CN103078828A - Cloud-model voice authentication system - Google Patents
Cloud-model voice authentication system Download PDFInfo
- Publication number
- CN103078828A CN103078828A CN 201110327622 CN201110327622A CN103078828A CN 103078828 A CN103078828 A CN 103078828A CN 201110327622 CN201110327622 CN 201110327622 CN 201110327622 A CN201110327622 A CN 201110327622A CN 103078828 A CN103078828 A CN 103078828A
- Authority
- CN
- China
- Prior art keywords
- user
- voice
- service
- authentication
- sound
- 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
Images
Abstract
The invention discloses a cloud-model voice authentication system, comprising a sound acquisition module, a voiceprint registration module, a service logic module, a voiceprint verification service module and the like. According to the invention, after a user registers user information and sound information in a system, the system acquires a user sound sample characteristic to be saved as voiceprint data, meanwhile, the system encapsulates a voiceprint comparison function into a network service to be supplied to the system for usage, after acquiring user sound data, an authentication function module provides sound sample data to request a system voiceprint identification service for carrying out voice and voiceprint identification, and the user identity is judged according to an identification result for carrying out authentication. According to the invention, based on acquisition and identification of sound and voiceprint, the authentication function similar to a fingerprint pattern is realized, and a simple and rapid remote authentication identification service is provided.
Description
Technical field
The present invention relates to the technical fields such as systems soft ware and speech recognition, refer to especially a kind of voice right discriminating system of cloud mode.
Background technology
Along with Internet technology, the particularly development of Internet technology and software engineering is for the right discriminating system of voice-based Application on Voiceprint Recognition provides feasibility.
Traditional authentication pattern is verified by the user name pin mode at present, there are certain security risk in user name and pin mode, the possibility that has information leakage, development along with biological identification technology, especially the development of speech recognition and sound groove recognition technology in e, for the authentication based on the bio-identification mode provides feasibility, simultaneously, the development of cloud computing technology, for obtaining of various remote functionalitys provides condition, carry out authentication in conjunction with cloud computing technology and biological identification technology, further improved the fail safe of authentication.
In view of this, the object of the invention is to propose the voice right discriminating system of a kind of cloud mode of a kind of speech recognition in conjunction with cloud computing technology and Application on Voiceprint Recognition.
Summary of the invention
Can find out from above, the voice right discriminating system of a kind of cloud mode provided by the invention, by randomly drawing speech verification problem and answer, the registered user realizes the voice right discriminating system of a kind of cloud mode that a kind of fail safe is higher by understanding phonetic problem and answering judgement that rear system carries out answer content and recognition and verification user identity that phonetic feature is vocal print and the answer of validation problem.
Have the following advantages specifically:
Living things feature recognition:
Based on the Application on Voiceprint Recognition of phonetic feature, possess the uniqueness recognition function with the similar bio-identification of fingerprint, can substitute the password under the general application scenarios, safe and reliable.
Easy to use:
The simple problem that simply answer system of user randomly draws can be identified and authentication, the occupation mode simple and fast.
Cloud mode is used:
Based on the application of cloud service pattern, speech recognition and vocal print recognition function are embedded and be coupled in the various application systems, autgmentability is strong, and application mode is flexible.
Random anti-counterfeit:
System randomly draws problem and requires the user to carry out voice answering, and system carries out the identification of voice content, with the attack of the broadcast mode that prevents from recording, the fail safe that has effectively improved system applies.
Description of drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, consists of the application's a part, and illustrative examples of the present invention and explanation thereof are used for explaining the present invention, do not consist of improper restriction of the present invention.In the accompanying drawings:
Fig. 1 is the schematic diagram of system module structure of the present invention.
Fig. 2 is operation flow schematic diagram of the present invention.
Embodiment
With reference to the accompanying drawings the present invention is described more fully, exemplary embodiment of the present invention wherein is described.
A kind of voice right discriminating system of cloud mode has been proposed for achieving the above object.
Below in conjunction with the drawings, embodiments of the present invention are described.
The key point of voice right discriminating system that realizes a kind of cloud mode is as follows:
Application on Voiceprint Recognition:
Speech parameter by extracting reflection speaker's physiology and behavioural characteristic in the speech waveform is identified based on the biological characteristic of sound as the sound biological characteristic, possesses and the similar function of fingerprint recognition, automatically identifies speaker ' s identity.
Speech recognition:
In order to prevent the machine playback, system carries out the extraction of stochastic problem and requires the user to answer simple question, and answers the identification checking that voice carry out content based on the user.
Cloud service:
System encapsulates Application on Voiceprint Recognition and speech recognition in the cloud service mode, use to system by service interface and network opening, carries out the lightweight coupling between system and the service, has expanded the ductility of system.
User rs authentication:
The variety of issue that preserve in system randomness extracted data storehouse, require the user to carry out the answer of voice, the system acquisition user speech and carry out the identification of content after the accuracy of authentication of users vocal print and answer content, think then that unanimously checking passes through, prevent with this that recording from playing and attack.
Main functional modules
As shown in Figure 1, a kind of system configuration of voice right discriminating system of cloud mode mainly comprises:
User's side:
Speech ciphering equipment 100:
The user side speech sound access equipment comprises phone, and portable terminal with the apparatus such as computer of phonetic function, can be linked into the system voice platform.
Audio access 101:
Be used for being linked into the access module of system voice system, user's speech ciphering equipment is linked into the system voice platform by transmission channel.
Transmission channel 102:
The passage of audio access and transmission is provided, comprises telephone network, the physical channels such as broadband data network are for user's audio access and the transmission of speech data provide passage.
System side:
Management configuration module 103
The system management function module comprises user management, and the various management functions such as logic manage, parameter configuration are carried out various management and configuration to system.
Voice interface module 104:
User's access system speech interface is provided, user speech is linked into each function service module of system by interface and the redirect of the voice flow of service based logic is provided.
Validation database 105:
The data management container of various validation problems and answer is provided, and the basic function of various databases is provided.
Voice print database 106:
It is the data management container of vocal print data that the voice biometric feature of various user's registrations is provided, and the basic function of various databases is provided.
Verification msg extracts 107:
Be responsible for randomly drawing validation problem and answer from validation database, offer the authentication functions module and carry out the problem checking.
Validation Answer Key checking 108:
Carry out the checking of answer according to the service logic of authentication functions module and the content of the voice answering data identification that provides according to the user, and the result that will verify offers the authentication logic module.
Data under voice 109:
Be responsible for to gather the speech data of user's access, and the speech data that gathers is offered other relevant functional modules, such as sound identification module etc.
Authentication logic processing module 110
Be responsible for the execution andlogic control of the service logic flow process of authentication, the service parameter service control logic flow according to different comprises the authentication business, and speech play flow process control etc. are judged the result of subscription authentication and authenticating result offered the system module of response.
Voice synthetic module 111:
The validation problem data communication device that extracts is crossed voice synthetic module play, the translation function of Text To Speech is provided, the user gets access to the validation problem of system plays by voice mode.
Sound identification module 111:
Be responsible for the user voice data that voice acquisition module is obtained is carried out the identification of voice content, provide the translation function of speech-to-text, and the result that will identify offer the comparison that the Validation Answer Key authentication module carries out user's answer content.
Voiceprint identification module 112:
Responsible user's vocal print data are registered and the user voice data that voice acquisition module is obtained are carried out the identification of user speech vocal print, and carry out comparing to differentiate user identity with voice print database.
System's door 113:
System user is logined the door of the system of door, and interface that the user uses system and the carrying of miscellaneous service flow process are provided.
The below gives one example to illustrate the identification authentication workflow of the voice that the present invention is based on cloud mode, and among this embodiment, business may further comprise the steps:
Prerequisite: the user is in system registry, system registry user's phonetic feature as the vocal print data.
Step 1: the user possesses the mode access system of voice transmission capabilities, access system login page by network or phone etc.;
Step 2: system randomly draws validation problem, and voice mode plays to the user, and prompting user carries out the answer of validation problem;
Step 3: after the user hears the problem of system, carry out the answer of voice mode;
Step 4. system acquisition and recording user voice content carry out the identification of vocal print and voice content;
The comparison user of step 5. system vocal print data are carried out the affirmation of user identity;
Step 6. system identification user speech content is carried out the affirmation of problem answers;
The comparison result that step 7. is answered a question according to Application on Voiceprint Recognition identity and user, system judges whether this user's login is correct.
Step 8. is according to system's judged result, and the user enters into system or prompting user logon error information, and prompting user carries out register again.
Description of the invention is in order to provide for the purpose of example and the explanation, and is not exhaustively or limit the invention to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Selecting and describing embodiment is for better explanation principle of the present invention and practical application, thereby and makes those of ordinary skill in the art can understand the various embodiment with various modifications that the present invention's design is suitable for special-purpose.
Claims (5)
1. the voice right discriminating system of a cloud mode, it is characterized in that, the user is in system registry user profile and the sample sound data are provided, system analyzes and processes the feature of extraction sound as the vocal print data, and become remote service to offer system the Application on Voiceprint Recognition function package to use, system is by randomly drawing the system verification problem and require the user to answer during authentication, and subscription client obtains after the user voice data by cloud mode Application on Voiceprint Recognition and voice content identification and according to recognition result and carries out authentication.
2. as claimed in claim 1, the user needs information of registered users and acoustic information, it is characterized in that, user's information of registered users, comprise user name, the information such as password, and the voice data sample is provided, system carries out analysis and the processing of sound, and the characteristic of extracting sound is saved in database and carries out related with user identity.
3. as claimed in claim 1, system is called with method of service after the Application on Voiceprint Recognition function is encapsulated, it is characterized in that, the voice data that system provides user registration extracts after the characteristic value as the vocal print data, and will identify the user voice function and open as method of service, system is called by Local or Remote cloud service invocation pattern Request System.
4. as claimed in claim 3, system carries out user's authentication and identification by the cloud service of request Application on Voiceprint Recognition, it is characterized in that, user side embeds sound collection module and service request module, such as microphone and sound collection module, the user is when carrying out authentication, and system issues validation problem and gathers user voice data by client terminal system, these data as the request of analyzing samples initiation to the service of system cloud Application on Voiceprint Recognition, after processing and identify, system are turned back to the third party system with the result.
5. as claimed in claim 4, system extracts stochastic problem and requires the user to answer, it is characterized in that for preventing the deception of record type, system randomly draws system verification storehouse validation problem data, require the user to require to answer according to problem, by stochastic problems and answer, guarantee the non-machine operation of user side, simultaneously, the system voice recognition function is identified the voice content of user's answer and is compared with the validation problem answer, and comparison vocal print and voice content can think just that correctly this authentication is successful.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110327622 CN103078828A (en) | 2011-10-25 | 2011-10-25 | Cloud-model voice authentication system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110327622 CN103078828A (en) | 2011-10-25 | 2011-10-25 | Cloud-model voice authentication system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103078828A true CN103078828A (en) | 2013-05-01 |
Family
ID=48155237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110327622 Pending CN103078828A (en) | 2011-10-25 | 2011-10-25 | Cloud-model voice authentication system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103078828A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325037A (en) * | 2013-06-06 | 2013-09-25 | 上海讯联数据服务有限公司 | Mobile payment safety verification method based on voice recognition |
| CN103442290A (en) * | 2013-08-15 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Information providing method and system based on television terminal users and voices |
| CN104038509A (en) * | 2014-07-03 | 2014-09-10 | 南昌欧菲生物识别技术有限公司 | Fingerprint authentication cloud system |
| CN104219303A (en) * | 2014-09-01 | 2014-12-17 | 广东安居宝数码科技股份有限公司 | Access control verification method and access control verification system |
| CN106357520A (en) * | 2016-10-21 | 2017-01-25 | 北京小米移动软件有限公司 | Instant messaging method and instant messaging device |
| CN107393541A (en) * | 2017-08-29 | 2017-11-24 | 百度在线网络技术（北京）有限公司 | Information Authentication method and apparatus |
| CN108734470A (en) * | 2018-05-07 | 2018-11-02 | 陕西科技大学 | A kind of device and method differentiating the IC card true and false |
| CN109003612A (en) * | 2018-06-08 | 2018-12-14 | 英业达科技有限公司 | Voice response based on artificial intelligence verifies system and method |
| WO2019037205A1 (en) * | 2017-08-24 | 2019-02-28 | 平安科技（深圳）有限公司 | Voice fraud identifying method and apparatus, terminal device, and storage medium |
| CN110574103A (en) * | 2018-06-29 | 2019-12-13 | 华为技术有限公司 | Voice control method, wearable device and terminal |
-
2011
- 2011-10-25 CN CN 201110327622 patent/CN103078828A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325037A (en) * | 2013-06-06 | 2013-09-25 | 上海讯联数据服务有限公司 | Mobile payment safety verification method based on voice recognition |
| CN103442290A (en) * | 2013-08-15 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Information providing method and system based on television terminal users and voices |
| CN104038509A (en) * | 2014-07-03 | 2014-09-10 | 南昌欧菲生物识别技术有限公司 | Fingerprint authentication cloud system |
| CN104219303B (en) * | 2014-09-01 | 2017-12-05 | 广东安居宝数码科技股份有限公司 | Gate inhibition's verification method and system |
| CN104219303A (en) * | 2014-09-01 | 2014-12-17 | 广东安居宝数码科技股份有限公司 | Access control verification method and access control verification system |
| CN106357520A (en) * | 2016-10-21 | 2017-01-25 | 北京小米移动软件有限公司 | Instant messaging method and instant messaging device |
| WO2019037205A1 (en) * | 2017-08-24 | 2019-02-28 | 平安科技（深圳）有限公司 | Voice fraud identifying method and apparatus, terminal device, and storage medium |
| CN107393541A (en) * | 2017-08-29 | 2017-11-24 | 百度在线网络技术（北京）有限公司 | Information Authentication method and apparatus |
| CN107393541B (en) * | 2017-08-29 | 2021-05-07 | 百度在线网络技术（北京）有限公司 | Information verification method and device |
| CN108734470A (en) * | 2018-05-07 | 2018-11-02 | 陕西科技大学 | A kind of device and method differentiating the IC card true and false |
| CN109003612A (en) * | 2018-06-08 | 2018-12-14 | 英业达科技有限公司 | Voice response based on artificial intelligence verifies system and method |
| CN109003612B (en) * | 2018-06-08 | 2021-01-29 | 英业达科技有限公司 | Voice question-answer verification system and method based on artificial intelligence |
| CN110574103A (en) * | 2018-06-29 | 2019-12-13 | 华为技术有限公司 | Voice control method, wearable device and terminal |
| CN110574103B (en) * | 2018-06-29 | 2020-10-23 | 华为技术有限公司 | Voice control method, wearable device and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103078828A (en) | Cloud-model voice authentication system | |
| US8812319B2 (en) | Dynamic pass phrase security system (DPSS) | |
| US8396711B2 (en) | Voice authentication system and method | |
| US9571490B2 (en) | Method and system for distinguishing humans from machines | |
| US7222072B2 (en) | Bio-phonetic multi-phrase speaker identity verification | |
| CN105069874B (en) | A kind of mobile Internet sound-groove gate inhibition system and its implementation | |
| US7340042B2 (en) | System and method of subscription identity authentication utilizing multiple factors | |
| US8139723B2 (en) | Voice authentication system and method using a removable voice ID card | |
| EP2364495B1 (en) | Method for verifying the identify of a speaker and related computer readable medium and computer | |
| US8537978B2 (en) | Method and system for using conversational biometrics and speaker identification/verification to filter voice streams | |
| US9697836B1 (en) | Authentication of users of self service channels | |
| US11625467B2 (en) | Authentication via a dynamic passphrase | |
| CN102543084A (en) | Online voiceprint recognition system and implementation method thereof | |
| CN107886958A (en) | A kind of express delivery cabinet pickup method and device based on vocal print | |
| RU2005133725A (en) | USER AUTHENTICATION BY COMBINING IDENTIFICATION OF TALING AND REVERSE TURING TEST | |
| EP1728244A2 (en) | Multiple choice challenge-response user authorization system and method | |
| CN102298929A (en) | Call center subscriber recognition method based on voice recognition | |
| US9462134B2 (en) | Method enabling verification of the user ID by means of an interactive voice response system | |
| CN104064062A (en) | On-line listening learning method and system based on voiceprint and voice recognition | |
| CN108417216A (en) | Speech verification method, apparatus, computer equipment and storage medium | |
| CN112417412A (en) | Bank account balance inquiry method, device and system | |
| CN110322890A (en) | A kind of identity recognition device | |
| CN208939994U (en) | Mobile device for long-distance identity-certifying | |
| CN117831142A (en) | Voice sign-in method, system, electronic equipment and storage medium | |
| Marzotti et al. | Biometric authentication using voice |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130501 |