CN111091837A - Time-varying voiceprint authentication method and system based on online learning - Google Patents
Time-varying voiceprint authentication method and system based on online learning Download PDFInfo
- Publication number
- CN111091837A CN111091837A CN201911371947.2A CN201911371947A CN111091837A CN 111091837 A CN111091837 A CN 111091837A CN 201911371947 A CN201911371947 A CN 201911371947A CN 111091837 A CN111091837 A CN 111091837A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- user
- password
- registered
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012795 verification Methods 0.000 claims abstract description 80
- 230000008569 process Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010835 comparative analysis Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
Abstract
The invention discloses a time-varying voiceprint authentication method and system based on online learning, wherein a prompt text is randomly generated, a user is prompted to read the prompt text aloud, and voiceprint features in audio aloud read by the user are collected; and comparing and analyzing the collected voiceprint features with the voiceprint features of the user registered before, judging that the user passes the verification when the voiceprint features are consistent, verifying the identity of the user through a password if the user does not pass the verification, and updating the voiceprint information of the user in the registered voiceprint database through an online learning method if the user passes the password verification. The advantages are that: compared with the prior art, the method improves the accuracy of identification, and improves the practicability and safety of the system; the user voiceprint information in the registered voiceprint database can be updated through an online learning method, so that the user is allowed to update the voiceprint registration information through a password, and the usability of the system is improved.
Description
Technical Field
The invention relates to a time-varying voiceprint authentication method based on online learning, and belongs to the technical field of biological information security.
Background
Voiceprint Recognition (Voiceprint Recognition), also known as speaker Recognition, is divided into speaker Recognition and speaker verification. The former is used for judging which one of a plurality of people says a certain section of voice; the latter is to determine whether a certain speech is spoken by a specific person. The tasks are different and the techniques used are different.
Voiceprint password authentication is an application of speaker verification, which requires a user to input speech and thereby confirm the identity of the speaker. In the application, the user registration and identity authentication usually adopt the voice input (text correlation) of a fixed password text, so that the voice content difference is eliminated, and the voiceprints of the user registration and identity authentication are more consistent, and accordingly, the authentication effect better than the confirmation of a speaker irrelevant to the text can be obtained. At present, a fixed number string (classical mode) or a random number string is often adopted for a commonly used voiceprint password, and compared with the former, the latter has the greatest characteristic of well preventing attacks such as recording playback and the like.
The disadvantages of the existing voiceprint password authentication technology include: under a text-independent mode, a plurality of voice data templates are needed for registration and verification, the verification process is slow, the method is not suitable for real-time user voiceprint password verification, and the user experience is poor; the classical mode related to the text has the risk of being intercepted and is more likely to be attacked by the playback of the recorded sound; the user's sound voiceprint is susceptible to other factors, and reasons such as the increase of age can all make the voiceprint take place slight change, reduce the matching similarity to influence the matching success rate, influence the user and use.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a time-varying voiceprint authentication method and system based on online learning, so that the accuracy, the real-time performance and the usability of an identification result are improved.
In order to solve the above technical problems, the present invention provides a time-varying voiceprint authentication method based on online learning,
randomly generating a prompt text, prompting a user to read the prompt text aloud, and collecting voiceprint characteristics in the audio aloud read by the user;
and comparing and analyzing the collected voiceprint features with the voiceprint features of the user registered before, judging that the user passes the verification when the voiceprint features are consistent, verifying the identity of the user through a password if the user does not pass the verification, and updating the voiceprint information of the user in the registered voiceprint database through an online learning method if the user passes the password verification.
Further, the voiceprint feature refers to a unique voice time-frequency characteristic of the user extracted by using an acoustic signal feature and a model method.
Further, the registration process is as follows:
when setting user information, requiring user to speak all numbers 0-9, segmenting according to voice audio frequency input by user, extracting corresponding characteristics and storing in a registered voiceprint database, and setting user login password and storing the password in a registered password database.
Further, the generation process of the prompt text is as follows:
randomly generating a numeric string with fixed length for prompting a user to speak the string of numbers, and simultaneously splicing the voiceprint features in the registered voiceprint database into a voiceprint feature sequence required by the comparison according to the numeric string sequence before the comparison and analysis.
Further, the comparative analysis process comprises:
comparing the similarity between the voice print features in the audio read by the user according to the prompt text prompted by the system and the voice print features stored in the registered voice print database, and judging the similarity according to f(s) < e > (s + α), wherein s is the feature similarity during registration and verification, α is the voice print verification judgment threshold, e is a natural index, when f(s) >1, the judgment is passed, and when f(s) <1, the judgment is not passed.
Further, the password verification process includes:
the user inputs password information, the system matches the input of the user with the user password in the registered password database, if the matching is successful, the system accepts, otherwise, the system rejects.
Further, the process of the online learning method is as follows:
in the case of not passing voiceprint authentication but passing password authentication, a judgment whether to update the current learning is made according to the similarity degree of the characteristics and a set learning threshold, and the judgment is made according to f(s) e (s + α), wherein s is the characteristic similarity degree at the time of registration and authentication, α is a voiceprint authentication judgment threshold, β is a learning threshold, e is a natural index, when β < f(s) <1, the updating is judged to be allowed, the corresponding characteristic information is updated to a registered voiceprint database, when f(s) is less than β, the database is judged not to pass, and the database is not updated.
A time-varying voiceprint authentication system based on online learning comprises a voiceprint characteristic acquisition module and an analysis comparison module;
the voiceprint feature acquisition module is used for randomly generating a prompt text, prompting a user to read the prompt text aloud and acquiring voiceprint features in the voice frequency aloud read by the user;
and comparing and analyzing the collected voiceprint features with the voiceprint features of the user registered before, judging that the user passes the verification when the voiceprint features are consistent, verifying the identity of the user through a password if the user does not pass the verification, and updating the voiceprint information of the user in the registered voiceprint database through an online learning method if the user passes the password verification.
Further, the system also comprises a registration voiceprint database, a registration password database and a registration module;
and the registration module outputs the registered voiceprint characteristics to a registration voiceprint database and outputs the registered password information to a registration password database.
Further, the analysis comparison module comprises a verification module and a learning module;
the verification module is used for verifying and comparing the collected voiceprint features with voiceprint features prestored in a registered voiceprint database, prompting a user to input password information when the collected voiceprint features are judged not to pass the registered voiceprint features, verifying and comparing the information input by the user with passwords prestored in the registered password database, outputting the voiceprint features input by the user to the learning module when the information input by the user passes the registered voiceprint features, and updating the voiceprint feature information of the user into the registered voiceprint database by the learning module.
The invention achieves the following beneficial effects:
compared with the prior art, the method improves the accuracy of identification, and improves the practicability and safety of the system; the user voiceprint information in the registered voiceprint database can be updated through an online learning method, so that the user is allowed to update the voiceprint registration information through a password, and the usability of the system is improved.
Drawings
FIG. 1 is a block diagram of the system of the present invention;
FIG. 2 is a flow chart of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
A time-varying voiceprint authentication method based on online learning,
randomly generating a prompt text, prompting a user to read the prompt text aloud, and collecting voiceprint characteristics in the audio aloud read by the user;
and comparing and analyzing the collected voiceprint features with the voiceprint features of the user registered before, judging that the user passes the verification when the voiceprint features are consistent, verifying the identity of the user through a password if the user does not pass the verification, and updating the voiceprint information of the user in the registered voiceprint database through an online learning method if the user passes the password verification.
The voiceprint features refer to the unique voice time-frequency characteristics of the user extracted by using the acoustic signal features and a model method.
The registration process comprises the following steps:
when setting user information, requiring user to speak all numbers 0-9, segmenting according to voice audio frequency input by user, extracting corresponding characteristics and storing in a registered voiceprint database, and setting user login password and storing the password in a registered password database.
The generation process of the prompt text comprises the following steps:
randomly generating a numeric string with fixed length for prompting a user to speak the string of numbers, and simultaneously splicing the voiceprint features in the registered voiceprint database into a voiceprint feature sequence required by the comparison according to the numeric string sequence before the comparison and analysis.
The comparative analysis process comprises the following steps:
comparing the similarity between the voice print features in the audio read by the user according to the prompt text prompted by the system and the voice print features stored in the registered voice print database, and judging the similarity according to f(s) < e > (s + α), wherein s is the feature similarity during registration and verification, α is the voice print verification judgment threshold, e is a natural index, when f(s) >1, the judgment is passed, and when f(s) <1, the judgment is not passed.
The password verification process comprises the following steps:
the user inputs password information, the system matches the input of the user with the user password in the registered password database, if the matching is successful, the system accepts, otherwise, the system rejects.
The process of the online learning method is as follows:
in the case of not passing voiceprint authentication but passing password authentication, a judgment whether to update the current learning is made according to the similarity degree of the characteristics and a set learning threshold, and the judgment is made according to f(s) e (s + α), wherein s is the characteristic similarity degree at the time of registration and authentication, α is a voiceprint authentication judgment threshold, β is a learning threshold, e is a natural index, when β < f(s) <1, the updating is judged to be allowed, the corresponding characteristic information is updated to a registered voiceprint database, when f(s) is less than β, the database is judged not to pass, and the database is not updated.
As shown in fig. 1, the present embodiment relates to a time-varying voiceprint authentication system based on online learning, which includes: register voiceprint database, register password database and register module, verification module and study module connected with it respectively, wherein: the registered voiceprint characteristics are output to a registered voiceprint database by a registration module, registered password information is output to the registered password database by a verification module, a password is generated and input by a user is prompted by the verification module, voiceprint characteristic extraction is carried out on the information input by the user, verification comparison is carried out on the information input by the user and the voiceprint characteristics prestored in the registered voiceprint database, when the information input by the user is not passed, the user is prompted to input the password information, the information input by the user is verified and compared with the password prestored in the registered password database, when the information input by the user is passed, the voiceprint characteristics input by the user are output to a learning module, and the voiceprint characteristic information of the user at this time is proportionally updated to the registered voiceprint database by the learning module.
The registration module comprises: the voice input unit is used for collecting user voiceprint information, the characteristic processing unit is used for segmenting and extracting characteristics of audio input by a user and storing the audio in the registered voiceprint database, and the password processing unit is used for collecting a user registration password and storing the user registration password in the registered password database.
The verification module comprises: the system comprises a prompt input unit for generating a prompt text numeric string and collecting voiceprint information during user verification, a feature extraction unit for segmenting and extracting a voice frequency input by a user, a model building unit for extracting corresponding voiceprint features from a registered voiceprint database according to the generated numeric string and re-splicing a temporary voiceprint model for the verification, a voiceprint verification decision unit for making a decision whether to allow the user to pass through the system verification according to the new model and the voiceprint features input by the user, and a password verification decision unit for inputting a user password and making a decision whether to allow the user to pass through the system verification and perform online learning according to the new password and password information prestored in a registered password database.
The learning module comprises: the voice print processing unit is used for carrying out segmentation calibration and feature extraction on voice information input by a user and the feature updating unit is used for updating the voice print feature information in the registered voice print database according to the new voice print features.
As shown in fig. 2, the present embodiment includes the following detailed operation steps:
step 1) registering, wherein a voice input unit of a registration module inputs 0-9 digit voice spoken by a user, and a password processing unit inputs user-defined password information.
And step 2) the feature processing unit segments the input voice, extracts features, correspondingly stores the features into a registered voiceprint database according to a numerical sequence, and stores user-defined password information into a registered password database.
And 3) verifying the voiceprint, wherein a prompt input unit of the verification module generates a six-digit random number string, a user is required to speak the number string and record the number string, the number string is delivered to a feature extraction unit, and a model building unit extracts corresponding feature information from a registered voiceprint database according to the number string and synthesizes the feature string used in the verification.
And 4) verifying the voiceprint of the user, wherein the voiceprint verification decision unit makes a decision on whether the user is allowed to pass the system verification according to the feature string generated by the model construction unit and the voiceprint feature of the voice recorded by the user for the verification at this time, and the decision is judged according to f(s) ((s) & gt e) & gt (s + α), wherein s is the feature similarity degree during registration and verification, if the feature similarity degree can be a negative value of the distance between the registered feature sequence and the tested feature sequence, α is a voiceprint verification judgment threshold, if f(s) & gt 1, the voiceprint verification is judged to pass and the authentication is successful, and if f(s) & lt 1, the voiceprint verification is judged not to pass, and the step 5 is executed.
Step 5) user password verification, wherein a password verification decision unit prompts that user voiceprint verification fails and requires a user to input a password for verification, then a decision whether the user is allowed to pass system verification is made according to the user password in the registered password library and the password input this time, if the user password passes the system verification, step 6) is executed, if the user password does not pass the system verification, authentication fails, and the verification is finished.
Step 6) online learning, wherein a voiceprint processing unit of a learning module receives the audio information input by the user at this time from a verification module prompt input unit, the audio is segmented according to corresponding digit strings, characteristics are extracted, then whether the learning is updated or not is judged according to the similarity degree of the characteristics and the original characteristics in the database and a set learning threshold, the judgment is based on [ (f),(s) and e ^ (s + α), wherein s is the characteristic similarity degree during registration and verification, such as the characteristic similarity degree can be a negative value of the distance between the registration and test characteristic sequences, α is a voiceprint verification judgment threshold, β is a learning threshold and β is 0.8, when β < f(s) <1, updating is allowed, corresponding characteristic information is updated into a registered voiceprint database, the identification rate under the time-varying voiceprint occurrence condition is improved, when f(s) < β, the database is not updated.
Use example one
The user registers the voiceprint, inputs the voice information of '0-9', sets the password 'Abc 888'
System prompts during voiceprint verification
Please say the following numeric string: 308267"
The user says "308267". The content is correct and the voiceprints are consistent, and the verification is passed.
Use example two
The user registers the voiceprint, inputs the voice information of '0-9', sets the password 'Abc 888'
System prompts during voiceprint verification
Please say the following numeric string: 308267"
The user says "123456". The content is incorrect and the verification fails. Password authentication is not allowed. And finishing the authentication.
Use example three
The user registers the voiceprint, inputs the voice information of '0-9', sets the password 'Abc 888'
System prompts during voiceprint verification
Please say the following numeric string: 308267"
The user says "308267". The content is correct but the voiceprints are not consistent, and the verification is not passed. Allowing password authentication.
When password verification is performed, system prompts
'please input your password'
The user enters "Abc 888". The password is the same and the authentication is passed. And f(s) >0.8 is calculated, and the system automatically updates the registered voiceprint database.
Use example four
The user registers the voiceprint, inputs the voice information of '0-9', sets the password 'Abc 888'
System prompts during voiceprint verification
Please say the following numeric string: 308267"
The user says "308267". The content is correct but the voiceprints are not consistent, and the verification is not passed. Allowing password authentication.
When password verification is performed, system prompts
'please input your password'
The user enters "Abc 888". The password is the same and the authentication is passed. Calculated f (distance) <0.8, the system does not update the registered voiceprint database.
Use example five
The user registers the voiceprint, inputs the voice information of '0-9', sets the password 'Abc 888'
System prompts during voiceprint verification
Please say the following numeric string: 308267"
The user says "308267". The content is correct but the voiceprints are not consistent, and the verification is not passed. Allowing password authentication.
When password verification is performed, system prompts
'please input your password'
The user enters "abc 888". The passwords are not the same and the authentication does not pass. And finishing the authentication.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may 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, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A time-varying voiceprint authentication method based on online learning is characterized in that,
randomly generating a prompt text, prompting a user to read the prompt text aloud, and collecting voiceprint characteristics in the audio aloud read by the user;
and comparing and analyzing the collected voiceprint features with the voiceprint features of the user registered before, judging that the user passes the verification when the voiceprint features are consistent, verifying the identity of the user through a password if the user does not pass the verification, and updating the voiceprint information of the user in the registered voiceprint database through an online learning method if the user passes the password verification.
2. The online-learning-based time-varying voiceprint authentication method according to claim 1, wherein the voiceprint features refer to user-unique speech time-frequency characteristics extracted by using acoustic signal features and a model method.
3. The online-learning-based time-varying voiceprint authentication method according to claim 1, wherein the registration process is as follows:
when setting user information, requiring user to speak all numbers 0-9, segmenting according to voice audio frequency input by user, extracting corresponding characteristics and storing in a registered voiceprint database, and setting user login password and storing the password in a registered password database.
4. The online learning-based time-varying voiceprint authentication method according to claim 1, wherein the generation process of the prompt text is as follows:
randomly generating a numeric string with fixed length for prompting a user to speak the string of numbers, and simultaneously splicing the voiceprint features in the registered voiceprint database into a voiceprint feature sequence required by the comparison according to the numeric string sequence before the comparison and analysis.
5. The online-learning-based time-varying voiceprint authentication method according to claim 1, wherein the comparison analysis process is as follows:
comparing the similarity between the voice print features in the audio read by the user according to the prompt text prompted by the system and the voice print features stored in the registered voice print database, and judging the similarity according to f(s) < e > (s + α), wherein s is the feature similarity during registration and verification, α is the voice print verification judgment threshold, e is a natural index, when f(s) >1, the judgment is passed, and when f(s) <1, the judgment is not passed.
6. The online learning-based time-varying voiceprint authentication method according to claim 1, wherein the password verification process is as follows:
the user inputs password information, the system matches the input of the user with the user password in the registered password database, if the matching is successful, the system accepts, otherwise, the system rejects.
7. The online learning-based time-varying voiceprint authentication method according to claim 1, wherein the online learning method comprises the following processes:
in the case of not passing voiceprint authentication but passing password authentication, a judgment whether to update the current learning is made according to the similarity degree of the characteristics and a set learning threshold, and the judgment is made according to f(s) e (s + α), wherein s is the characteristic similarity degree at the time of registration and authentication, α is a voiceprint authentication judgment threshold, β is a learning threshold, e is a natural index, when β < f(s) <1, the updating is judged to be allowed, the corresponding characteristic information is updated to a registered voiceprint database, when f(s) is less than β, the database is judged not to pass, and the database is not updated.
8. A time-varying voiceprint authentication system based on online learning is characterized by comprising a voiceprint feature acquisition module and an analysis comparison module;
the voiceprint feature acquisition module is used for randomly generating a prompt text, prompting a user to read the prompt text aloud and acquiring voiceprint features in the voice frequency aloud read by the user;
and comparing and analyzing the collected voiceprint features with the voiceprint features of the user registered before, judging that the user passes the verification when the voiceprint features are consistent, verifying the identity of the user through a password if the user does not pass the verification, and updating the voiceprint information of the user in the registered voiceprint database through an online learning method if the user passes the password verification.
9. The online-learning-based time-varying voiceprint authentication method according to claim 8, further comprising a registration voiceprint database, a registration password database, and a registration module;
and the registration module outputs the registered voiceprint characteristics to a registration voiceprint database and outputs the registered password information to a registration password database.
10. The online-learning-based time-varying voiceprint authentication method according to claim 8, wherein the analysis comparison module comprises a verification module and a learning module;
the verification module is used for verifying and comparing the collected voiceprint features with voiceprint features prestored in a registered voiceprint database, prompting a user to input password information when the collected voiceprint features are judged not to pass the registered voiceprint features, verifying and comparing the information input by the user with passwords prestored in the registered password database, outputting the voiceprint features input by the user to the learning module when the information input by the user passes the registered voiceprint features, and updating the voiceprint feature information of the user into the registered voiceprint database by the learning module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911371947.2A CN111091837A (en) | 2019-12-27 | 2019-12-27 | Time-varying voiceprint authentication method and system based on online learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911371947.2A CN111091837A (en) | 2019-12-27 | 2019-12-27 | Time-varying voiceprint authentication method and system based on online learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111091837A true CN111091837A (en) | 2020-05-01 |
Family
ID=70398420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911371947.2A Pending CN111091837A (en) | 2019-12-27 | 2019-12-27 | Time-varying voiceprint authentication method and system based on online learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111091837A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111898109A (en) * | 2020-08-14 | 2020-11-06 | 苏州思必驰信息科技有限公司 | Recognition method and system for biological characteristic adaptive learning |
| CN112309406A (en) * | 2020-09-21 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Voiceprint registration method, voiceprint registration device and computer-readable storage medium |
| CN112550139A (en) * | 2020-12-22 | 2021-03-26 | 东风汽车有限公司 | Automobile safety alarm method, storage medium and electronic equipment |
| CN113241080A (en) * | 2021-06-10 | 2021-08-10 | 思必驰科技股份有限公司 | Automatic registration voiceprint recognition method and device |
| CN113570754A (en) * | 2021-07-01 | 2021-10-29 | 汉王科技股份有限公司 | Voiceprint lock control method and device and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007052496A (en) * | 2005-08-15 | 2007-03-01 | Advanced Media Inc | User authentication system and user authentication method |
| CN104168270A (en) * | 2014-07-31 | 2014-11-26 | 腾讯科技（深圳）有限公司 | Identity verifying method, server, client side and system |
| CN106506524A (en) * | 2016-11-30 | 2017-03-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for verifying user |
| CN106782564A (en) * | 2016-11-18 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for processing speech data |
| CN106961418A (en) * | 2017-02-08 | 2017-07-18 | 北京捷通华声科技股份有限公司 | Identity identifying method and identity authorization system |
| US20170365259A1 (en) * | 2015-02-05 | 2017-12-21 | Beijing D-Ear Technologies Co., Ltd. | Dynamic password voice based identity authentication system and method having self-learning function |
| CN107919961A (en) * | 2017-12-07 | 2018-04-17 | 广州势必可赢网络科技有限公司 | A kind of identity authentication protocol and server updated based on dynamic code and dynamic vocal print |
| CN108231082A (en) * | 2017-12-29 | 2018-06-29 | 广州势必可赢网络科技有限公司 | A kind of update method and device of self study Application on Voiceprint Recognition |
| CN108847243A (en) * | 2018-06-19 | 2018-11-20 | Oppo广东移动通信有限公司 | Vocal print feature update method, device, storage medium and electronic equipment |
| CN109636937A (en) * | 2018-12-18 | 2019-04-16 | 深圳市沃特沃德股份有限公司 | Voice Work attendance method, device and terminal device |
-
2019
- 2019-12-27 CN CN201911371947.2A patent/CN111091837A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007052496A (en) * | 2005-08-15 | 2007-03-01 | Advanced Media Inc | User authentication system and user authentication method |
| CN104168270A (en) * | 2014-07-31 | 2014-11-26 | 腾讯科技（深圳）有限公司 | Identity verifying method, server, client side and system |
| US20170365259A1 (en) * | 2015-02-05 | 2017-12-21 | Beijing D-Ear Technologies Co., Ltd. | Dynamic password voice based identity authentication system and method having self-learning function |
| CN106782564A (en) * | 2016-11-18 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for processing speech data |
| CN106506524A (en) * | 2016-11-30 | 2017-03-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for verifying user |
| CN106961418A (en) * | 2017-02-08 | 2017-07-18 | 北京捷通华声科技股份有限公司 | Identity identifying method and identity authorization system |
| CN107919961A (en) * | 2017-12-07 | 2018-04-17 | 广州势必可赢网络科技有限公司 | A kind of identity authentication protocol and server updated based on dynamic code and dynamic vocal print |
| CN108231082A (en) * | 2017-12-29 | 2018-06-29 | 广州势必可赢网络科技有限公司 | A kind of update method and device of self study Application on Voiceprint Recognition |
| CN108847243A (en) * | 2018-06-19 | 2018-11-20 | Oppo广东移动通信有限公司 | Vocal print feature update method, device, storage medium and electronic equipment |
| CN109636937A (en) * | 2018-12-18 | 2019-04-16 | 深圳市沃特沃德股份有限公司 | Voice Work attendance method, device and terminal device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111898109A (en) * | 2020-08-14 | 2020-11-06 | 苏州思必驰信息科技有限公司 | Recognition method and system for biological characteristic adaptive learning |
| CN111898109B (en) * | 2020-08-14 | 2022-07-08 | 思必驰科技股份有限公司 | Recognition method and system for self-adaptive learning of biological characteristics |
| CN112309406A (en) * | 2020-09-21 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Voiceprint registration method, voiceprint registration device and computer-readable storage medium |
| CN112550139A (en) * | 2020-12-22 | 2021-03-26 | 东风汽车有限公司 | Automobile safety alarm method, storage medium and electronic equipment |
| CN113241080A (en) * | 2021-06-10 | 2021-08-10 | 思必驰科技股份有限公司 | Automatic registration voiceprint recognition method and device |
| CN113570754A (en) * | 2021-07-01 | 2021-10-29 | 汉王科技股份有限公司 | Voiceprint lock control method and device and electronic equipment |
| CN113570754B (en) * | 2021-07-01 | 2022-04-29 | 汉王科技股份有限公司 | Voiceprint lock control method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111091837A (en) | Time-varying voiceprint authentication method and system based on online learning | |
| JP6567040B2 (en) | Voiceprint login method and device based on artificial intelligence | |
| US10476872B2 (en) | Joint speaker authentication and key phrase identification | |
| US7447632B2 (en) | Voice authentication system | |
| WO2017114307A1 (en) | Voiceprint authentication method capable of preventing recording attack, server, terminal, and system | |
| EP2120232A1 (en) | A random voice print cipher certification system, random voice print cipher lock and generating method thereof | |
| US20060222210A1 (en) | System, method and computer program product for determining whether to accept a subject for enrollment | |
| JPH0345417B2 (en) | ||
| US6496800B1 (en) | Speaker verification system and method using spoken continuous, random length digit string | |
| CN105656887A (en) | Artificial intelligence-based voiceprint authentication method and device | |
| WO2018129869A1 (en) | Voiceprint verification method and apparatus | |
| EP3989217A1 (en) | Method for detecting an audio adversarial attack with respect to a voice input processed by an automatic speech recognition system, corresponding device, computer program product and computer-readable carrier medium | |
| CN107221333A (en) | A kind of identity authentication method and device | |
| CN110379433A (en) | Method, apparatus, computer equipment and the storage medium of authentication | |
| CN111081223A (en) | Voice recognition method, device, equipment and storage medium | |
| CN111402899A (en) | Cross-channel voiceprint identification method and device | |
| JP3849841B2 (en) | Speaker recognition device | |
| WO2023274028A1 (en) | Voiceprint lock control method and apparatus, and electronic device | |
| JP4440414B2 (en) | Speaker verification apparatus and method | |
| CN110797032B (en) | Voiceprint database establishing method and voiceprint identification method | |
| CN109872721A (en) | Voice authentication method, information processing equipment and storage medium | |
| CN110931020A (en) | Voice detection method and device | |
| CN110517695A (en) | Verification method and device based on vocal print | |
| CN108447491A (en) | A kind of Intelligent voice recognition method | |
| CN116597845B (en) | Random voiceprint verification system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200501 |