CN102404287A - Voiceprint identification system and method for determining voiceprint authentication threshold value through data multiplexing method - Google Patents
Voiceprint identification system and method for determining voiceprint authentication threshold value through data multiplexing method Download PDFInfo
- Publication number
- CN102404287A CN102404287A CN2010102807341A CN201010280734A CN102404287A CN 102404287 A CN102404287 A CN 102404287A CN 2010102807341 A CN2010102807341 A CN 2010102807341A CN 201010280734 A CN201010280734 A CN 201010280734A CN 102404287 A CN102404287 A CN 102404287A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- threshold value
- user
- identification module
- data
- 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
Landscapes
- Telephonic Communication Services (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a voiceprint identification system for determining a voiceprint authentication threshold value through a data multiplexing method, which comprises a password establishing module, a voice identification module and a voiceprint identification module. The password establishing module is connected with a server, the server generates a random password for a user, or the user sets a fixed password. The voice identification module is used for matching the voice content provided by the user with the password content, if the voice content provided by the user is matched with the password content, the voiceprint identification module is entered. The voiceprint identification module comprises a register unit and a test unit, wherein the register unit comprises a model establishing module and a threshold value determining module. A speaker model is established in the register unit, simultaneously register data of a user are reused, and the voiceprint authentication threshold of the user is determined. The speaker model is accessed in the test unit, and voice characteristics provided during test are analyzed and compared with the voiceprint of the user, thereby determining whether to accept or not. In addition, the invention further discloses an achieving method of the system. The voiceprint identification system and a method for determining the voiceprint authentication threshold value through the data multiplexing method are simple to operate, more convenient to use and more likely to be accepted by the user.
Description
Technical field
The present invention relates to a kind of voiceprint system, relate in particular to a kind of voiceprint system that confirms the voiceprint threshold value with the data multiplex method; In addition, the invention still further relates to the implementation method of this voiceprint system.
Background technology
Application on Voiceprint Recognition (Voiceprint recognition) is called Speaker Identification (SpeakerRecognition) again, is a speech parameter according to reflection speaker physiology, psychology and behavioural characteristic in the speech waveform, discerns the technology of speaker ' s identity automatically.Because the difference of the difference of congenital channel structure and the pronunciation of forming day after tomorrow custom causes everyone sound all to have uniqueness, according to this uniqueness, can distinguish people's identity accurately.
In the voiceprint system (or Application on Voiceprint Recognition), threshold value is a very crucial parameter, and owing to everyone the vocal organs physiological characteristic and the different of custom of pronouncing, everyone threshold value is also different.For for each user confirms threshold value, need usually to collect the user's voice data in addition, this has increased user's use complexity.
Therefore, need a kind of voiceprint of research and development system, confirm the voiceprint threshold value for each user, with being used for more convenient and quicker to reduce the use complexity of system.
Summary of the invention
The technical problem that the present invention will solve provides a kind of voiceprint system that confirms the voiceprint threshold value with the data multiplex method; It does not need the user to provide extra data promptly to can be the threshold value that it confirms voiceprint; Reduced user's operation; Make the voiceprint system more convenient to use, more be prone to accept for the user.For this reason, the present invention also provides the implementation method of this voiceprint system.
For solving the problems of the technologies described above, the present invention provides a kind of and confirms the voiceprint system of voiceprint threshold value with the data multiplex method, and comprising: password is set up module, sound identification module and voiceprint identification module; This password is set up module and is linked to each other with server, and server produces random cipher and offers the user or the user sets fixed password, and the user provides speech data, and is submitted to server; The voice that this sound identification module is used for the user is provided carry out content analysis, and the voice content and the password content that provide are carried out pattern matching, if both do not meet, explains that the password that the user provides is nonconforming, conform to as if both, then get into voiceprint identification module; This voiceprint identification module is divided into registering unit and test cell, and this registering unit comprises sets up model module and definite threshold module, sets up speaker model in registering unit, and the log-on data of users multiplexing is simultaneously confirmed the threshold value of its voiceprint for each user; Call speaker model at test cell, the phonetic feature that provides during analytical test confirms that with user's vocal print threshold value compares, and judges and accepts or refusal.
Set up speaker model in registering unit in the said voiceprint identification module; Be specially: the speaker provides the speech data of plurality of sections fixed password and random number word string; On the basis of the universal background model that a large amount of voice trainings by a large amount of speakers go out; Through the maximum a posteriori probability adaptive algorithm this speaker's model parameter is estimated, set up this speaker model.
In the said voiceprint identification module in the log-on data of registering unit users multiplexing; Confirm the threshold value of its voiceprint for each user; Be specially: the speech data with a part of speaker is trained speaker model; Remaining speech data is tested (remaining speech data and speaker model are mated, obtain the scoring of a plurality of tested speech) to the speaker model of being trained, and uses the result's (being the scoring of a plurality of tested speech) who is tested to estimate threshold value; This process can according to circumstances be carried out repeatedly, to obtain the best estimate of threshold value.
Call speaker model at test cell in the said voiceprint identification module, the phonetic feature that provides during analytical test obtains a coupling scoring of tested speech and this speaker model coupling; And the threshold value that will mark with voiceprint matees, and carries out one and confirms judgement, if scoring is greater than threshold value; Then accept; Otherwise,, then refuse if scoring is lower than threshold value.
In addition, the present invention also provides a kind of and confirms to comprise the steps: the implementation method of the voiceprint system of voiceprint threshold value with the data multiplex method
(1) server produces random cipher and offers the user or the user sets fixed password;
(2) user provides voice;
(3) sound identification module carries out content analysis to the voice that the user provides, and the voice content and the password content that provide are carried out pattern matching, judges whether both conform to; If do not meet; Explain that the password that the user provides is nonconforming, should give refusal, get back to step (2); If conform to, then get into step (4);
(4) at registration phase, voiceprint identification module is set up speaker model, and the log-on data of users multiplexing is simultaneously confirmed the threshold value of its voiceprint for each user; At test phase, voiceprint identification module is called speaker model, and the phonetic feature that provides during analytical test confirms that with user's vocal print threshold value compares, and judges and accepts or refusal.
In the step (4); Saidly set up speaker model in the registration phase voiceprint identification module; Be specially: the speaker provides the speech data of plurality of sections fixed password and random number word string; On the basis of the universal background model that a large amount of voice trainings by a large amount of speakers go out, through the maximum a posteriori probability adaptive algorithm this speaker's model parameter is estimated, set up this speaker model.
In the step (4); Said log-on data in registration phase voiceprint identification module users multiplexing; For each user confirms the threshold value of its voiceprint, be specially: the speech data with a part of speaker is trained speaker model, and remaining speech data is tested the speaker model of being trained and (remaining speech data and speaker model mated; Obtain the scoring of a plurality of tested speech); Use the result's (being the scoring of a plurality of tested speech) who is tested to estimate threshold value, this process can according to circumstances be carried out repeatedly, to obtain the best estimate of threshold value.
In the step (4), saidly call speaker model in the test phase voiceprint identification module, the phonetic feature that provides during analytical test; Obtain a coupling scoring of tested speech and this speaker model coupling; And the threshold value that will mark with voiceprint matees, and carries out one and confirms judgement, if scoring is greater than threshold value; Then accept process ends; Otherwise if scoring is lower than threshold value, then refusal is got back to step (2).
Beneficial effect of the present invention is: the present invention is through the log-on data of users multiplexing; Do not need the user to provide extra data promptly to can be the threshold value that it confirms voiceprint; Reduced user's operation, made the voiceprint system more convenient to use, more be prone to accept for the user.
Description of drawings
Fig. 1 is the modular structure sketch map of system of the present invention;
Fig. 2 is the schematic flow sheet of registration phase in the inventive method;
Fig. 3 is the schematic flow sheet of test phase in the inventive method;
Fig. 4 is the schematic flow sheet that threshold value is confirmed in the inventive method.
Embodiment
As shown in Figure 1, voiceprint of the present invention system needs the user that satisfactory voice are provided, and the present invention is example with the random cipher, mainly divides three parts:
First: password is set up module, is produced random cipher and is offered the user by server, and the user provides the satisfactory speech data of some, and is submitted to server.
Second: sound identification module, this module is carried out content analysis to the voice that the user provides, and the voice and the password content that provide are carried out pattern matching, judges whether both conform to, if do not meet, explains that the password that the user provides is nonconforming, should with refusal.If conform to, the voiceprint identification module below then getting into.
The 3rd: voiceprint identification module, this module is made up of two parts: registering unit and test cell; Registering unit comprises sets up model module and definite threshold module; Set up model module and be used to set up speaker model; Be specially: the speaker provides the plurality of sections speech data; On the basis of the universal background model (for example gauss hybrid models) that a large amount of voice trainings by a large amount of speakers go out; Through maximum a posteriori probability adaptive algorithm (classic algorithm well known in the art) this speaker's model parameter is estimated, set up this speaker model; Simultaneously; Start to confirm to be specially threshold module: the log-on data of users multiplexing, confirm the threshold value of its voiceprint for each user; Promptly train speaker model with a part of speaker's speech data; Remaining speech data is tested (be about to remaining speech data and speaker model and mate, obtain the scoring of a plurality of tested speech) to the speaker model of being trained, and uses the result's (being the scoring of a plurality of tested speech) who is tested to estimate threshold value.The estimation procedure of user's threshold value can adopt following method: the scoring that is obtained by the user data multiplexing method estimates the matching score of a user to own model; And user's threshold value (being initially domestic consumer's threshold value, i.e. common threshold) is adjusted optimization according to this score, if this score is high than domestic consumer; Then can on the basis of domestic consumer's threshold value (common threshold), heighten this user's threshold value; Otherwise, turn down this user's threshold value, the amplitude of adjustment is relevant with this scoring.This process can according to circumstances be carried out repeatedly, to obtain the best estimate of threshold value.Test cell: the speaker model of system call statement, the phonetic feature that provides during analytical test obtains a coupling scoring of the speaker model coupling of tested speech and this statement; And will mark and user's vocal print confirms that threshold value compares, carry out one and confirm judgement, judge and accept or refusal; If scoring greater than threshold value, is then accepted, otherwise; If scoring is lower than threshold value, then refuse.
As shown in Figures 2 and 3, the implementation method of voiceprint of the present invention system is an example with the random cipher, comprises the steps:
(1) server produces random cipher and offers the user;
(2) user provides speech data, and is submitted to server;
(3) sound identification module carries out content analysis to the voice that the user provides, and the voice content and the password content that provide are carried out pattern matching, judges whether both conform to; If do not meet; Explain that the password that the user provides is nonconforming, should give refusal, get back to step (2); If conform to, then get into step (4);
(4) at registration phase, voiceprint identification module is set up speaker model (promptly registering model), and the log-on data of users multiplexing for the threshold value that each user confirms its voiceprint, is seen Fig. 2 simultaneously; At test phase, voiceprint identification module is called speaker model (promptly registering model), the phonetic feature that provides during analytical test; Obtain a coupling scoring of the speaker model coupling of tested speech and this statement; And will mark and user's vocal print confirms that threshold value compares, carry out one and confirm judgement, if scoring is greater than threshold value; Then accept process ends; Otherwise if scoring is lower than threshold value, then refusal is got back to step (2), sees Fig. 3.
As shown in Figure 4; When user registration course; Needing the user that N bar training data is provided (is that user among Fig. 4 registers voice 1,2 ... N); Like N=5; The M bar of getting wherein is used for training pattern (like M=N-1), and all the other N-M bars (are M+1 ... The N bar) be used for test (promptly call sound-groove model (speaker model) and carry out Model Matching), the scoring that can obtain
individual tested speech is used for confirming threshold value.As work as N=5; During M=4;
promptly is equivalent to have the scoring of 5 tested speech, and do not need the user to provide 5 voice to be used for confirming threshold value specially.Like this, when the user registers completion, be it and confirmed threshold value, its sound-groove model (being speaker model, registration model) has promptly been set up complete, and the back can normally be logined and use.
The present invention adopts the method for multiplex data to confirm the threshold value of voiceprint, through the log-on data of users multiplexing, does not need extra data can confirm user's voiceprint threshold value, has simplified user's operation, confirms that threshold mode is more convenient.
Claims (10)
1. confirm the voiceprint system of voiceprint threshold value to it is characterized in that comprise: password is set up module, sound identification module and voiceprint identification module with the data multiplex method for one kind;
This password is set up module and is linked to each other with server, and server produces random cipher and offers the user or the user sets fixed password, and the user provides speech data, and is submitted to server;
The voice that this sound identification module is used for the user is provided carry out content analysis, and the voice content and the password content that provide are carried out pattern matching, if both do not meet, explains that the password that the user provides is nonconforming, conform to as if both, then get into voiceprint identification module;
This voiceprint identification module is divided into registering unit and test cell; This registering unit comprises sets up model module and definite threshold module, sets up speaker model in registering unit, and the log-on data of users multiplexing is simultaneously confirmed the threshold value of its voiceprint for each user; Call speaker model at test cell, the phonetic feature that provides during analytical test confirms that with user's vocal print threshold value compares, and judges and accepts or refusal.
2. the voiceprint system that confirms the voiceprint threshold value with the data multiplex method as claimed in claim 1; It is characterized in that; Set up speaker model in registering unit in the said voiceprint identification module, be specially: the speaker provides the speech data of plurality of sections fixed password and random number word string, on the basis of the universal background model that a large amount of voice trainings by a large amount of speakers go out; Through the maximum a posteriori probability adaptive algorithm this speaker's model parameter is estimated, set up this speaker model.
According to claim 1 or claim 2 confirm the voiceprint system of voiceprint threshold value with the data multiplex method; It is characterized in that; In the log-on data of registering unit users multiplexing, the threshold value for each user confirms its voiceprint is specially in the said voiceprint identification module: the speech data with a part of speaker is trained speaker model; Remaining speech data is tested the speaker model of being trained; Use the result who is tested to estimate threshold value, this process can according to circumstances be carried out repeatedly, to obtain the best estimate of threshold value.
4. the voiceprint system that confirms the voiceprint threshold value with the data multiplex method as claimed in claim 3; It is characterized in that; Said remaining speech data is tested the speaker model of being trained, and uses the result who is tested to estimate threshold value, is specially: remaining speech data and speaker model are mated; Obtain the scoring of a plurality of tested speech, estimate threshold value with the scoring of these a plurality of tested speech.
5. as claimed in claim 1ly confirm to it is characterized in that the voiceprint system of voiceprint threshold value, call speaker model at test cell in the said voiceprint identification module with the data multiplex method; The phonetic feature that provides during analytical test obtains a coupling scoring of tested speech and this speaker model coupling, and will mark and the threshold value of voiceprint is mated; Carry out one and confirm judgement, if scoring greater than threshold value, is then accepted; Otherwise,, then refuse if scoring is lower than threshold value.
6. confirm to it is characterized in that the implementation method of the voiceprint system of voiceprint threshold value with the data multiplex method for one kind, comprise the steps:
(1) server produces random cipher and offers the user or the user sets fixed password;
(2) user provides voice;
(3) sound identification module carries out content analysis to the voice that the user provides, and the voice content and the password content that provide are carried out pattern matching, judges whether both conform to; If do not meet; Explain that the password that the user provides is nonconforming, should give refusal, get back to step (2); If conform to, then get into step (4);
(4) at registration phase, voiceprint identification module is set up speaker model, and the log-on data of users multiplexing is simultaneously confirmed the threshold value of its voiceprint for each user; At test phase, voiceprint identification module is called speaker model, and the phonetic feature that provides during analytical test confirms that with user's vocal print threshold value compares, and judges and accepts or refusal.
7. the implementation method of confirming the voiceprint system of voiceprint threshold value with the data multiplex method as claimed in claim 6; It is characterized in that; In the step (4); Saidly set up speaker model in the registration phase voiceprint identification module, be specially: the speaker provides the speech data of plurality of sections fixed password and random number word string, on the basis of the universal background model that a large amount of voice trainings by a large amount of speakers go out; Through the maximum a posteriori probability adaptive algorithm this speaker's model parameter is estimated, set up this speaker model.
8. the implementation method of confirming the voiceprint system of voiceprint threshold value with the data multiplex method as claimed in claim 6; It is characterized in that, in the step (4), said log-on data in registration phase voiceprint identification module users multiplexing; Confirm the threshold value of its voiceprint for each user; Be specially: the speech data with a part of speaker is trained speaker model, and remaining speech data is tested the speaker model of being trained, and uses the result who is tested to estimate threshold value; This process can according to circumstances be carried out repeatedly, to obtain the best estimate of threshold value.
9. the implementation method of confirming the voiceprint system of voiceprint threshold value with the data multiplex method as claimed in claim 8; It is characterized in that; Said remaining speech data is tested the speaker model of being trained, and uses the result who is tested to estimate threshold value, is specially: remaining speech data and speaker model are mated; Obtain the scoring of a plurality of tested speech, estimate threshold value with the scoring of these a plurality of tested speech.
10. as claimed in claim 6ly confirm to it is characterized in that the implementation method of the voiceprint system of voiceprint threshold value, in the step (4) with the data multiplex method; Saidly call speaker model in the test phase voiceprint identification module, the phonetic feature that provides during analytical test obtains tested speech and marks with a coupling of this speaker model coupling; And the threshold value that will mark with voiceprint matees, and carries out one and confirms judgement, if scoring is greater than threshold value; Then accept process ends; Otherwise if scoring is lower than threshold value, then refusal is got back to step (2).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010102807341A CN102404287A (en) | 2010-09-14 | 2010-09-14 | Voiceprint identification system and method for determining voiceprint authentication threshold value through data multiplexing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010102807341A CN102404287A (en) | 2010-09-14 | 2010-09-14 | Voiceprint identification system and method for determining voiceprint authentication threshold value through data multiplexing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102404287A true CN102404287A (en) | 2012-04-04 |
Family
ID=45886082
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010102807341A Pending CN102404287A (en) | 2010-09-14 | 2010-09-14 | Voiceprint identification system and method for determining voiceprint authentication threshold value through data multiplexing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102404287A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103986725A (en) * | 2014-05-29 | 2014-08-13 | 中国农业银行股份有限公司 | Client side, server side and identity authentication system and method |
CN104036780A (en) * | 2013-03-05 | 2014-09-10 | 阿里巴巴集团控股有限公司 | Man-machine identification method and system |
WO2014190742A1 (en) * | 2013-05-29 | 2014-12-04 | Tencent Technology (Shenzhen) Company Limited | Method, device and system for identity verification |
WO2016015687A1 (en) * | 2014-07-31 | 2016-02-04 | 腾讯科技(深圳)有限公司 | Voiceprint verification method and device |
CN105575385A (en) * | 2015-12-16 | 2016-05-11 | 中国建设银行股份有限公司 | Voice cipher setting system and method, and sound cipher verification system and method |
WO2016123900A1 (en) * | 2015-02-05 | 2016-08-11 | 北京得意音通技术有限责任公司 | Dynamic password voice based identity authentication system and method having self-learning function |
WO2016150369A1 (en) * | 2015-03-24 | 2016-09-29 | 中兴通讯股份有限公司 | Method and device for recording and recognising voice password |
CN106033670A (en) * | 2015-03-19 | 2016-10-19 | 科大讯飞股份有限公司 | Voiceprint password authentication method and system |
CN106796785A (en) * | 2014-10-22 | 2017-05-31 | 高通股份有限公司 | Sample sound for producing sound detection model is verified |
WO2017113658A1 (en) * | 2015-12-30 | 2017-07-06 | 百度在线网络技术(北京)有限公司 | Artificial intelligence-based method and device for voiceprint authentication |
CN106971733A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技(杭州)有限公司 | The method and system and intelligent terminal of Application on Voiceprint Recognition based on voice de-noising |
CN107046517A (en) * | 2016-02-05 | 2017-08-15 | 阿里巴巴集团控股有限公司 | A kind of method of speech processing, device and intelligent terminal |
CN108172230A (en) * | 2018-01-03 | 2018-06-15 | 平安科技(深圳)有限公司 | Voiceprint registration method, terminal installation and storage medium based on Application on Voiceprint Recognition model |
CN109872721A (en) * | 2017-12-05 | 2019-06-11 | 富士通株式会社 | Voice authentication method, information processing equipment and storage medium |
WO2019228135A1 (en) * | 2018-05-30 | 2019-12-05 | Oppo广东移动通信有限公司 | Method and device for adjusting matching threshold, storage medium and electronic device |
US10593334B2 (en) | 2014-10-10 | 2020-03-17 | Alibaba Group Holding Limited | Method and apparatus for generating voiceprint information comprised of reference pieces each used for authentication |
CN111344783A (en) * | 2017-11-14 | 2020-06-26 | 思睿逻辑国际半导体有限公司 | Registration in a speaker recognition system |
CN111599365A (en) * | 2020-04-08 | 2020-08-28 | 云知声智能科技股份有限公司 | Adaptive threshold generation system and method for voiceprint recognition system |
US20210233542A1 (en) * | 2017-12-27 | 2021-07-29 | Rovi Guides, Inc. | Systems and methods for identifying users based on voice data and media consumption data |
CN114093370A (en) * | 2022-01-19 | 2022-02-25 | 珠海市杰理科技股份有限公司 | Voiceprint recognition method and device, computer equipment and storage medium |
-
2010
- 2010-09-14 CN CN2010102807341A patent/CN102404287A/en active Pending
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036780A (en) * | 2013-03-05 | 2014-09-10 | 阿里巴巴集团控股有限公司 | Man-machine identification method and system |
CN104036780B (en) * | 2013-03-05 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Man-machine identification method and system |
US9571490B2 (en) | 2013-03-05 | 2017-02-14 | Alibaba Group Holding Limited | Method and system for distinguishing humans from machines |
WO2014190742A1 (en) * | 2013-05-29 | 2014-12-04 | Tencent Technology (Shenzhen) Company Limited | Method, device and system for identity verification |
CN104219195A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技(深圳)有限公司 | Identity verifying method, device and system |
CN104219195B (en) * | 2013-05-29 | 2018-05-22 | 腾讯科技(深圳)有限公司 | Proof of identity method, apparatus and system |
CN103986725A (en) * | 2014-05-29 | 2014-08-13 | 中国农业银行股份有限公司 | Client side, server side and identity authentication system and method |
US10276168B2 (en) | 2014-07-31 | 2019-04-30 | Tencent Technology (Shenzhen) Company Limited | Voiceprint verification method and device |
WO2016015687A1 (en) * | 2014-07-31 | 2016-02-04 | 腾讯科技(深圳)有限公司 | Voiceprint verification method and device |
US10593334B2 (en) | 2014-10-10 | 2020-03-17 | Alibaba Group Holding Limited | Method and apparatus for generating voiceprint information comprised of reference pieces each used for authentication |
CN106796785A (en) * | 2014-10-22 | 2017-05-31 | 高通股份有限公司 | Sample sound for producing sound detection model is verified |
US10540980B2 (en) | 2015-02-05 | 2020-01-21 | Beijing D-Ear Technologies Co., Ltd. | Dynamic security code speech-based identity authentication system and method having self-learning function |
WO2016123900A1 (en) * | 2015-02-05 | 2016-08-11 | 北京得意音通技术有限责任公司 | Dynamic password voice based identity authentication system and method having self-learning function |
CN106033670A (en) * | 2015-03-19 | 2016-10-19 | 科大讯飞股份有限公司 | Voiceprint password authentication method and system |
CN106033670B (en) * | 2015-03-19 | 2019-11-15 | 科大讯飞股份有限公司 | Voiceprint password authentication method and system |
WO2016150369A1 (en) * | 2015-03-24 | 2016-09-29 | 中兴通讯股份有限公司 | Method and device for recording and recognising voice password |
CN106161727A (en) * | 2015-03-24 | 2016-11-23 | 中兴通讯股份有限公司 | The typing of a kind of verbal instructions, recognition methods and device |
CN105575385A (en) * | 2015-12-16 | 2016-05-11 | 中国建设银行股份有限公司 | Voice cipher setting system and method, and sound cipher verification system and method |
WO2017113658A1 (en) * | 2015-12-30 | 2017-07-06 | 百度在线网络技术(北京)有限公司 | Artificial intelligence-based method and device for voiceprint authentication |
US10699716B2 (en) | 2015-12-30 | 2020-06-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Artificial intelligence-based method and device for voiceprint authentication |
CN106971733A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技(杭州)有限公司 | The method and system and intelligent terminal of Application on Voiceprint Recognition based on voice de-noising |
CN107046517A (en) * | 2016-02-05 | 2017-08-15 | 阿里巴巴集团控股有限公司 | A kind of method of speech processing, device and intelligent terminal |
CN111344783A (en) * | 2017-11-14 | 2020-06-26 | 思睿逻辑国际半导体有限公司 | Registration in a speaker recognition system |
CN109872721A (en) * | 2017-12-05 | 2019-06-11 | 富士通株式会社 | Voice authentication method, information processing equipment and storage medium |
US20210233542A1 (en) * | 2017-12-27 | 2021-07-29 | Rovi Guides, Inc. | Systems and methods for identifying users based on voice data and media consumption data |
US11798565B2 (en) * | 2017-12-27 | 2023-10-24 | Rovi Guides, Inc. | Systems and methods for identifying users based on voice data and media consumption data |
CN108172230A (en) * | 2018-01-03 | 2018-06-15 | 平安科技(深圳)有限公司 | Voiceprint registration method, terminal installation and storage medium based on Application on Voiceprint Recognition model |
WO2019228135A1 (en) * | 2018-05-30 | 2019-12-05 | Oppo广东移动通信有限公司 | Method and device for adjusting matching threshold, storage medium and electronic device |
CN111599365A (en) * | 2020-04-08 | 2020-08-28 | 云知声智能科技股份有限公司 | Adaptive threshold generation system and method for voiceprint recognition system |
CN111599365B (en) * | 2020-04-08 | 2023-05-05 | 云知声智能科技股份有限公司 | Adaptive threshold generation system and method for voiceprint recognition system |
CN114093370A (en) * | 2022-01-19 | 2022-02-25 | 珠海市杰理科技股份有限公司 | Voiceprint recognition method and device, computer equipment and storage medium |
CN114093370B (en) * | 2022-01-19 | 2022-04-29 | 珠海市杰理科技股份有限公司 | Voiceprint recognition method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102404287A (en) | Voiceprint identification system and method for determining voiceprint authentication threshold value through data multiplexing method | |
CN104036774B (en) | Tibetan dialect recognition methods and system | |
CN105304080B (en) | Speech synthetic device and method | |
CN106847292B (en) | Method for recognizing sound-groove and device | |
Aronowitz | Inter dataset variability compensation for speaker recognition | |
CN107146624B (en) | A kind of method for identifying speaker and device | |
CN108806667A (en) | The method for synchronously recognizing of voice and mood based on neural network | |
Wand et al. | Session-independent EMG-based Speech Recognition. | |
CN101315733B (en) | Self-adapting method aiming at computer language learning system pronunciation evaluation | |
CN107767861A (en) | voice awakening method, system and intelligent terminal | |
CN107492382A (en) | Voiceprint extracting method and device based on neutral net | |
CN107146615A (en) | Audio recognition method and system based on the secondary identification of Matching Model | |
CN108694954A (en) | A kind of Sex, Age recognition methods, device, equipment and readable storage medium storing program for executing | |
CN102413101A (en) | Voice-print authentication system having voice-print password voice prompting function and realization method thereof | |
CN103811009A (en) | Smart phone customer service system based on speech analysis | |
CN105590625A (en) | Acoustic model self-adaptive method and system | |
CN1808567A (en) | Voice-print authentication device and method of authenticating people presence | |
CN104104664A (en) | Method, server, client and system for verifying verification code | |
CN105023570B (en) | A kind of method and system for realizing sound conversion | |
CN104717219A (en) | Vocal print login method and device based on artificial intelligence | |
CN102968990A (en) | Speaker identifying method and system | |
CN106898355A (en) | A kind of method for distinguishing speek person based on two modelings | |
CN108831484A (en) | A kind of offline and unrelated with category of language method for recognizing sound-groove and device | |
CN111583936A (en) | Intelligent voice elevator control method and device | |
CN102314877A (en) | Voiceprint identification method for character content prompt |
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: 20120404 |