CN104183238A - Old people voiceprint recognition method based on questioning and answering - Google Patents
Old people voiceprint recognition method based on questioning and answering Download PDFInfo
- Publication number
- CN104183238A CN104183238A CN201410453940.6A CN201410453940A CN104183238A CN 104183238 A CN104183238 A CN 104183238A CN 201410453940 A CN201410453940 A CN 201410453940A CN 104183238 A CN104183238 A CN 104183238A
- Authority
- CN
- China
- Prior art keywords
- user
- social security
- voice
- elderly
- old people
- 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.)
- Granted
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention provides an old people voiceprint recognition method based on questioning and answering. An assigned telephone number is dialed to have access to a call center, a system obtains the telephone number and inquires the account number of the social security of a user, and if the inquiring process fails, the primary authentication is unsuccessful. If the authentication is successful, the system can prompt the user to continue to answer questions, all the questions are related to the common personal information, a background carries out the voice analysis according to the answer of the user, whether the voice is matched with the voiceprint in an original voice library or not is judged, and finally the identity of the user is judged. The social security system is characterized in that due to the facts that the old people are poor in language expression capability, the memory of the old people declines, and the old people are unlikely to say complex content integrally and clearly, the mode that only the common personal information is questioned is adopted; judgment is automatically carried out when the voice of the old people is obtained, the corresponding zooming-in and zooming-out operations are carried out according to different situations so as to obtain the clear and feasible voiceprint, the memory of the old people is facilitated to the greatest extent, and the recognition error is reduced.
Description
Technical field
The present invention relates to a kind of method for recognizing sound-groove, especially a kind of the elderly's method for recognizing sound-groove of replying based on enquirement.
Background technology
After social security socialization because employment unit resettlement, change, close, the reasons such as the retired strange land endowment, cause the personnel of insuring frequently flow, disperse.So determine that insurer's survival state is that social security pays a difficult problem in Claims Resolution work always, the situation that has occurred that successively the phenomenon that social insurance funds is falsely taken, especially endowment insurance money be falsely taken in all parts of the country is even more serious; In order to solve this difficult problem, need to use Application on Voiceprint Recognition this biotechnology, especially the elderly.But the error that this biotechnology of existing Application on Voiceprint Recognition is brought due to difference and the articulation problems etc. of various places dialect greatly reduces the discrimination of the decorum.
Summary of the invention
The technical issues that need to address of the present invention are to provide a kind of a kind of the elderly's method for recognizing sound-groove of replying based on enquirement that greatly improves Application on Voiceprint Recognition rate.
Technical matters to be solved by this invention realizes by the following technical solutions.
The elderly's social security sector of replying based on enquirement, comprises following steps:
(1) registration phase, user dials the number of specifying response center, and call center obtains user's telephone number, the social security account corresponding according to number searching, and checking;
(2) system is extracted user's personal information storage, guarantees that vocal print is corresponding one by one with account information;
(3) characteristic information the modeling of extracting vocal print according to identification sound bank, draw corresponding vocal print threshold information;
(4) cognitive phase, user dials the number of specifying response center, and call center obtains user's telephone number, the social security account corresponding according to number searching, and checking;
(5) be proved to be successful for the first time, system is randomly drawed the response message of problem recording user;
(6) system is carried out modeling processing to extracted voiceprint, according to model value contrast in existing sound bank, if threshold value is less than model value, is judged to be to identify successfully;
(7) system completes authentication process, finally identifies successfully just accessible social security service.
According to the functional module of digital speech card, user's number is write in remote data base.If there is the social security account corresponding with it in database, initial authentication is passed through, otherwise disconnects, and above rule is applicable to registration and cognitive phase.
The voice messaging extracting comprises that user registers voice, and user identifies voice.
Answer all relevant with individual general information problem at registration phase, only answer system the random problem proposing at cognitive phase.
Entering cognitive phase, according to user's telephone number, mating its social security account and extract corresponding identification voice threshold value.
Identification voice in system are carried out to eigenwert and extract and modeling, calculate the threshold value of identification voice and compare with the registration threshold size being written into.If the threshold value of identification voice is less than registration voice, i.e. identification is passed through.
The invention has the beneficial effects as follows, answer by arranging of such step and individual general information the Application on Voiceprint Recognition rate that improved.
Brief description of the drawings
Fig. 1: the extraction of characteristic parameter
Fig. 2: speech recognition system block diagram
Fig. 3: workflow diagram
Fig. 4: system topological figure
Embodiment
For technological means, creation characteristic that the present invention is realized, reach object and effect is easy to understand, below in conjunction with specific embodiment and diagram, further set forth the present invention.
A kind of concrete implementation step of the elderly's method for recognizing sound-groove of replying based on enquirement of the present invention is as follows:
(1) registration phase, user dials the number of specifying response center, and call center obtains user's telephone number, the social security account corresponding according to number searching, and checking;
(2) system is extracted user's personal information storage, guarantees that vocal print is corresponding one by one with account information;
(3) characteristic information the modeling of extracting vocal print according to identification sound bank, draw corresponding vocal print threshold information;
(4) cognitive phase, user dials the number of specifying response center, and call center obtains user's telephone number, the social security account corresponding according to number searching, and checking;
(5) be proved to be successful for the first time, system is randomly drawed the response message of problem recording user;
(6) system is carried out modeling processing to extracted voiceprint, according to model value contrast in existing sound bank, if threshold value is less than model value, is judged to be to identify successfully;
(7) system completes authentication process, finally identifies successfully just accessible social security service.
According to the functional module of digital speech card, user's number is write in remote data base.If there is the social security account corresponding with it in database, initial authentication is passed through, otherwise disconnects, and above rule is applicable to registration and cognitive phase.
The voice messaging extracting comprises that user registers voice, and user identifies voice.
Answer all relevant with individual general information problem at registration phase, only answer system the random problem proposing at cognitive phase.
The rule that arranges of relevant issues is: what all problems related to is all individual general information.As: " please after a sound of beep, saying your social security account " " please says your telephone number " " please after a sound of beep, saying your ID (identity number) card No. " etc. after a sound of beep.
Entering cognitive phase, according to user's telephone number, mating its social security account and extract corresponding identification voice threshold value.
Identification voice in system are carried out to eigenwert and extract and modeling, calculate the threshold value of identification voice and compare with the registration threshold size being written into.If the threshold value of identification voice is less than registration voice, i.e. identification is passed through.
In step (2) and (5), all adopt the problem relevant with individual general information to ask for the problem of the required answer of user, facilitate the elderly to answer.
The voiceprint using in step comprises registration voice and identification voice messaging.
Social security service object's vocal print authentication, be divided into two stages: the one, vocal print registration phase: may be under the supervision of community work personnel's scene, social security service object adopts the mode that interactive telephone phonetic is replied to register speech samples to system input, the vocal print characteristic sequence that system utilization is extracted from registration voice, for insurant builds sound-groove model; The 2nd, the voiceprint stage: social security service object can be required to do termly authentication conventionally, he/her can directly dial social security service hotline by movement/phone whenever and wherever possible so, under the voice message of far end system, reply and speak online, system is automatically enrolled the voice of insurant, carries out Application on Voiceprint Recognition authentication; In addition, the sound-groove model of insurant suitably be upgraded or adjust to system can, according to the situation of insurant voice identification authentication.
More than show and described ultimate principle of the present invention, principal character and advantage.The technician of the industry should understand; the present invention is not restricted to the described embodiments; that in above-described embodiment and instructions, describes just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.The claimed scope of the present invention is defined by appending claims and equivalent thereof.
Claims (8)
1. the elderly's method for recognizing sound-groove of replying based on enquirement, is characterized in that: comprise following steps:
(1) registration phase, user dials the number of specifying response center, and call center obtains user's telephone number, the social security account corresponding according to number searching, and checking;
(2) system is extracted user's personal information storage, guarantees that vocal print is corresponding one by one with account information;
(3) characteristic information the modeling of extracting vocal print according to identification sound bank, draw corresponding vocal print threshold information;
(4) cognitive phase, user dials the number of specifying response center, and call center obtains user's telephone number, the social security account corresponding according to number searching, and checking;
(5) be proved to be successful for the first time, system is randomly drawed the response message of problem recording user;
(6) system is carried out modeling processing to extracted voiceprint, according to model value contrast in existing sound bank, if threshold value is less than model value, is judged to be to identify successfully;
(7) system completes authentication process, finally identifies successfully just accessible social security service.
2. the elderly's social security sector of replying based on enquirement according to claim 1, is characterized in that: according to the functional module of digital speech card, user's number is write in remote data base.If there is the social security account corresponding with it in database, initial authentication is passed through, otherwise disconnects, and above rule is applicable to registration and cognitive phase.
3. the elderly's social security sector of replying based on enquirement according to claim 1, is characterized in that: the voice messaging extracting comprises that user registers voice, and user identifies voice.
4. the elderly's social security sector of replying based on enquirement according to claim 1, is characterized in that: answer all relevant with individual general information problem at registration phase, only answer system the random problem proposing at cognitive phase.
5. the elderly's social security sector of replying based on enquirement according to claim 4, is characterized in that: the rule that arranges of relevant issues is: all problems all arranges individual general information.
6. the elderly's social security sector of replying based on enquirement according to claim 1, is characterized in that: entering cognitive phase, according to user's telephone number, mating its social security account and extract corresponding identification voice threshold value.
7. the elderly's social security sector of replying based on enquirement according to claim 1, it is characterized in that: at cognitive phase, identification voice in system are carried out to eigenwert and extract and modeling, calculate the threshold value of identification voice and compare with the registration threshold size being written into.If the threshold value of identification voice is less than registration voice, i.e. identification is passed through.
8. the elderly's social security sector of replying based on enquirement according to claim 1, is characterized in that: in step (2) and (5), all adopt the problem relevant with individual general information to ask for the problem of the required answer of user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410453940.6A CN104183238B (en) | 2014-09-09 | 2014-09-09 | A kind of the elderly's method for recognizing sound-groove based on enquirement response |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410453940.6A CN104183238B (en) | 2014-09-09 | 2014-09-09 | A kind of the elderly's method for recognizing sound-groove based on enquirement response |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104183238A true CN104183238A (en) | 2014-12-03 |
| CN104183238B CN104183238B (en) | 2018-02-27 |
Family
ID=51964228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410453940.6A Expired - Fee Related CN104183238B (en) | 2014-09-09 | 2014-09-09 | A kind of the elderly's method for recognizing sound-groove based on enquirement response |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104183238B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157959A (en) * | 2015-03-31 | 2016-11-23 | 讯飞智元信息科技有限公司 | Sound-groove model update method and system |
| CN106488050A (en) * | 2015-09-01 | 2017-03-08 | 阿里巴巴集团控股有限公司 | Interactive voice answering method and system |
| CN107993662A (en) * | 2017-12-20 | 2018-05-04 | 广州势必可赢网络科技有限公司 | User identity identification method and device applied to telephone customer service |
| CN109462603A (en) * | 2018-12-14 | 2019-03-12 | 平安城市建设科技(深圳)有限公司 | Voiceprint authentication method, equipment, storage medium and device based on blind Detecting |
| CN109636630A (en) * | 2018-12-07 | 2019-04-16 | 泰康保险集团股份有限公司 | Method, apparatus, medium and electronic equipment of the detection for behavior of insuring |
| CN112465313A (en) * | 2020-11-13 | 2021-03-09 | 天津矿山工程有限公司 | Digital mine production scheduling method, system, terminal and storage medium |
| CN113411458A (en) * | 2021-05-21 | 2021-09-17 | 海南太美航空股份有限公司 | Travel information notification method, device, terminal and storage medium |
| WO2023016347A1 (en) * | 2021-08-13 | 2023-02-16 | 华为技术有限公司 | Voiceprint authentication response method and system, and electronic devices |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101256700A (en) * | 2008-03-31 | 2008-09-03 | 浙江大学城市学院 | ATM of mixed type user identification authentication |
| CN101572756A (en) * | 2008-04-29 | 2009-11-04 | 台达电子工业股份有限公司 | Dialogue system and voice dialogue processing method |
| CN102142254A (en) * | 2011-03-25 | 2011-08-03 | 北京得意音通技术有限责任公司 | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method |
| CN102298929A (en) * | 2010-06-23 | 2011-12-28 | 上海博路信息技术有限公司 | Call center subscriber recognition method based on voice recognition |
| WO2012024508A2 (en) * | 2010-08-18 | 2012-02-23 | Matthew Staker | Systems and methods for securing virtual machine computing environments |
| 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 |
| CN103258535A (en) * | 2013-05-30 | 2013-08-21 | 中国人民财产保险股份有限公司 | Identity recognition method and system based on voiceprint recognition |
| CN103501296A (en) * | 2013-09-27 | 2014-01-08 | 厦门天聪智能软件有限公司 | Social insurance survival authentication system based on voiceprint recognition technique and authentication method thereof |
-
2014
- 2014-09-09 CN CN201410453940.6A patent/CN104183238B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101256700A (en) * | 2008-03-31 | 2008-09-03 | 浙江大学城市学院 | ATM of mixed type user identification authentication |
| CN101572756A (en) * | 2008-04-29 | 2009-11-04 | 台达电子工业股份有限公司 | Dialogue system and voice dialogue processing method |
| CN102298929A (en) * | 2010-06-23 | 2011-12-28 | 上海博路信息技术有限公司 | Call center subscriber recognition method based on voice recognition |
| WO2012024508A2 (en) * | 2010-08-18 | 2012-02-23 | Matthew Staker | Systems and methods for securing virtual machine computing environments |
| CN102142254A (en) * | 2011-03-25 | 2011-08-03 | 北京得意音通技术有限责任公司 | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method |
| 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 |
| CN103258535A (en) * | 2013-05-30 | 2013-08-21 | 中国人民财产保险股份有限公司 | Identity recognition method and system based on voiceprint recognition |
| CN103501296A (en) * | 2013-09-27 | 2014-01-08 | 厦门天聪智能软件有限公司 | Social insurance survival authentication system based on voiceprint recognition technique and authentication method thereof |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157959A (en) * | 2015-03-31 | 2016-11-23 | 讯飞智元信息科技有限公司 | Sound-groove model update method and system |
| CN106157959B (en) * | 2015-03-31 | 2019-10-18 | 讯飞智元信息科技有限公司 | Sound-groove model update method and system |
| CN106488050A (en) * | 2015-09-01 | 2017-03-08 | 阿里巴巴集团控股有限公司 | Interactive voice answering method and system |
| CN106488050B (en) * | 2015-09-01 | 2019-06-07 | 阿里巴巴集团控股有限公司 | Interactive voice answering method and system |
| CN107993662A (en) * | 2017-12-20 | 2018-05-04 | 广州势必可赢网络科技有限公司 | User identity identification method and device applied to telephone customer service |
| CN109636630A (en) * | 2018-12-07 | 2019-04-16 | 泰康保险集团股份有限公司 | Method, apparatus, medium and electronic equipment of the detection for behavior of insuring |
| CN109462603A (en) * | 2018-12-14 | 2019-03-12 | 平安城市建设科技(深圳)有限公司 | Voiceprint authentication method, equipment, storage medium and device based on blind Detecting |
| CN112465313A (en) * | 2020-11-13 | 2021-03-09 | 天津矿山工程有限公司 | Digital mine production scheduling method, system, terminal and storage medium |
| CN112465313B (en) * | 2020-11-13 | 2022-08-26 | 天津矿山工程有限公司 | Digital mine production scheduling method, system, terminal and storage medium |
| CN113411458A (en) * | 2021-05-21 | 2021-09-17 | 海南太美航空股份有限公司 | Travel information notification method, device, terminal and storage medium |
| CN113411458B (en) * | 2021-05-21 | 2023-04-07 | 海南太美航空股份有限公司 | Travel information notification method, device, terminal and storage medium |
| WO2023016347A1 (en) * | 2021-08-13 | 2023-02-16 | 华为技术有限公司 | Voiceprint authentication response method and system, and electronic devices |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104183238B (en) | 2018-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104183238A (en) | Old people voiceprint recognition method based on questioning and answering | |
| US20230335116A1 (en) | Multi-user authentication on a device | |
| JP6394709B2 (en) | SPEAKER IDENTIFYING DEVICE AND FEATURE REGISTRATION METHOD FOR REGISTERED SPEECH | |
| US10777207B2 (en) | Method and apparatus for verifying information | |
| US9361891B1 (en) | Method for converting speech to text, performing natural language processing on the text output, extracting data values and matching to an electronic ticket form | |
| CN106373575B (en) | User voiceprint model construction method, device and system | |
| CN108447471A (en) | Audio recognition method and speech recognition equipment | |
| CN111696558A (en) | Intelligent outbound method, device, computer equipment and storage medium | |
| WO2015033121A1 (en) | Biometric verification using predicted signatures | |
| CN103679452A (en) | Payment authentication method, device thereof and system thereof | |
| CN108735200A (en) | A kind of speaker's automatic marking method | |
| CN113903363B (en) | Violation behavior detection method, device, equipment and medium based on artificial intelligence | |
| CN111901473A (en) | Incoming call processing method, device, equipment and storage medium | |
| CN112235470B (en) | Incoming call client follow-up method, device and equipment based on voice recognition | |
| CN104954532B (en) | The method and device and mobile terminal of speech recognition | |
| CN104348621A (en) | Authentication system based on voiceprint recognition and method thereof | |
| CN111142834A (en) | Service processing method and system | |
| CN106782567A (en) | Method and device for establishing voiceprint model | |
| CN109817223A (en) | Phoneme marking method and device based on audio fingerprints | |
| CN113051384A (en) | User portrait extraction method based on conversation and related device | |
| CN104468932A (en) | Method and device for automatically recording digital information in call content | |
| CN110853674A (en) | Text collation method, apparatus, and computer-readable storage medium | |
| CN108717851A (en) | A kind of audio recognition method and device | |
| CN112820292A (en) | Method, device, electronic device and storage medium for generating conference summary | |
| CN107945808A (en) | Customer management method and device based on voiceprint recognition |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180227 Termination date: 20200909 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |