CN105913850B - Text correlation vocal print method of password authentication - Google Patents
Text correlation vocal print method of password authentication Download PDFInfo
- Publication number
- CN105913850B CN105913850B CN201610246535.6A CN201610246535A CN105913850B CN 105913850 B CN105913850 B CN 105913850B CN 201610246535 A CN201610246535 A CN 201610246535A CN 105913850 B CN105913850 B CN 105913850B
- Authority
- CN
- China
- Prior art keywords
- user
- sound
- password
- vocal print
- model
- 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.)
- Active
Links
- 230000001755 vocal effect Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012795 verification Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000010835 comparative analysis Methods 0.000 claims description 2
- 239000010779 crude oil Substances 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- 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
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Collating Specific Patterns (AREA)
Abstract
A kind of text correlation vocal print method of password authentication, user is prompted to read aloud by generating character or character string at random, and compare and analyze the collected vocal print read aloud in audio and preset user's sound-groove model, when content is correct and vocal print is consistent, decision verification passes through.The present invention can ensure accuracy rate, safety and the real-time of recognition result, and user-friendly.
Description
Technical field
The present invention relates to a kind of technology of information security field, specifically a kind of text correlation vocal print password authentification side
Method.
Background technique
Application on Voiceprint Recognition (Voiceprint Recognition) is also referred to as Speaker Identification, is divided into speaker's identification and speaks
People's confirmation.The former is to judge that certain section of voice is which of several people say；And the latter is then whether to judge certain section of voice
It is described in particular person.Task is different, and used technology is also different.
Vocal print password authentification is a kind of application of speaker verification, and this method requires user to input voice, and confirms accordingly
Speaker's identity.User's registration and authentication generally use voice input (the text phase of fixed password text in this application
Close), voice content difference is eliminated, thus its vocal print is frequently more consistent, can obtain unrelated compared to text say accordingly
It talks about people and confirms better verification the verifying results.Common vocal print password often uses fixed number word string (classical mode) or random number at present
Word string, for the former, the feature of the latter's maximum is to can be good at preventing attack, the only a fews such as recording playback from can use
Text is unrelated.
The shortcomings that existing vocal print cipher verification technique include: text independent manner registration, verifying voice data it is more, test
Card process is slow, is not suitable for real-time, user's vocal print password authentification, and user experience is also poor；The relevant classical mode of text exists
The security risk being ravesdropping is more likely to the attack by recording playback；Random cipher prompt modes are as the related classical mould of text
A kind of modification of formula is not present content confidentiality, and declines relative to text correlation classical mode accuracy rate.Due to above-mentioned several
The respective disadvantage of kind scheme, Application on Voiceprint Recognition do not obtain large-scale application at this stage.
Summary of the invention
The present invention In view of the above shortcomings of the prior art, proposes a kind of text correlation vocal print method of password authentication, can
To ensure accuracy rate, safety and the real-time of recognition result, and it is user-friendly.
The present invention is achieved by the following technical solutions:
The present invention relates to a kind of text correlation vocal print method of password authentication, are used by generating character or character string prompt at random
Family is read aloud, and the collected vocal print read aloud in audio and preset user's sound-groove model are compared and analyzed, when interior
Decision verification passes through when appearance is correct and vocal print is consistent.
The vocal print refers to: vocal print is by acoustic signal feature and the unique voice of the extracted user of model method
Characteristic.
The sound-groove model refers to: the identity model established using the characteristics of speech sounds of user for it.
It is described default to refer to: when carrying out voiceprint registration, it is desirable that user says a self-defining character string as password,
Sound-groove model is established according to the voice messaging that user reads aloud, for calling when voice print verification.
The random generation refers to: the extraction section word from the self-defining character string as password of user preset at random
Symbol or partial character string, and the location expression of the partial character or partial character string is provided, prompt user to say the customized word
Symbol string and specific position character.
The comparative analysis refers to: comparing the voiceprint and its acoustics that the verifying audio extraction that user newly provides obtains
Similarity degree between model, similarity height then receive, otherwise refuse.
The location expression is used but is not limited to: partial character or partial character string are located at the phase in self-defining character string
To position.
The specific position is used but is not limited to: first character, last character or centre in self-defining character string
The character of any one or more position.
The present invention relates to a kind of systems for realizing the above method, comprising: user's sound-groove model database and difference are therewith
Connected voiceprint registration module, secret generation module and vocal print authentication module, in which: voiceprint registration module is by the vocal print of registration
Model is exported to user's sound-groove model database, and secret generation module generates password and prompts user's typing, voice print verification module
Sound-groove model extraction is carried out to the information of user's input, and carries out comparison with the sound-groove model prestored in model database.
Technical effect
Compared with prior art, the present invention due to each random content it is different, listener-in have no way of learning original password and
Combined method reduces the security risk for revealing password because meeting with eavesdropping, more avoids recording replay attack；Secondly, opposite
In random cipher prompt modes, there is content confidentiality, and accuracy rate is higher, and required registration audio time is short, identification is quasi-
True rate is high, and user experience is good.
Detailed description of the invention
Fig. 1 is present system structure chart；
Fig. 2 is flow chart of the present invention.
Specific embodiment
As shown in Figure 1, the present embodiment is related to a kind of text correlation vocal print password validation system, comprising: user's sound-groove model
Database and the voiceprint registration module being attached thereto respectively, secret generation module and vocal print authentication module, in which: voiceprint registration
Module exports the sound-groove model of registration to user's sound-groove model database, and secret generation module generates password and prompts user
Typing, the information that voice print verification module inputs user carry out sound-groove model extraction, and with the vocal print that is prestored in model database
Model carries out comparison.
The voiceprint registration module includes: for acquiring the vocal print typing unit of user's voiceprint, according to collecting
Voiceprint be user's model training unit for establishing sound-groove model and being stored in user's sound-groove model database.
The secret generation module includes: for choosing the random site generation unit of random site, for determining
The description of the position of selection, such as the 4th or 2nd different description methods reciprocal location expression unit, for determining pair
Selected position is converted, such as selected location is that number can carry out the mapping mode generation unit and use that add 1 operation
In verification by first three module generate password description whether it is legal and output to user description legitimacy verifies unit.
The voice print verification module includes: Xinmi City's code conversion crude oil vocal print mould for being generated according to secret generation module
Type is the sound-groove model converter unit of the relevant sound-groove model of new password, is generated according to secret generation module for acquiring user
Password describes the user's checking typing unit of the voiceprint of the new password read and according to new model and user's checking vocal print
Information makes the voice print verification decision package for the decision for whether allowing user to verify by system.
As shown in Fig. 2, the present embodiment includes operating procedure in detailed below:
Step 1) voiceprint registration, vocal print typing unit acquire the customized password of multipass of user's typing.
The training of step 2) sound-groove model, model training unit are that user establishes sound-groove model according to collected voiceprint
And it is stored in user's sound-groove model database.
Step 3) is verified password and is generated, and is completed by four submodule cooperations of secret generation module: random site generation unit
Random site is chosen, location expression unit determines how to describe selected position, and it is how right that mapping mode generation unit determines
Selected position is converted, generate verifying password description, via description legitimacy verifies unit verification it is legal after will be final
Password description be transferred to sound-groove model converter unit and be prompted to user.
Step 4) is verified sound-groove model and is generated, and sound-groove model converter unit is responsible for the password generated according to secret generation module
Description transformation crude oil sound-groove model is the relevant sound-groove model of new password.
Step 5) user's voice print verification, the password that user's checking typing unit acquisition user generates according to secret generation module
The voiceprint of the new password read is described.Voice print verification decision-making module is made according to new model and user's checking voiceprint information
The decision for whether allowing user to verify by system out.
Use example one
When carrying out voiceprint registration, registration process is completed in the customized password of user " 234524 ", continuous typing three times.
When carrying out voice print verification, system prompt
" connecting method: suffix splicing
Location expression: bit digital second from the bottom
Mapping mode: nothing "
User reads " 2345242 ".Content is correct and vocal print is unanimously then verified, and otherwise system is refused.
Use example two
When carrying out voiceprint registration, registration process is completed in the customized password of user " 2345242 ", continuous typing three times.
2. carry out voice print verification, system prompt
" connecting method: prefix splicing
Location expression: the 1st bit digital
Mapping mode :+1 "
User reads " 3234524 ".Content is correct and vocal print is unanimously then verified, and otherwise system is refused.
Use example three
1. carry out voiceprint registration, registration process is completed in the customized password of user " 234524 ", continuous typing three times.
When carrying out voice print verification, system prompt
" connecting method: suffix splicing
Location expression: even number position digital
Mapping mode: nothing "
2. user reads " 234524354 ".Content is correct and vocal print is unanimously then verified, and otherwise system is refused.
Use example four
1. carry out voiceprint registration, the customized password of user " happy new year 121 ", continuous typing three times is completed to register
Journey.
When carrying out voice print verification, system prompt
" connecting method: suffix splicing
Location expression: first Chinese character
Mapping mode: nothing "
User reads " happy new year 121 new ".Content is correct and vocal print is unanimously then verified, and otherwise system is refused.
Above-mentioned specific implementation can by those skilled in the art under the premise of without departing substantially from the principle of the invention and objective with difference
Mode carry out local directed complete set to it, protection scope of the present invention is subject to claims and not by above-mentioned specific implementation institute
Limit, each implementation within its scope is by the constraint of the present invention.
Claims (5)
1. a kind of text correlation vocal print method of password authentication, which is characterized in that used by generating character or character string prompt at random
Family is read aloud, and the collected vocal print read aloud in audio and preset user's sound-groove model are compared and analyzed, when interior
Decision verification passes through when appearance is correct and vocal print is consistent；
The vocal print refers to: vocal print is special by acoustic signal feature and the unique voice of the extracted user of model method
Property；
The sound-groove model refers to: the identity model established using the characteristics of speech sounds of user for it；
It is described default to refer to: when carrying out voiceprint registration, it is desirable that user says a self-defining character string as password, according to
The voice messaging that user reads aloud establishes sound-groove model, for calling when voice print verification；
The described random generation refers to: at random from the self-defining character string as password of user preset extraction section character or
Partial character string, and the location expression of the partial character or partial character string is provided, prompt user to say the self-defining character string
And specific position character.
2. text correlation vocal print method of password authentication according to claim 1, characterized in that the comparative analysis is
Refer to: comparing the similarity degree between the voiceprint and its acoustic model that the verifying audio extraction that user newly provides obtains, it is similar
Degree height then receives, and otherwise refuses.
3. a kind of system for realizing method as claimed in claim 1 or 2 characterized by comprising user's sound-groove model database with
And voiceprint registration module, secret generation module and the vocal print authentication module being attached thereto respectively, in which: voiceprint registration module will be infused
The sound-groove model of volume is exported to user's sound-groove model database, and secret generation module generates password and prompts user's typing, sound
Line authentication module carries out sound-groove model extraction to the information that user inputs, and carries out with the sound-groove model prestored in model database
Comparison；
The secret generation module includes: for choosing the random site generation unit of random site, for selected by determination
Position description location expression unit, for determine the mapping mode generation unit that selected position is converted with
And for verify pass through first three module generate password description whether it is legal and output to user description legitimacy verifies list
Member.
4. system according to claim 3, characterized in that the voiceprint registration module includes: for acquiring user's sound
The vocal print typing unit of line information is that user establishes sound-groove model and is stored in user's sound-groove model according to collected voiceprint
Model training unit in database.
5. system according to claim 3, characterized in that the voice print verification module includes: for raw according to password
At the sound-groove model converter unit that the original sound-groove model of Xinmi City's code conversion that module generates is the relevant sound-groove model of new password, use
In the user's checking typing of the voiceprint for the new password that the password description that acquisition user generates according to secret generation module is read
The decision whether unit and being made according to new model and user's checking voiceprint information allows user to verify by system
Voice print verification decision package.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610246535.6A CN105913850B (en) | 2016-04-20 | 2016-04-20 | Text correlation vocal print method of password authentication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610246535.6A CN105913850B (en) | 2016-04-20 | 2016-04-20 | Text correlation vocal print method of password authentication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105913850A CN105913850A (en) | 2016-08-31 |
| CN105913850B true CN105913850B (en) | 2019-05-28 |
Family
ID=56746477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610246535.6A Active CN105913850B (en) | 2016-04-20 | 2016-04-20 | Text correlation vocal print method of password authentication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105913850B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106531171B (en) * | 2016-10-13 | 2020-02-11 | 普强信息技术（北京）有限公司 | Method for realizing dynamic voiceprint password system |
| CN107492379B (en) | 2017-06-30 | 2021-09-21 | 百度在线网络技术（北京）有限公司 | Voiceprint creating and registering method and device |
| 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 |
| CN109087647B (en) * | 2018-08-03 | 2023-06-13 | 平安科技（深圳）有限公司 | Voiceprint recognition processing method and device, electronic equipment and storage medium |
| CN109473107B (en) * | 2018-12-03 | 2020-12-22 | 厦门快商通信息技术有限公司 | Text semi-correlation voiceprint recognition method and system |
| CN111445904A (en) * | 2018-12-27 | 2020-07-24 | 北京奇虎科技有限公司 | Cloud-based voice control method and device and electronic equipment |
| CN110021307B (en) * | 2019-04-04 | 2022-02-01 | Oppo广东移动通信有限公司 | Audio verification method and device, storage medium and electronic equipment |
| CN110570869B (en) * | 2019-08-09 | 2022-01-14 | 科大讯飞股份有限公司 | Voiceprint recognition method, device, equipment and storage medium |
| CN110502886B (en) * | 2019-08-16 | 2022-05-27 | 广州国音智能科技有限公司 | Multiple identity authentication method, device, terminal and computer storage medium |
| CN110517695A (en) * | 2019-09-11 | 2019-11-29 | 国微集团(深圳)有限公司 | Verification method and device based on vocal print |
| CN111883141B (en) * | 2020-07-27 | 2022-02-25 | 重庆金宝保信息技术服务有限公司 | Text semi-correlation voiceprint recognition method and system |
| CN116612766B (en) * | 2023-07-14 | 2023-11-17 | 北京中电慧声科技有限公司 | Conference system with voiceprint registration function and voiceprint registration method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222502A (en) * | 2011-05-16 | 2011-10-19 | 上海先先信息科技有限公司 | Effective way for voice verification by Chinese text-prompted mode |
| CN102254559A (en) * | 2010-05-20 | 2011-11-23 | 盛乐信息技术（上海）有限公司 | Identity authentication system and method based on vocal print |
| CN102413100A (en) * | 2010-09-25 | 2012-04-11 | 盛乐信息技术（上海）有限公司 | Voice-print authentication system having voice-print password picture prompting function and realization method thereof |
| CN102543084A (en) * | 2010-12-29 | 2012-07-04 | 盛乐信息技术（上海）有限公司 | Online voiceprint recognition system and implementation method thereof |
| CN102708867A (en) * | 2012-05-30 | 2012-10-03 | 北京正鹰科技有限责任公司 | Method and system for identifying faked identity by preventing faked recordings based on voiceprint and voice |
| US9147400B2 (en) * | 2011-12-21 | 2015-09-29 | Sri International | Method and apparatus for generating speaker-specific spoken passwords |
-
2016
- 2016-04-20 CN CN201610246535.6A patent/CN105913850B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254559A (en) * | 2010-05-20 | 2011-11-23 | 盛乐信息技术（上海）有限公司 | Identity authentication system and method based on vocal print |
| CN102413100A (en) * | 2010-09-25 | 2012-04-11 | 盛乐信息技术（上海）有限公司 | Voice-print authentication system having voice-print password picture prompting function and realization method thereof |
| CN102543084A (en) * | 2010-12-29 | 2012-07-04 | 盛乐信息技术（上海）有限公司 | Online voiceprint recognition system and implementation method thereof |
| CN102222502A (en) * | 2011-05-16 | 2011-10-19 | 上海先先信息科技有限公司 | Effective way for voice verification by Chinese text-prompted mode |
| US9147400B2 (en) * | 2011-12-21 | 2015-09-29 | Sri International | Method and apparatus for generating speaker-specific spoken passwords |
| CN102708867A (en) * | 2012-05-30 | 2012-10-03 | 北京正鹰科技有限责任公司 | Method and system for identifying faked identity by preventing faked recordings based on voiceprint and voice |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105913850A (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105913850B (en) | Text correlation vocal print method of password authentication | |
| CN101231737B (en) | Method and system for enhancing internet bank trade security | |
| US7386448B1 (en) | Biometric voice authentication | |
| CN106373575B (en) | User voiceprint model construction method, device and system | |
| JP4213716B2 (en) | Voice authentication system | |
| CN105069874B (en) | A kind of mobile Internet sound-groove gate inhibition system and its implementation | |
| US8812319B2 (en) | Dynamic pass phrase security system (DPSS) | |
| CN105933323B (en) | Voiceprint registration, authentication method and device | |
| CN104217149B (en) | Biometric authentication method and equipment based on voice | |
| US8139723B2 (en) | Voice authentication system and method using a removable voice ID card | |
| JP2003058190A (en) | Personal authentication system | |
| KR20190045099A (en) | Voice Authentication System and Method | |
| CN103546622A (en) | Control method, device and system for identifying login on basis of voiceprint | |
| CN105933272A (en) | Voiceprint recognition method capable of preventing recording attack, server, terminal, and system | |
| US20060293898A1 (en) | Speech recognition system for secure information | |
| CN104064189A (en) | Vocal print dynamic password modeling and verification method | |
| JP2006505021A (en) | Robust multi-factor authentication for secure application environments | |
| EP3248188B1 (en) | Authentication method | |
| Saquib et al. | A survey on automatic speaker recognition systems | |
| CN102543084A (en) | Online voiceprint recognition system and implementation method thereof | |
| CN101685635A (en) | Identity authentication system and method | |
| CN104104664A (en) | Method, server, client and system for verifying verification code | |
| CN104462912B (en) | Improved biometric password security | |
| CN104269170B (en) | A kind of ERP authorities audio recognition method | |
| Turner et al. | Attacking speaker recognition systems with phoneme morphing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200617 Address after: Room 105G, 199 GuoShoujing Road, Pudong New Area, Shanghai, 200120 Patentee after: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. Address before: 200240 Dongchuan Road, Shanghai, No. 800, No. Patentee before: SHANGHAI JIAO TONG University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201028 Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: AI SPEECH Ltd. Address before: Room 105G, 199 GuoShoujing Road, Pudong New Area, Shanghai, 200120 Patentee before: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: Sipic Technology Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee before: AI SPEECH Ltd. |
|
| CP01 | Change in the name or title of a patent holder |