CN110086629A - A kind of multiple spurs is from voiceprint authentication method, terminal, server and storage medium - Google Patents
A kind of multiple spurs is from voiceprint authentication method, terminal, server and storage medium Download PDFInfo
- Publication number
- CN110086629A CN110086629A CN201910328466.7A CN201910328466A CN110086629A CN 110086629 A CN110086629 A CN 110086629A CN 201910328466 A CN201910328466 A CN 201910328466A CN 110086629 A CN110086629 A CN 110086629A
- Authority
- CN
- China
- Prior art keywords
- several
- user
- voiceprint
- multiple spurs
- voice
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000001755 vocal effect Effects 0.000 claims abstract description 11
- 238000012795 verification Methods 0.000 claims abstract description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000012011 method of payment Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/12—Score normalisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Telephone Function (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of multiple spurs from voiceprint authentication method, terminal, server and storage medium, which comprises in registration process, obtains user in several range directions and registers voice, generate several speech models, complete registration;In verification process, voice messaging of the active user under a certain distance is obtained, the voice messaging is the voice messaging that speaker is obtained by identification vocal print;Current speech information is compared marking with several speech models respectively, obtains corresponding several score values, and verify to active user according to several score values.The present invention effectively solves the problems, such as far and near field identification, and voice recognition rate can be increased to 95 from 80, and method is simple, versatile, can effectively solve the application problem of actual scene.
Description
Technical field
The present invention relates to vocal print technical fields, and in particular to a kind of multiple spurs is from voiceprint authentication method, terminal, server and deposits
Storage media.
Background technique
A kind of biological identification technology of sound groove recognition technology in e, identifies speaker's identity by voice.Sound groove recognition technology in e
It is applied in more scenes, such as phone, mobile phone, application program app, access control system, sound equipment, robot etc..
Wherein remote Near-field Problems In Civil Engineering (speaker and equipment equidistant from) has a great impact to Application on Voiceprint Recognition.For phone, hand
Machine is to use close to face, therefore influence on it smaller mostly in the scene made a phone call.But application program app, access control system,
Sound equipment, robot etc. just have a great impact, and there are remote Near-field Problems In Civil Engineerings.Existing voiceprint registration is mostly to take the side repeatedly registered
Method just can solve the remote Near-field Problems In Civil Engineering of user.
Summary of the invention
It is an object of the invention to overcome prior art problem, far and near field can be effectively solved the problems, such as, improve actual field
Application on Voiceprint Recognition rate in scape proposes a kind of multiple spurs from voiceprint authentication method, terminal, server and storage medium.
To reach above-mentioned purpose, the present invention adopts the following technical scheme: a kind of multiple spurs is from voiceprint authentication method, including it is as follows
Step:
In registration process, user is obtained in several range directions and registers voice, several speech models is generated, completes
Registration;
In verification process, voice messaging of the active user under a certain distance is obtained, the voice messaging is to pass through knowledge
Other vocal print obtains the voice messaging of speaker;Current speech information is compared marking with several speech models respectively, is obtained
Obtain several score values accordingly;
Current speech information is compared marking with several speech models respectively, obtains corresponding several score values, root
Active user is verified according to several score values.
It is described that active user is verified according to several score values further include:
Score value soprano will be taken as final identification score, final identification score will be compared with the threshold value of setting, when
Final identification score is greater than or is more than or equal to given threshold, then judges that current user authentication passes through, otherwise judge that active user tests
Card does not pass through.
Further, the acquisition user registers voice in several range directions specifically: respectively in several distances
The sound that user reads aloud setting paragraph is obtained under direction, and Application on Voiceprint Recognition is carried out by the sound to user and obtains voiceprint.
Further, several described range directions are at least one distance and/or at least one direction.
Further, by current speech information respectively with several speech models using cosine algorithm or PLDA algorithm into
Row marking.
The embodiment of the invention also provides a kind of terminal, the terminal includes: processor, memory and is stored in described
On memory and proving program of the multiple spurs from voiceprint registration that can run on the processor, the Auto-matching payment program
The step of above-mentioned multiple spurs is from voiceprint authentication method is realized when being executed by the processor.
The embodiment of the invention also provides a kind of server, the server includes: processor, memory and is stored in
On the memory and proving program of the multiple spurs from voiceprint registration that can run on the processor, the Auto-matching payment
Program realizes the step of above-mentioned multiple spurs is from voiceprint authentication method when being executed by the processor.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Proving program of the multiple spurs from voiceprint registration is contained, is realized such as when proving program of the multiple spurs from voiceprint registration is executed by processor
The step of above-mentioned multiple spurs is from voiceprint authentication method.
Compared with prior art, multiple spurs provided by the invention is situated between from voiceprint authentication method, terminal, server and storage
Matter, method is simple, in registration process, generates several speech models;In verification process, by current speech information respectively with
Several speech models are compared marking, obtain corresponding several score values;Active user is verified according to several score values.
Such as active user is verified by score value soprano, effectively solve the problems, such as far and near field identification, voice recognition rate can be from 80
95 are increased to, the threshold value in addition set can be defined according to model itself, had versatility, can effectively be solved actual scene
Application problem.
Detailed description of the invention
Fig. 1 is process step figure of the multiple spurs from voiceprint authentication method of the embodiment of the present invention 1.
Specific embodiment
In order to make the above objects, features, and advantages of the present application more apparent, with reference to the accompanying drawing and it is specific real
Applying mode, the present application will be further described in detail.
Embodiment 1
The embodiment of the invention provides a kind of multiple spurs from voiceprint authentication method, as shown in Fig. 1, has including walking as follows
It is rapid:
Step S1 obtains user in several range directions and registers voice, generate several voice moulds in registration process
Type completes registration;By taking several are three as an example, further instruction, specifically: user is registered into language in three range directions
Sound generates three speech models and obtains speech production the first voice mould of user when user and terminal distance are first distance
Type;When user and terminal distance are second distance, the second speech model of speech production of user is obtained, user is with terminal distance
Third apart from when, obtain the speech production third speech model of user, when user complete three times voice register after just complete registration;
Step S2 obtains voice messaging of the active user under a certain distance in verification process, and the voice messaging is
The voice messaging of speaker is obtained by identification vocal print;
Current speech information is compared marking by step S3 with several speech models respectively, is obtained corresponding several
Score value;Further, current speech information is compared with several speech models using PLDA algorithm by the present embodiment respectively
Marking.PLDA algorithm (Probabilistic Linear Discriminant Analysis) is also a kind of channel compensation calculation
Method, the also referred to as LDA algorithm of Probability Forms.
Step S4 will take score value soprano as final identification score, and be denoted as S;
S is compared by step S5 with the threshold value of setting, and when S is greater than or is more than or equal to given threshold, then judgement is current uses
Family is verified, and otherwise judges that current user authentication does not pass through.
Further, the acquisition user registers voice in several range directions specifically: respectively in several distances
The sound that user reads aloud setting paragraph is obtained under direction, and Application on Voiceprint Recognition is carried out by the sound to user and obtains voiceprint.
Several described range directions are at least one distance and/or at least one direction.
It should be noted that several of present invention meaning are one or more, multiple is two or two or more.Example
Such as, the distance between voice recognition device of the position of user X sounding and terminal is 10cm, when the position of user's X sounding is side
To A, obtains user X and register voice at this time as first registration voice, when the position of user's X sounding is direction B, acquisition user X
Register voice at this time as second registration voice.First registers voice and second to register voice can be different registration voices.
In order to further increase discrimination, the range direction is necessary for different distance, for example, the position of user's Y sounding
The distance between voice recognition device of terminal is 15cm, and when the position of user's Y sounding is direction A, acquisition user Y is infused at this time
Volume voice is first registration voice, and the distance between the position of user's Y sounding and the voice recognition device of terminal are 20cm, when
The position of user's Y sounding is direction A, obtains user Y and registers voice at this time as second registration voice.
It should be noted that different distance direction can be the different distance same direction, same distance different directions, difference
Apart from different directions.
In order to which the present invention is well understood, the method for the present invention is being registered so that user A is by carrying out mobile telephone registration APP as an example
In the process, user is obtained to be briefly described for three range directions register voice.
During APP registration, user A reads n (n >=1) all over voice at 15cm (from mobile phone), and voice registration generates
First model, is denoted as M1;User A reads n (n >=1) all over voice at 35cm (from mobile phone), and voice registration generates the second model,
It is denoted as M2;User A reads n (n >=1) all over voice at 65cm (from mobile phone), and voice registration generates third model, is denoted as M3, this
User A generates the model of three different distances altogether.It should be noted that user A is at 15cm, at 35cm, at 65cm, not
It is what fixed position carried out, user A can choose at random three different distances and carry out voice registration.
During verifying, user A inputs voice under a certain distance, which is compared with M1, M2, M3 respectively
Marking is corresponding to obtain marking S1, S2, S3, and takes score value soprano as final identification score, is denoted as S.Wherein, the voice and M1
It is compared marking and obtains marking value S1, which is compared marking with M2 and obtains marking value S2, which is compared with M3
Marking value S3 is obtained compared with marking.
In embodiments of the present invention, it is preferable that marking refers to depositing in vocal print feature and speech model by active user
The vocal print feature of storage is compared to obtain similarity score.
If S is greater than or is more than or equal to threshold value, judgement is verified, otherwise verifies and do not pass through.It should be noted that this
A threshold value is fixed according to model itself.
In order to promote the accuracy of registration process, the voice that user reads aloud can be repeated several times and read aloud, it is ensured that voiceprint extraction
Accuracy, indirectly promoted verifying accuracy.
It should be noted that the embodiment of the present invention carries out letter to the method for the present invention so that three range directions register voice as an example
Illustrate, be not intended as the restriction of the method for the present invention certainly, several range directions of the invention register voice, are not limited to three
Range direction, it is of the invention it is several refer to one or more, theoretically number is The more the better, but in practical applications, can
To select several range direction registration voices according to usage scenario.
Embodiment 2
The embodiment of the invention provides a kind of multiple spurs from voiceprint authentication method, has and includes the following steps:
In registration process, user is obtained in 4 range directions and registers voice, corresponding 4 speech models is generated, completes
Registration;When being first distance direction i.e. between user and access control and attendance equipment, user is registered into voice in first range direction,
Obtain the first speech model of speech production of user;When being second distance direction between user and access control and attendance equipment, by user
Voice is registered in second range direction, obtains the second speech model of speech production of user;User and access control and attendance equipment it
Between be third range direction when, by user third range direction registration voice, obtain the speech production third voice of user
Model;When being four range directions between user and access control and attendance equipment, user is registered into voice in the 4th range direction, is obtained
Take the 4th speech model of speech production at family;
In verification process, voice messaging of the active user under a certain distance is obtained, the voice messaging is to pass through knowledge
Other vocal print obtains the voice messaging of speaker;
Current speech information is compared marking with 4 speech models respectively, obtains corresponding 4 score values, respectively
Current speech information is compared marking with the first speech model and obtains the first score value A1, current speech information and the second voice mould
Type is compared marking and obtains the second score value A2, and current speech information is compared marking with third speech model and obtains third point
Value A3, current speech information are compared marking with the 4th speech model and obtain quartile A4;Four score values are obtained to be averaged
Value Z, i.e. Z=(A1+A2+A3+A4)/4;Or be, it is of course also possible to obtain wherein maximum score value and the second largest score value carry out it is flat
Mean value is Z2, and current speech information is compared marking using cosine algorithm with 4 speech models respectively by the present embodiment.
Cosine algorithm is cosine similarity algorithm, similar between them to measure by measuring the cosine value of angle of two vectors
Property.
The average value Z of four score values is compared by step S5 with the threshold value of setting, when Z is greater than or is more than or equal to setting
Threshold value then judges that current user authentication passes through, otherwise judges that current user authentication does not pass through.It or is maximum score value and second
It is that Z2 is compared with the threshold value of setting that big score value, which carries out average value, and when Z2 is greater than or is more than or equal to given threshold, then judgement is worked as
Preceding user's checking passes through.
Embodiment 3
The embodiment of the invention discloses a kind of terminals, it is preferable that the terminal is mobile terminal, such as smart phone, IPAD
Deng the terminal includes: processor, memory and is stored on the memory and can run on the processor more
Proving program apart from voiceprint registration realizes that multiple spurs is recognized from vocal print when the Auto-matching payment program is executed by the processor
The step of card method.
The multiple spurs includes the following steps: from voiceprint authentication method
In registration process, user is obtained in several range directions and registers voice, several speech models is generated, completes
Registration;
In verification process, voice messaging of the active user under a certain distance is obtained, the voice messaging is to pass through knowledge
Other vocal print obtains the voice messaging of speaker;Current speech information is compared marking with several speech models respectively, is obtained
Obtain several score values accordingly;
Current speech information is compared marking with several speech models respectively, obtains corresponding several score values, root
Active user is verified according to several score values.
It is described that active user is verified according to several score values further include:
Score value soprano will be taken as final identification score, and be denoted as S;S is compared with the threshold value of setting, when S is big
In or more than or equal to given threshold, then judges that current user authentication passes through, otherwise judge that current user authentication does not pass through.
Further, the acquisition user registers voice in several range directions specifically: respectively in several distances
The sound that user reads aloud setting paragraph is obtained under direction, and Application on Voiceprint Recognition is carried out by the sound to user and obtains voiceprint.
Further, several described range directions are two range directions or multiple range directions.
Wherein the specific embodiment with multiple spurs described in embodiment 1 of the Auto-matching method of payment are from voiceprint authentication method phase
Together, details are not described herein for the embodiment of the present invention.In addition to above-mentioned smart phone, the mobile terminal of IPAD, present invention may also apply to
More scenes, such as phone, application program app, gate inhibition or attendance checking system, intelligent sound, robot, Intelligent bracelet etc..
It will be understood by those skilled in the art that the memory includes but is not limited to random access memory, flash memory, read-only storage
Device, programmable read only memory, volatile memory, nonvolatile memory, serial storage, parallel storage or register
Deng;The processor can be central processing unit (Central Processing Unit, CPU), controller, microcontroller, micro-
Processor or other data processing chips.
Embodiment 4
The embodiment of the invention discloses a kind of server, the server includes: processor, memory and is stored in institute
Proving program of the multiple spurs from voiceprint registration stated on memory and can run on the processor, the Auto-matching pay journey
The step of multiple spurs is from voiceprint authentication method is realized when sequence is executed by the processor.
The multiple spurs includes the following steps: from voiceprint authentication method
In registration process, user is obtained in several range directions and registers voice, several speech models is generated, completes
Registration;
In verification process, voice messaging of the active user under a certain distance is obtained, the voice messaging is to pass through knowledge
Other vocal print obtains the voice messaging of speaker;Current speech information is compared marking with several speech models respectively, is obtained
Obtain several score values accordingly;
Current speech information is compared marking with several speech models respectively, obtains corresponding several score values, root
Active user is verified according to several score values.
It is described that active user is verified according to several score values further include:
Score value soprano will be taken as final identification score, and be denoted as S;S is compared with the threshold value of setting, when S is big
In or more than or equal to given threshold, then judges that current user authentication passes through, otherwise judge that current user authentication does not pass through.
Further, the acquisition user registers voice in several range directions specifically: respectively in several distances
The sound that user reads aloud setting paragraph is obtained under direction, and Application on Voiceprint Recognition is carried out by the sound to user and obtains acoustic information.
Further, several described range directions are at least one distance and/or at least one direction.
Wherein the specific embodiment with multiple spurs described in embodiment 1 of the Auto-matching method of payment are from voiceprint authentication method phase
Together, details are not described herein for the embodiment of the present invention.
It will be understood by those skilled in the art that the memory includes but is not limited to random access memory, flash memory, read-only storage
Device, programmable read only memory, volatile memory, nonvolatile memory, serial storage, parallel storage or register
Deng;The processor can be central processing unit (Central Processing Unit, CPU), controller, microcontroller, micro-
Processor or other data processing chips.
Embodiment 5
The embodiment of the invention discloses a kind of computer readable storage medium, stored on the computer readable storage medium
There is proving program of the multiple spurs from voiceprint registration, the multiple spurs is realized when being executed from the proving program of voiceprint registration by the processor
The step of multiple spurs is from voiceprint authentication method.The Auto-matching method of payment is multiple spurs described in embodiment 1 from voiceprint authentication method,
Details are not described herein.
The computer readable storage medium include but is not limited to flash memory, hard disk, multimedia card, card-type memory (for example,
SD or DX memory etc.), random access storage device (Random Access Memory, RAM), static random-access memory
(Static Random-Access Memory, SRAM), read-only memory (Read Only Memory, ROM), electric erasable
Programmable read only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM),
Programmable read only memory (Programmable Read-Only Memory, PROM), magnetic storage, disk, CD etc.
Non-volatile memory medium.
The foregoing is merely the embodiments of description of the invention one or more embodiment, are not limited to this hair
Bright specification one or more embodiment.To those skilled in the art, description of the invention one or more embodiment
There can be various modifications and variations.All any modification, equivalent replacement, improvement within the spirit and principles of the present application
Deng should be included within scope of the claims.
Claims (8)
1. a kind of multiple spurs is from voiceprint authentication method, which comprises the steps of:
In registration process, user is obtained in several range directions and registers voice, several speech models is generated, completes note
Volume;
In verification process, voice messaging of the active user under a certain distance is obtained, the voice messaging is to pass through identification sound
The voice messaging of line acquisition speaker;
Current speech information is compared marking with several speech models respectively, obtains corresponding several score values, if according to
Dry score value verifies active user.
2. multiple spurs according to claim 1 is from voiceprint authentication method, which is characterized in that
It is described that active user is verified according to score value soprano further include:
Score value soprano will be taken as final identification score, final identification score will be compared with the threshold value of setting, when final
Identification score is greater than or is more than or equal to given threshold, then judges that current user authentication passes through, otherwise judge current user authentication not
Pass through.
3. multiple spurs according to claim 1 is from voiceprint authentication method, which is characterized in that
It obtains user and registers voice in several range directions specifically:
The sound that user reads aloud setting paragraph is obtained under several range directions respectively, vocal print is carried out by the sound to user
Identification obtains voiceprint.
4. multiple spurs according to claim 1 is from voiceprint authentication method, which is characterized in that
Several described range directions are at least one distance and/or at least one direction.
5. multiple spurs according to claim 1 is from voiceprint authentication method, which is characterized in that
Current speech information is given a mark with several speech models using cosine algorithm or PLDA algorithm respectively.
6. a kind of terminal, which is characterized in that
The terminal includes: processor, memory and is stored on the memory and can run on the processor
Proving program of the multiple spurs from voiceprint registration realizes such as claim when the Auto-matching payment program is executed by the processor
The step of multiple spurs described in any one of 1 to 5 is from voiceprint authentication method.
7. a kind of server, which is characterized in that
The server includes: processor, memory and is stored on the memory and can run on the processor
Proving program of the multiple spurs from voiceprint registration, when the Auto-matching payment program is executed by the processor realize as right is wanted
The step of multiple spurs described in asking any one of 1 to 5 is from voiceprint authentication method.
8. a kind of computer readable storage medium, which is characterized in that
Proving program of the multiple spurs from voiceprint registration is stored on the computer readable storage medium, the multiple spurs is from voiceprint registration
Proving program realize when being executed by processor the multiple spurs as described in any one of claims 1 to 5 from voiceprint authentication method
Step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910328466.7A CN110086629A (en) | 2019-04-23 | 2019-04-23 | A kind of multiple spurs is from voiceprint authentication method, terminal, server and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910328466.7A CN110086629A (en) | 2019-04-23 | 2019-04-23 | A kind of multiple spurs is from voiceprint authentication method, terminal, server and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110086629A true CN110086629A (en) | 2019-08-02 |
Family
ID=67416242
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910328466.7A Withdrawn CN110086629A (en) | 2019-04-23 | 2019-04-23 | A kind of multiple spurs is from voiceprint authentication method, terminal, server and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110086629A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110600040A (en) * | 2019-09-19 | 2019-12-20 | 北京三快在线科技有限公司 | Voiceprint feature registration method and device, computer equipment and storage medium |
CN110807630A (en) * | 2019-09-19 | 2020-02-18 | 平安科技(深圳)有限公司 | Payment method and device based on face recognition, computer equipment and storage medium |
CN112634909A (en) * | 2020-12-15 | 2021-04-09 | 北京百度网讯科技有限公司 | Method, device, equipment and computer readable storage medium for sound signal processing |
US20210110273A1 (en) * | 2019-10-10 | 2021-04-15 | Samsung Electronics Co., Ltd. | Apparatus and method with model training |
-
2019
- 2019-04-23 CN CN201910328466.7A patent/CN110086629A/en not_active Withdrawn
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110600040A (en) * | 2019-09-19 | 2019-12-20 | 北京三快在线科技有限公司 | Voiceprint feature registration method and device, computer equipment and storage medium |
CN110807630A (en) * | 2019-09-19 | 2020-02-18 | 平安科技(深圳)有限公司 | Payment method and device based on face recognition, computer equipment and storage medium |
CN110600040B (en) * | 2019-09-19 | 2021-05-25 | 北京三快在线科技有限公司 | Voiceprint feature registration method and device, computer equipment and storage medium |
CN110807630B (en) * | 2019-09-19 | 2022-06-17 | 平安科技(深圳)有限公司 | Payment method and device based on face recognition, computer equipment and storage medium |
US20210110273A1 (en) * | 2019-10-10 | 2021-04-15 | Samsung Electronics Co., Ltd. | Apparatus and method with model training |
CN112634909A (en) * | 2020-12-15 | 2021-04-09 | 北京百度网讯科技有限公司 | Method, device, equipment and computer readable storage medium for sound signal processing |
CN112634909B (en) * | 2020-12-15 | 2022-03-15 | 北京百度网讯科技有限公司 | Method, device, equipment and computer readable storage medium for sound signal processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110086629A (en) | A kind of multiple spurs is from voiceprint authentication method, terminal, server and storage medium | |
CN108417217B (en) | Speaker recognition network model training method, speaker recognition method and system | |
US10635893B2 (en) | Identity authentication method, terminal device, and computer-readable storage medium | |
JP6682523B2 (en) | Voiceprint authentication processing method and apparatus | |
CN109166586B (en) | Speaker identification method and terminal | |
CN102915731B (en) | A kind of method and device of the speech recognition of personalization | |
US7873189B2 (en) | Face recognition by dividing an image and evaluating a similarity vector with a support vector machine | |
CN110164453A (en) | A kind of method for recognizing sound-groove, terminal, server and the storage medium of multi-model fusion | |
CN102270450B (en) | System and method of multi model adaptation and voice recognition | |
US20170110125A1 (en) | Method and apparatus for initiating an operation using voice data | |
CN109360572B (en) | Call separation method and device, computer equipment and storage medium | |
WO2019136912A1 (en) | Electronic device, identity authentication method and system, and storage medium | |
US20140341443A1 (en) | Joint modeling for facial recognition | |
US11545154B2 (en) | Method and apparatus with registration for speaker recognition | |
CN103337241B (en) | Voice recognition method and device | |
CN111079791A (en) | Face recognition method, face recognition device and computer-readable storage medium | |
CN109002784B (en) | Street view identification method and system | |
Ben-Harush et al. | Initialization of iterative-based speaker diarization systems for telephone conversations | |
CN110556126A (en) | Voice recognition method and device and computer equipment | |
CN106062871A (en) | Training classifiers using selected cohort sample subsets | |
JP2014071813A (en) | Character recognition device and program | |
CN110111798A (en) | A kind of method and terminal identifying speaker | |
CN110263726B (en) | Finger vein identification method and device based on deep correlation feature learning | |
CN109448732A (en) | A kind of digit string processing method and processing device | |
CN106205610B (en) | A kind of voice information identification method and equipment |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190802 |