Figure 17 This is the third convolutional coding diagram in the embodiment of this application. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0081] It should be noted that the voiceprint information processing method and device provided in this application can be used in the financial field, and can also be used in any field other than the financial field. The application field of the voiceprint information processing method and device provided in this application is not limited.

[0082] With the increasing popularity of online financial services, an increasing number of payment scenarios are employing authentication methods such as passwords, facial recognition, fingerprints, and voiceprints to ensure the security of funds during the payment process. However, the channel coding technology currently used to transmit voiceprint information over the channel is linear block codes, which have relatively poor error control. In harsh environments, the signal may be affected and distorted, ultimately affecting the effectiveness of authentication.

[0083] In order to solve the problems existing in the prior art, in one embodiment, see Figure 1 In order to accurately verify the user's voiceprint information and complete legal voiceprint payment, this application provides a voiceprint information processing method, including:

[0084] S101: Generate an original signal sequence according to the voiceprint signal to be identified;

[0085] S102: Perform convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and send it to the voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal according to the signal convolution sequence.

[0086] It is understandable that the application scenario of the embodiment of the present application is based on voiceprint recognition technology, see Figure 14As shown. The client 100 includes but is not limited to smart terminals such as personal computers (PCs), tablet computers and mobile phones, which are used to enable customers to complete voiceprint entry and process the voiceprint information entered by customers; that is, to complete steps S101 to S102. The server 200 includes but is not limited to the backend server of the financial institution, which is used to receive the voiceprint information to be identified sent by the client, perform voiceprint authentication on it, and send the authentication result to the client; that is, to complete steps S401 to S403. Figure 4 In one embodiment, a voiceprint information processing method includes:

[0087] S401: Receive a signal convolution sequence corresponding to a voiceprint signal to be identified from a client;

[0088] S402: Perform voiceprint authentication on the voiceprint signal according to the signal convolution sequence;

[0089] S403: Send an authentication success notification or a re-authentication instruction to the client according to the voiceprint authentication result.

[0090] In specific implementation, ① the user first initiates a payment request using the client 100. At this time, a voiceprint verification page will appear on the client 100. This page may display multiple random numbers or other random content, and the user needs to complete reading within a preset time (e.g., within 15 seconds). The following uses random numbers as an example, but this application is not limited to this.

[0091] ② The user can record the corresponding random digital voice information through the microphone on the client 100. The microphone converts the sound information into a signal current. The frequency and amplitude changes of this signal current are exactly the same as those of the sound, "mimicking" the "every move" of the signal, and obtaining an analog signal corresponding to the voiceprint, that is, the voiceprint signal S to be identified. In one embodiment, generating the original signal sequence based on the voiceprint signal to be identified includes: performing analog-to-digital conversion on the voiceprint signal to obtain the original signal sequence.

[0092] ③ The analog signal S can be converted into a digital signal C sequence through an A / D module (analog-to-digital conversion module). C can be a coded sequence in binary form. It should be noted that the user's legal voiceprint information, as the user's legitimacy information, needs to be pre-stored on the server 200 for use in the subsequent voiceprint authentication process.

[0093] ④ The digital signal C is in the form of different binary symbols. In the embodiment of the present application, convolution coding is used as the channel coding method when the signal is transmitted in the channel. The input of the convolution algorithm is the digital signal C in binary form. At this time, C is used as the convolution coding input, and each bit is input to Figure 15 The input terminal is shown. Figure 15 In the figure, b1, b2, and b3 are registers. In one embodiment, these registers each store a 1-bit symbol and are initially set to 0. The three adders below each have their own input data and output results, c1, c2, and c3. By applying the corresponding registers and inputs to the calculations of each adder, the corresponding results of each adder can be obtained. Therefore, each 1-bit input corresponds to a 3-bit output, c1, c2, and c3. For example, if a 1 is input, the output is 101, and if a 0 is input, the output is 100, and so on. If the voiceprint digital signal C sequence is 1010, then the G sequence after convolution can be 101100101100, with a bit count of 12.

[0094] ⑤ Compare the convolution result sequence G with the user's legal voiceprint information sequence H stored in the database of server 200. Based on the comparison result, a score value grade is obtained and saved. The score value is then compared with the user's legal score threshold value Max stored in the database to determine whether the user is legal.

[0095] ⑥ If the user is a legitimate user, the score value and result sequence will be saved in the database, and the subsequent payment process will be completed and the payment result will be displayed to the user.

[0096] ⑦ If the user is an illegal user, the score value is saved, and the result and the number of voiceprint authentications performed by the user within the preset time are saved in the database.

[0097] ⑧If the user's recording time does not exceed the preset number (for example, 3 times), the next voice recording is allowed to proceed, and the above-mentioned convolution algorithm, comparison, scoring and legality judgment process is repeated; if the user exceeds the preset number (for example, 3 times), the voice recording is stopped and the system is exited.

[0098] As can be seen from the above description, the voiceprint information processing method provided by this application can, after obtaining the voiceprint signal of the user to be identified, perform convolution processing on the voiceprint signal, thereby improving its transmission reliability during channel transmission, reducing the bit error rate, and thus optimizing error control. The convolution-processed voiceprint signal is then compared with the user's legitimate voiceprint signal stored in the database, and a score is scored to determine whether the voiceprint signal of the user to be identified is legitimate, thereby achieving the purpose of accurately verifying the voiceprint in different environmental noise environments.

[0099] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0100] In one embodiment, see Figure 2 , perform convolution processing on the original signal sequence to obtain the corresponding signal convolution sequence, including:

[0101] S201: Determine a corresponding sub-generator polynomial according to the original signal sequence;

[0102] S202: Determine the corresponding sub-generator according to the sub-generator polynomial;

[0103] S203: Determine a subgenerator polynomial matrix according to the subgenerators;

[0104] S204: Determine a signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix.

[0105] Understandably, see Figure 3 , determining a corresponding subgenerator polynomial based on the original signal sequence. A specific implementation method may include inputting the original signal sequence into an adder to obtain a corresponding additive expression (S301); then inputting the additive expression into an encoder to obtain a subgenerator polynomial (S302). Determining the signal convolution sequence based on the original signal sequence and the subgenerator polynomial matrix includes: multiplying the original signal sequence by the subgenerator polynomial matrix to obtain the signal convolution sequence.

[0106] Specifically, Figure 16 The block diagram of a convolutional code encoder is shown. In one embodiment, the encoder includes three main components: a shift register, n modulo-2 adders, and a rotary switch. Each modulo-2 adder can have a different number of inputs connected to the output of the shift register. The output of the modulo-2 adder is connected to the rotary switch. Time is divided into equally spaced time slots. In each time slot, k bits enter the shift register from the left, and the information temporarily stored in each stage of the shift register is shifted right by k bits. The rotary switch rotates once per time slot, outputting n bits (n>k).

[0107] Figure 14 This is a block diagram of a convolutional encoder for a (3,1,3) convolutional code. In one embodiment, the left side shows the information input, and the right side shows the coded output. In the center are three shift registers, three modulo-2 adders, and a rotary switch. In each time slot, only one bit of input information enters the shift register, and the contents of each stage of the shift register are shifted right by one bit. Each rotation of the switch results in a three-bit output. Given k = 1 and n = 3, the code rate R = 1 / 3. The constraint length nN = 9.

[0108] See also Figure 17 , the signal convolution sequence can be determined according to the following process:

[0109] 1. The user's voiceprint recording electrical signal is obtained and converted into a digital signal sequence C through analog-to-digital conversion. The following example uses C=10111.

[0110] 2. Assume that the circuit diagram of the convolutional code encoder used in the modulator used for convolution processing is as follows Figure 17As shown, a (2, 1, 2) convolutional code encoder.

[0111] (1) Voiceprint digital signal C sequence: C = 10111, starting from 0 and increasing in power from left to right, C(x) = 1×x + 0×x 1 +1×x 2 +1×x 3 +1×x 4 Its polynomial expression is C(x)=1+x 2 +x 3 +x 4 .

[0112] (2) According to the connection orientation of the convolutional code encoder

[0113] The upper adder consists of three inputs: left, middle, and right. The sub-generator polynomial is: g(1,1)(x)=1+x+x 2 ;

[0114] The adder below consists of two inputs, left and right, and the sub-generator polynomial is: g(1,2)(x)=1+x 2 .

[0115] (3) According to the above subgenerator polynomials, written in binary form, we get the subgenerators g(1,1)=(111) and g(1,2)=(101).

[0116] (4) Generator polynomial matrix G(x) = [g(1,1)(x), g(1,2)(x)]

[0117] G(x)=[1+x+x 2 , 1+x 2 ]

[0118] (5) Convolutional encoder output sequence The output code sequence consists of n0 subsequences, namely And c(x)=C(x)G(x),

[0119] where c(1)(x)=C(x)g(1,1)(x) and c(2)(x)=C(x)g(1,2)(x)

[0120] c(1)(x)=C(x)g(1,1)(x)=(1+x 2 +x 3 +x 4 )(1+x+x 2 )=1+x+x 4 +x 6

[0121] Written in binary form: c1=1100101

[0122] c(2)(x)=C(x)g(1,2)(x)=(1+x 2 +x 3 +x 4 )(1+x 2 )=1+x 3 +x 5 +x 6

[0123] Written in binary form: c2=1001011

[0124] Two-way merging: c = 11100001100111

[0125] (6) According to the above (5), the calculated convolution result c=11100001100111 is obtained.

[0126] 3. The convolution result G is sent to the server 200. The convolution result G needs to be compared with the qualified voiceprint sequence H = 11100001011111 of the user that has been cached in the server. For example, in one embodiment, if 3 digits are different, the score can be graded as 96, which meets the qualified score range.

[0127] 4. The server determines that the voiceprint is qualified according to the grade result, and returns a qualified mark to the client, indicating that the voiceprint comparison has passed; otherwise, a notification to re-enter the voiceprint can be returned; in one embodiment, see Figure 5 , performing voiceprint authentication on the voiceprint signal according to the signal convolution sequence, including: S501: searching for a legal voiceprint signal corresponding to the voiceprint signal in the voiceprint information database; S502: comparing the signal convolution sequence with the legal voiceprint signal to obtain a voiceprint authentication result.

[0128] 5. The client 100 may display a successful result page indicating that the voiceprint has passed or a notification to re-enter the voiceprint.

[0129] From the above description, it can be seen that the voiceprint information processing method provided in this application can perform convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence.

[0130] In one embodiment, see Figure 6 , compare the signal convolution sequence with the legal voiceprint signal to obtain the voiceprint authentication result, including:

[0131] S601: Compare the signal convolution sequence with the legal voiceprint signal to obtain the number of difference bits;

[0132] S602: Determine an authentication score based on the number of difference digits and a preset threshold;

[0133] S603: Determine the voiceprint authentication result according to the score.

[0134] It is understood that the voiceprint convolution sequence (e.g., 100100010101110111) is a linear non-block code, also known as a convolutional code, which has high reliability and low bit error rate in channel transmission. This voiceprint convolution sequence is compared with the previously recorded legitimate user's information codeword H sequence (legitimate voiceprint sequence), and a grade is derived based on the number of different bits found in the comparison. For example, a complete match is 100 points, a single bit difference is 99 points, a two-bit difference is 98 points, and so on.

[0135] For each user, a legal voice score is stored on server 200 based on the user ID, i.e., the critical score (Max) for legal users. The score is compared with the critical score. If the score is greater than the Max, the user is legal and authentication is successful. If the score is less than the Max, the voice is considered illegal and authentication fails.

[0136] In one embodiment, the scoring table may be as shown in Table 1 below:

[0137] Table 1

[0138]

[0139]

[0140] Considering that the bit error rate cannot be too high and the number of comparison error bits should not exceed 6, a score of 90 is the best.

[0141] After the above comparison, the Max value itself is between 90 and 100 points. Therefore, if the comparison score between the user's voiceprint convolution sequence and the legal sequence (H) is between 90-100 points, it can generally be considered a legal voiceprint. If it is lower than 90 points, it is generally considered an illegal voiceprint. In this case, the user can be asked to re-enter the voiceprint.

[0142] As can be seen from the above description, the voiceprint information processing method provided by this application can, after obtaining the voiceprint signal of the user to be identified, perform convolution processing on the voiceprint signal, thereby improving its transmission reliability during channel transmission, reducing the bit error rate, and thus optimizing error control. The convolution-processed voiceprint signal is then compared with the user's legitimate voiceprint signal stored in the database, and a score is scored to determine whether the voiceprint signal of the user to be identified is legitimate, thereby achieving the purpose of accurately verifying the voiceprint in different environmental noise environments.

[0143] The present invention has at least the following beneficial effects:

[0144] 1. This invention proposes using a channel convolution algorithm to replace the linear block code used to transmit voiceprint information over a channel. Convolutional coding is a linear, non-blocking algorithm that can improve the reliability of information transmission, specifically, reduce the bit error rate during transmission. After obtaining the user's voiceprint information, a convolution algorithm is used during channel transmission to improve the reliability of voice information transmission over the channel, achieving a lower bit error rate and, in turn, more optimized error control coding.

[0145] 2. The present invention proposes a solution for judging the legitimacy and accuracy of voiceprint information based on the convolution algorithm: the user's voiceprint information is convolutionally encoded and then compared with the voiceprint information of the user already stored in the database. A corresponding score value is obtained based on the comparison. The legitimacy of the user's voiceprint information is judged by the score value, thereby achieving the purpose of accurately verifying the voiceprint under different environmental noises.

[0146] Based on the same inventive concept, the embodiments of the present application also provide a voiceprint information processing device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem by the voiceprint information processing device is similar to that of the voiceprint information processing method, the implementation of the voiceprint information processing device can refer to the implementation of the method based on the software performance benchmark, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements the predetermined function. Although the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0147] In one embodiment, see Figure 7 , the present application provides a voiceprint information processing device, including: an original sequence generation unit 701 and a convolution processing unit 702.

[0148] The original sequence generating unit 701 is used to generate an original signal sequence according to the voiceprint signal to be identified;

[0149] The convolution processing unit 702 is configured to perform convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and send the result to the voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication according to the signal convolution sequence.

[0150] In one embodiment, the original sequence generating unit is configured to:

[0151] Perform analog-to-digital conversion on the voiceprint signal to obtain the original signal sequence.

[0152] Further, see Figure 8The convolution processing unit 702 includes: a polynomial determination module 801, a generator determination module 802, a matrix determination module 803 and a convolution sequence determination module 804.

[0153] A polynomial determination module 801 is configured to determine a corresponding sub-generator polynomial according to the original signal sequence;

[0154] A generator determining module 802 is configured to determine a corresponding sub-generator according to the sub-generator polynomial;

[0155] A matrix determination module 803 is configured to determine a subgenerator polynomial matrix according to the subgenerators;

[0156] The convolution sequence determination module 804 is configured to determine the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix.

[0157] Further, see Figure 9 The polynomial determination module 801 includes: an expression generation submodule 901 and a polynomial determination submodule 902.

[0158] The expression generation submodule 901 is used to input the original signal sequence into the adder to obtain the corresponding addition expression;

[0159] The polynomial determination submodule 902 is configured to input the addition expression into an encoder to obtain the sub-generator polynomial.

[0160] Furthermore, the convolution sequence determination module is used to:

[0161] The signal original sequence is multiplied by the sub-generator polynomial matrix to obtain the signal convolution sequence.

[0162] In one embodiment, see Figure 10 The present application provides a voiceprint information processing device, including: a convolution sequence receiving unit 1001, a voiceprint authentication unit 1002 and an authentication result sending unit 1003.

[0163] The convolution sequence receiving unit 1001 is configured to receive a signal convolution sequence corresponding to a voiceprint signal to be identified from a client;

[0164] A voiceprint authentication unit 1002, configured to perform voiceprint authentication on the voiceprint signal according to the signal convolution sequence;

[0165] The authentication result sending unit 1003 is configured to send an authentication success notification or a re-authentication instruction to the client according to the voiceprint authentication result.

[0166] In one embodiment, see Figure 11The voiceprint authentication unit 1002 includes: a legal signal search module 1101 and an authentication result generation module 1102.

[0167] A legal signal search module 1101 is configured to search a voiceprint information database for a legal voiceprint signal corresponding to the voiceprint signal;

[0168] The authentication result generating module 1102 is configured to compare the signal convolution sequence with the legal voiceprint signal to obtain the voiceprint authentication result.

[0169] In one embodiment, see Figure 12 The voiceprint authentication unit 1002 includes: a difference digit determination module 1201, an authentication score determination module 1202 and a voiceprint authentication module 1203.

[0170] The difference bit determination module 1201 is used to compare the signal convolution sequence with the legal voiceprint signal to obtain the difference bit number;

[0171] An authentication score determination module 1202 is configured to determine an authentication score based on the number of digits of the difference and a preset threshold;

[0172] The voiceprint authentication module 1203 is configured to determine the voiceprint authentication result according to the score.

[0173] From a hardware perspective, in order to accurately verify the user's voiceprint information so as to complete legal voiceprint payment, this application provides an embodiment of an electronic device for implementing all or part of the voiceprint information processing method. The electronic device specifically includes the following:

[0174] A processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to transmit information between the voiceprint information processing device and related devices such as the core business system, user terminals, and related databases; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiments of the voiceprint information processing method and the voiceprint information processing device in the embodiments, and their contents are incorporated herein, and repeated parts are not repeated.

[0175] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0176] In practical applications, portions of the voiceprint information processing method can be executed on the electronic device as described above, or all operations can be performed on the client device. The specific method can be selected based on the processing capabilities of the client device and the limitations of the user's usage scenario. This application does not impose any restrictions on this. If all operations are performed on the client device, the client device may also include a processor.

[0177] The client device may include a communication module (i.e., a communication unit) that can establish a communication connection with a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0178] Figure 13 Schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 13 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that the Figure 13 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0179] In one embodiment, the voiceprint information processing method function may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0180] S101: Generate an original signal sequence according to the voiceprint signal to be identified;

[0181] S102: performing convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and sending the result to a voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal according to the signal convolution sequence.

[0182] As can be seen from the above description, the voiceprint information processing method provided by this application can, after obtaining the voiceprint signal of the user to be identified, perform convolution processing on the voiceprint signal, thereby improving its transmission reliability during channel transmission, reducing the bit error rate, and thus optimizing error control. The convolution-processed voiceprint signal is then compared with the user's legitimate voiceprint signal stored in the database, and a score is scored to determine whether the voiceprint signal of the user to be identified is legitimate, thereby achieving the purpose of accurately verifying the voiceprint in different environmental noise environments.

[0183] In another embodiment, the voiceprint information processing device can be configured separately from the central processing unit 9100. For example, the data composite transmission device voiceprint information processing device can be configured as a chip connected to the central processing unit 9100, and the functions of the voiceprint information processing method can be realized through the control of the central processing unit.

[0184] like Figure 13 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 13 In addition, the electronic device 9600 may also include all components shown in Figure 13 For components not shown, reference may be made to the prior art.

[0185] like Figure 13 As shown, the central processing unit 9100 is sometimes also referred to as a controller or operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0186] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0187] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0188] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), or a SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0189] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various driver programs for the electronic device's communication functions and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0190] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in a conventional mobile communication terminal.

[0191] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing common telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0192] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the voiceprint information processing method in the above embodiments, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements all steps of the voiceprint information processing method in the above embodiments, where the execution subject is a server or a client. For example, when the processor executes the computer program, the following steps are implemented:

[0193] S101: Generate an original signal sequence according to the voiceprint signal to be identified;

[0194] S102: performing convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and sending the result to a voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal according to the signal convolution sequence.

[0195] As can be seen from the above description, the voiceprint information processing method provided by this application can, after obtaining the voiceprint signal of the user to be identified, perform convolution processing on the voiceprint signal, thereby improving its transmission reliability during channel transmission, reducing the bit error rate, and thus optimizing error control. The convolution-processed voiceprint signal is then compared with the user's legitimate voiceprint signal stored in the database, and a score is scored to determine whether the voiceprint signal of the user to be identified is legitimate, thereby achieving the purpose of accurately verifying the voiceprint in different environmental noise environments.

[0196] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0197] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0198] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0199] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0200] Specific embodiments are used in the present invention to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A voiceprint information processing method, characterized in that: include: Generate an original signal sequence according to the voiceprint signal to be identified; Performing convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and sending it to a voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal based on an error comparison between the signal convolution sequence and the stored voiceprint information; The convolution process is performed on the original signal sequence to obtain a corresponding signal convolution sequence, including: Determine a corresponding sub-generator polynomial according to the original sequence of the signal; Determine a corresponding sub-generator according to the sub-generator polynomial; Determine a subgenerator polynomial matrix according to the subgenerator; The signal convolution sequence is determined according to the original signal sequence and the sub-generator polynomial matrix.

2. The voiceprint information processing method according to claim 1, characterized in that: The generating of the original signal sequence according to the voiceprint signal to be identified includes: Perform analog-to-digital conversion on the voiceprint signal to obtain the original signal sequence.

3. The voiceprint information processing method according to claim 1, characterized in that: The determining of the corresponding sub-generator polynomial according to the original signal sequence includes: Inputting the original signal sequence into an adder to obtain a corresponding addition expression; The addition expression is input into an encoder to obtain the sub-generator polynomial.

4. The voiceprint information processing method according to claim 1, characterized in that: The determining the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix includes: The signal original sequence is multiplied by the sub-generator polynomial matrix to obtain the signal convolution sequence.

5. A voiceprint information processing method, characterized in that: include: Receive a signal convolution sequence corresponding to the voiceprint signal to be identified from the client; Performing voiceprint authentication on the voiceprint signal according to the signal convolution sequence, including: searching a voiceprint information database for a valid voiceprint signal corresponding to the voiceprint signal; performing a bit comparison between the signal convolution sequence and the valid voiceprint signal to obtain a voiceprint authentication result; Sending an authentication success notification or a re-authentication instruction to the client according to the voiceprint authentication result; The signal convolution sequence is obtained by convolution processing the original signal sequence corresponding to the voiceprint signal, including: determining the corresponding sub-generator polynomial according to the original signal sequence; determining the corresponding sub-generator according to the sub-generator polynomial; determining the sub-generator polynomial matrix according to the sub-generator; and determining the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix.

6. The voiceprint information processing method according to claim 5, characterized in that: The step of comparing the number of bits of the signal convolution sequence with the legal voiceprint signal to obtain a voiceprint authentication result includes: Comparing the signal convolution sequence with the legal voiceprint signal to obtain the number of difference bits; Determine an authentication score based on the number of digits of the difference and a preset threshold; The voiceprint authentication result is determined according to the score.

7. A voiceprint information processing device, characterized in that: include: An original sequence generating unit, configured to generate an original signal sequence according to the voiceprint signal to be identified; a convolution processing unit, configured to perform convolution processing on the original signal sequence to obtain a corresponding signal convolution sequence and send the result to a voiceprint authentication server, so that the voiceprint authentication server performs voiceprint authentication on the voiceprint signal based on an error comparison between the signal convolution sequence and the stored voiceprint information; The convolution processing unit includes: a polynomial determination module, a generator determination module, a matrix determination module and a convolution sequence determination module; The polynomial determination module is used to determine the corresponding sub-generator polynomial according to the original signal sequence; The generator determination module is used to determine the corresponding sub-generator according to the sub-generator polynomial; The matrix determination module is used to determine the sub-generator polynomial matrix according to the sub-generator; The convolution sequence determination module is used to determine the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix.

8. A voiceprint information processing device, characterized in that: include: A convolution sequence receiving unit, configured to receive a signal convolution sequence corresponding to a voiceprint signal to be identified from a client; a voiceprint authentication unit, configured to perform voiceprint authentication on the voiceprint signal according to the signal convolution sequence; An authentication result sending unit, configured to send an authentication success notification or a re-authentication instruction to the client according to the voiceprint authentication result; The voiceprint authentication unit includes a legal signal search module and an authentication result generation module; The legal signal search module is used to search the voiceprint information database for a legal voiceprint signal corresponding to the voiceprint signal; The authentication result generating module is configured to compare the number of bits of the signal convolution sequence with the legal voiceprint signal to obtain the voiceprint authentication result; The signal convolution sequence is obtained by convolution processing the original signal sequence corresponding to the voiceprint signal, including: determining the corresponding sub-generator polynomial according to the original signal sequence; determining the corresponding sub-generator according to the sub-generator polynomial; determining the sub-generator polynomial matrix according to the sub-generator; and determining the signal convolution sequence according to the original signal sequence and the sub-generator polynomial matrix.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the voiceprint information processing method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the voiceprint information processing method according to any one of claims 1 to 6 are implemented.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the voiceprint information processing method according to any one of claims 1 to 6 are implemented.

Images