CN109785834A - A kind of voice data sample acquisition system and its method based on identifying code - Google Patents
A kind of voice data sample acquisition system and its method based on identifying code Download PDFInfo
- Publication number
- CN109785834A CN109785834A CN201910065909.8A CN201910065909A CN109785834A CN 109785834 A CN109785834 A CN 109785834A CN 201910065909 A CN201910065909 A CN 201910065909A CN 109785834 A CN109785834 A CN 109785834A
- Authority
- CN
- China
- Prior art keywords
- sample
- speech
- text
- verification
- 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.)
- Granted
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of voice data sample acquisition system and its method based on identifying code, user terminal is connect with speech verification and acquisition module, user initiates verification request by user terminal, by mainly by sample collection server, sample database, the speech verification and acquisition module that calling terminal and speech-to-text server are constituted provide the service for checking credentials for user terminal, when in use, speech verification and acquisition module request to issue grapholect sample data according to verification, user reads aloud the word content of grapholect sample data according to instruction by user terminal, obtain speech samples;Speech verification and acquisition module carry out the processing of speech-to-text to the speech samples, obtain instant character sample, carry out proving and comparisom, compare and successfully then acquire the speech samples, otherwise abandon.Whole process only needs user's checking to participate in, and is not necessarily to collection in worksite, and compared with the way of traditional artificial typing, speech samples collecting work amount is few, the investment of sampling cost is lower.
Description
Technical field
The present invention relates to a kind of data under voice technology, especially a kind of voice data sample collection based on identifying code
System and method.
Background technique
With the fast development of big data industry and artificial intelligence deep learning, the demand to data sample exponentially increases
It is long.Because either artificial intelligence or big data are all to need just to can be carried out on the basis of obtaining based on front end data in next step
Data processing, and the application scenarios of different field and different function for data sample acquisition difference it is larger, especially relate to
And the acquisition of the biological characteristic of human body itself.Such as recognition of face, image recognition, speech recognition, voiced translation etc., due to acquisition
Data sample be related to the peculiar biological characteristic of fingerprint, face image, sound of different crowd et al. itself, it is therefore desirable to acquisition is big
The data sample of amount.In the prior art, the acquisition carried out for the acquisition of voice data sample generally by manual entry,
Labor intensive resource is big, and data acquisition cost is caused to improve.
Identifying code (CAPTCHA) is " Completely Automated Public Turing test to tell
The abbreviation of Computers and Humans Apart " (the full-automatic turing test for distinguishing computer and the mankind), is a kind of area
Dividing user is computer or the public full auto-programs of people.User can prevent when using on third platform: maliciously crack close
Functions, the identifying codes such as code, brush ticket, forum pour water, identity verification have become the current mode of many websites/platform.Therefore, it is based on
Third platform simultaneously realizes that the acquisition of voice data sample becomes a major challenge of data collecting field by verification code technology.
Summary of the invention
Goal of the invention of the invention is, in view of the above-mentioned problems, providing a kind of voice data sample collection based on identifying code
System, the present invention is based on providing the approach of identifying code service for third-party platform, and it is wide in identifying code service using user
The acquisition of voice data sample, the cost of effectively save data acquisition smoothly and are fast completed in general participation.
In order to achieve the above objectives, the technical scheme adopted by the invention is that:
A kind of voice data sample acquisition system based on identifying code, including user terminal and speech verification and acquisition mould
Block, the user terminal are connect with speech verification and acquisition module, to initiate verification request to speech verification and acquisition module,
User reads aloud the word content in text sample data, and corresponding generation language according to the instruction that speech verification and acquisition module are sent
Sound sample, the speech samples are sent to speech verification and acquisition module by user terminal, and the text sample data includes text
Printed words sheet and number;
The speech verification and acquisition module, to receive user terminal verification request, and according to verification request to
Family terminal sends text sample data to be identified, at the same receive speech samples that user terminal is sent and by the speech samples into
After the processing of row speech-to-text, obtain instant character sample data, then by instant character sample data and speech verification and
The grapholect sample data stored in acquisition module carries out verification comparison, determines whether to acquire by the result of verification comparison
The speech samples.
Preferably, the speech verification and acquisition module include sample collection server, sample database,
Calling terminal and speech-to-text server,
The user terminal is connect with sample collection server, for sample collection server carry out information exchange and to
Sample collection server initiates checking request;The user terminal is also connect with calling terminal, is sent to receive calling terminal
Speech channel calling, and according to speech channel calling read aloud text sample data, with corresponding to calling terminal output character sample data
Speech samples;
The sample collection server, to provide the service for checking credentials to user terminal;The sample collection server also with
Sample database connection, for transferring the text sample data stored in sample database;The sample collection server also with
Calling terminal connection initiates call verification to user terminal for controlling calling terminal;
The sample database is connect with sample collection server, for providing text sample to sample collection server
Number and the sample label of storage identification;The sample database is also connect with calling terminal, for storing calling terminal hair
The speech samples come;
The calling terminal is connect with sample collection server, and the Call- Control1 for receiving sample collection server is asked
It asks;The calling terminal is connect with user terminal, for initiating to call to user terminal;The calling terminal also turns text with voice
Speech samples are changed into text sample for controlling speech-to-text server by character server connection;The calling terminal also with
Sample database connection, for speech samples and text sample to be associated storage;
The speech-to-text server is connect with calling terminal, for responding the control from calling terminal, by language
Sound sample changes into text sample.
In above scheme, it is preferable that the speech verification and acquisition module further include third-party platform, and the third party is flat
Platform is connect with sample collection server, to receive sample collection server to the verification result of speech samples;Third-party platform
It is connect with user terminal.
In above scheme, it is preferable that the sample database will identify that successful text sample adds in order each time
Into voice collecting sample storehouse, speech samples number of the storage after sample collection server verifies successfully in the storehouse
According to.
In above scheme, it is preferable that the data sample includes text sample data and voice sample data.
The voice data sample collection method based on identifying code that the present invention also provides a kind of, includes the following steps:
The information of S1, the sample collection server between user and third-party platform, which is mutually handed over, provides the service for checking credentials, uses
Family sends verification request to the sample collection server by user terminal;
S2, the sample collection server receive come user terminal verification request after, in Xiang Suoshu sample database
The request for sending called data sample data after obtaining the response of sample database, obtains and contains text sample number to be identified
According to;
The text sample and number in text sample data that S3, the sample collection server obtain step S2 are made
It is corresponding to generate a school after carrying out binding integration with the effective check code being stored in the sample collection server for data sample
Code is tested, and the check code is sent to user terminal, while user being reminded to answer the call of calling terminal, the data sample
This includes data sample number and text sample data;
S4, the sample collection server initiate call request, and the data sample that sending step S3 is obtained to calling terminal
This number;
After S5, the calling terminal receive the call request that step S4 is sent, initiate to call to user terminal;
S6, user's ring and off-hook;
S7, the calling terminal play the voice prompting for reading aloud text sample content to user terminal;
After S8, user hear the voice prompting sound for reading aloud beginning, start to read aloud in the text of the text sample in step S3
Hold, after on-hook, generate corresponding with word content speech samples;
S9, the calling terminal cache the obtained speech samples of step S8, while to speech-to-text server
Send the request of speech-to-text;
The speech samples that S10, the speech-to-text server obtain step S8 carry out speech-to-text processing, obtain
Speech-to-text is as a result, the speech-to-text result is instant character sample, and the instant character sample is returned to calling
Terminal;
Instant character sample is sent to the sample collection server and carries out result comparison by S11, the calling terminal;
The check code that S12, the sample collection server are obtained by step S3 is by instant character sample and sample collection
The grapholect sample of server memory storage is compared;
If S13, successful match, the request of storaged voice sample is sent to calling terminal, and test to user terminal feedback
Successful message is demonstrate,proved, while successfully notifying that the calling terminal receives deposit voice to third-party platform push user's checking
It, will be in the corresponding storehouse of text sample of speech samples deposit sample database after the request of sample;
If S14, it fails to match, the instruction for abandoning the speech samples is sent to calling terminal, and send to user terminal
The message of authentication failed, while to the notice of third-party platform push user's checking failure, calling terminal, which receives, abandons voice sample
After this notice, by the data dump of the speech samples.
Due to the adoption of the above technical scheme, the invention has the following advantages:
1. user is connect by user terminal with speech verification and acquisition module, realize that information between the two is mutually handed over, uses
Verification request is initiated by user terminal in family, by mainly by sample collection server, sample database, calling terminal and voice
Turn the text service device composition speech verification and acquisition module and provides the service for checking credentials for user terminal, in the use of the present invention,
Speech verification and acquisition module request to issue text sample data according to verification, and user reads aloud mark by user terminal according to instruction
The word content of quasi- text sample data, obtains speech samples;Speech verification and acquisition module carry out voice to the speech samples
The processing for turning text obtains instant character sample, based on check code again by the grapholect of instant character sample and storage inside
Sample data carries out proving and comparisom, compares and successfully then acquires the speech samples, otherwise abandons.Whole process only needs user's checking
Participation is not necessarily to collection in worksite, and compared with the way of traditional artificial typing, speech samples collecting work amount is few, samples cost
Investment it is lower.
2. the present invention takes full advantage of wide participation of the user in identifying code service for the acquisition method of speech samples,
Complete the acquisition of voice data sample, not only a large amount of save the costs, can also by be arranged or improvement system described in sample
The grapholect sample data that stores in acquisition server and the function of speech-to-text server is improved to improve speech samples
The accuracy of acquisition, and by the verification mode of text-to-speech-speech-to-text and the comparison of text and text, it will not be by a
The influence of the factors such as dialectal accent, the pronunciation standard of people can greatly improve the normalization of voice collecting.
Detailed description of the invention
Fig. 1 is a kind of the system composition block diagram of the voice data sample acquisition system based on identifying code of the present invention.
Fig. 2 is a kind of timing diagram of the voice data sample collection method based on identifying code of the present invention.
Specific embodiment
It is further illustrated below in conjunction with specific implementation of the attached drawing to invention.
A kind of voice data sample acquisition system based on identifying code, including user terminal and speech verification and acquisition mould
Block, the user terminal are connect with speech verification and acquisition module, to initiate verification request to speech verification and acquisition module,
User reads aloud the word content in text sample data, and corresponding generation language according to the instruction that speech verification and acquisition module are sent
Sound sample, the speech samples are sent to speech verification and acquisition module by user terminal, and the text sample data includes text
Printed words sheet and number.
The speech verification and acquisition module, to receive user terminal verification request, and according to verification request to
Family terminal sends text sample data to be identified, at the same receive speech samples that user terminal is sent and by the speech samples into
After the processing of row speech-to-text, obtain instant character sample data, then by instant character sample data and speech verification and
The grapholect sample data stored in acquisition module carries out verification comparison, determines whether to acquire by the result of verification comparison
The speech samples.
As shown in Figure 1, the speech verification and acquisition module include sample collection server, sample database, call eventually
End, speech-to-text server and third-party platform.
The user terminal and sample collection server, for carrying out information exchange with sample collection server and to sample
Acquisition server initiates checking request;The user terminal is also connect with calling terminal, to receive if calling terminal sends
Road calling, and text sample data is read aloud according to speech channel calling, with to the corresponding voice of calling terminal output character sample data
Sample.
The user terminal have networking, display, audio input output function equipment, such as smart phone,
Tablet computer or the tablet computer with sound equipment etc..
The sample collection server, to provide the service for checking credentials to user terminal.The sample collection server also with
Sample database connection, for transferring the text sample data stored in sample database.The sample collection server also with
Calling terminal connection initiates call verification to user terminal for controlling calling terminal.
The sample database is connect with sample collection server, for providing text sample to sample collection server
Number and the sample label of storage identification.The sample database is also connect with calling terminal, for storing calling terminal hair
The speech samples come.
The calling terminal is connect with sample collection server, and the Call- Control1 for receiving sample collection server is asked
It asks;The calling terminal is connect with user terminal, for initiating to call to user terminal.The calling terminal also turns text with voice
Speech samples are changed into text sample for controlling speech-to-text server by character server connection;The calling terminal also with
Sample database connection, for speech samples and text sample to be associated storage.The calling terminal, which is specifically as follows, exhales
It is platform or call server.
The speech-to-text server is connect with calling terminal, for responding the control from calling terminal, by language
Sound sample changes into text sample.
The third-party platform is connect with sample collection server, to receive sample collection server to speech samples
Verification result;Third-party platform is connect with user terminal.The third-party platform is specifically this voice data sample acquisition system
The third company or mechanism of service.This voice data sample acquisition system can provide the service for checking credentials for third-party platform.
The sample database will identify that successful text sample is added sequentially to voice collecting sample storehouse each time
In, voice sample data of the storage after sample collection server verifies successfully in the storehouse.
The data sample includes text sample data and voice sample data.
As shown in Fig. 2, the present invention provides a kind of voice data sample collection method based on identifying code, including walk as follows
It is rapid:
The information of S1, the sample collection server between user and third-party platform, which is mutually handed over, provides the service for checking credentials, uses
Family sends verification request to the sample collection server by user terminal;
S2, the sample collection server receive come user terminal verification request after, in Xiang Suoshu sample database
The request for sending called data sample data after obtaining the response of sample database, obtains and contains text sample number to be identified
According to;
The text sample and number in text sample data that S3, the sample collection server obtain step S2 are made
It is corresponding to generate a school after carrying out binding integration with the effective check code being stored in the sample collection server for data sample
Code is tested, and the check code is sent to user terminal, while user being reminded to answer the call of calling terminal, the data sample
This includes data sample number and text sample data;
S4, the sample collection server initiate call request, and the data sample that sending step S3 is obtained to calling terminal
This number;
After S5, the calling terminal receive the call request that step S4 is sent, initiate to call to user terminal;
S6, user's ring and off-hook;
S7, the calling terminal play the voice prompting for reading aloud text sample content to user terminal;
After S8, user hear the voice prompting sound for reading aloud beginning, start to read aloud in the text of the text sample in step S3
Hold, after on-hook, generate corresponding with word content speech samples;
S9, the calling terminal cache the obtained speech samples of step S8, while to speech-to-text server
Send the request of speech-to-text;
The speech samples that S10, the speech-to-text server obtain step S8 carry out speech-to-text processing, obtain
Speech-to-text is as a result, the speech-to-text result is instant character sample, and the instant character sample is returned to calling
Terminal;
Instant character sample is sent to the sample collection server and carries out result comparison by S11, the calling terminal;
The check code that S12, the sample collection server are obtained by step S3 is by instant character sample and sample collection
The grapholect sample of server memory storage is compared;
If S13, successful match, the request of storaged voice sample is sent to calling terminal, and test to user terminal feedback
Successful message is demonstrate,proved, while successfully notifying that the calling terminal receives deposit voice to third-party platform push user's checking
It, will be in the corresponding storehouse of text sample of speech samples deposit sample database after the request of sample;
If S14, it fails to match, the instruction for abandoning the speech samples is sent to calling terminal, and send to user terminal
The message of authentication failed, while to the notice of third-party platform push user's checking failure, calling terminal, which receives, abandons voice sample
After this notice, by the data dump of the speech samples.
The acquisition principle of voice data sample i.e. of the invention is: text-to-speech (text sample is read aloud by user, into
And obtain speech samples) → speech-to-text (speech samples are carried out speech-to-text processing by speech-to-text server) → text
The verification (sample collection server carries out verification comparison) of word and text comparison, above-mentioned identification collection process will not be by personal mouths
The influence of the factors such as sound, personal pronunciation or dialect, can greatly improve the normalization of voice collecting.
Above description is the detailed description for the present invention preferably possible embodiments, but embodiment is not limited to this hair
Bright patent claim, it is all the present invention suggested by technical spirit under completed same changes or modifications change, should all belong to
In the covered the scope of the patents of the present invention.
Claims (6)
1. a kind of voice data sample acquisition system based on identifying code, it is characterised in that: including user terminal and speech verification
And acquisition module,
The user terminal is connect with speech verification and acquisition module, is asked to initiate verification to speech verification and acquisition module
It asks, user reads aloud the word content in text sample data, and corresponding life according to the instruction that speech verification and acquisition module are sent
At speech samples, the speech samples are sent to speech verification and acquisition module, the text sample data packet by user terminal
Include text sample and number;
The speech verification and acquisition module are requested to receive the verification of user terminal, and are requested according to verification to user terminal
Text sample data to be identified is sent, while receiving speech samples that user terminal is sent and the speech samples is subjected to voice
After the processing for turning text, instant character sample data is obtained, then by instant character sample data and speech verification and acquisition mould
The grapholect sample data stored in block carries out verification comparison, determines whether to acquire the voice by the result of verification comparison
Sample.
2. a kind of voice data sample acquisition system based on identifying code according to claim 1, it is characterised in that: described
Speech verification and acquisition module include sample collection server, sample database, calling terminal and speech-to-text server,
The user terminal is connect with sample collection server, for carrying out information exchange with sample collection server and to sample
Acquisition server initiates checking request;The user terminal is also connect with calling terminal, to receive if calling terminal sends
Road calling, and text sample data is read aloud according to speech channel calling, with to the corresponding voice of calling terminal output character sample data
Sample;
The sample collection server is to provide the service for checking credentials to user terminal;The sample collection server also with sample number
It is connected according to library, for transferring the text sample data stored in sample database;The sample collection server is also whole with calling
End connection initiates call verification to user terminal for controlling calling terminal;
The sample database is connect with sample collection server, for providing the number of text sample to sample collection server
And the sample label of storage identification;The sample database is also connect with calling terminal, is sent for storing calling terminal
Speech samples;
The calling terminal is connect with sample collection server, and the Call- Control1 for receiving sample collection server is requested;Institute
It states calling terminal to connect with user terminal, for initiating to call to user terminal;The calling terminal also takes with speech-to-text
Speech samples are changed into text sample for controlling speech-to-text server by business device connection;The calling terminal also with sample
Database connection, for speech samples and text sample to be associated storage;
The speech-to-text server is connect with calling terminal, for responding the control from calling terminal, by voice sample
Originally text sample is changed into.
3. a kind of voice data sample acquisition system based on identifying code according to claim 2, it is characterised in that: described
Speech verification and acquisition module further include third-party platform, and the third-party platform is connect with sample collection server, to connect
Sample collection server is received to the verification result of speech samples;Third-party platform is connect with user terminal.
4. a kind of voice data sample acquisition system based on identifying code according to claim 2, it is characterised in that: described
Sample database will identify that successful text sample is added sequentially in voice collecting sample storehouse each time, in the storehouse
Store the voice sample data after sample collection server verifies successfully.
5. a kind of voice data sample acquisition system based on identifying code according to claim 1, it is characterised in that: described
Data sample includes text sample data and voice sample data.
6. a kind of voice data sample collection method based on identifying code, which comprises the steps of:
The information of S1, the sample collection server between user and third-party platform, which is mutually handed over, provides the service for checking credentials, Yong Hutong
It crosses user terminal and sends verification request to the sample collection server;
S2, the sample collection server receive come user terminal verification request after, sent in Xiang Suoshu sample database
The request of called data sample data after obtaining the response of sample database, obtains and contains text sample data to be identified;
The text sample and number in text sample data that S3, the sample collection server obtain step S2, as number
It is corresponding to generate a verification after carrying out binding integration with the effective check code being stored in the sample collection server according to sample
Code, and is sent to user terminal for the check code, while user being reminded to answer the call of calling terminal, the data sample
Including data sample number and text sample data;
S4, the sample collection server initiate call request to calling terminal, and the data sample that sending step S3 is obtained is compiled
Number;
After S5, the calling terminal receive the call request that step S4 is sent, initiate to call to user terminal;
S6, user's ring and off-hook;
S7, the calling terminal play the voice prompting for reading aloud text sample content to user terminal;
After S8, user hear the voice prompting sound for reading aloud beginning, start to read aloud the word content of the text sample in step S3, ties
On-hook after beam generates speech samples corresponding with word content;
S9, the calling terminal cache the obtained speech samples of step S8, while sending to speech-to-text server
The request of speech-to-text;
The speech samples that S10, the speech-to-text server obtain step S8 carry out speech-to-text processing, obtain voice
Turn text results, the speech-to-text result is instant character sample, and the instant character sample is returned to calling terminal;
Instant character sample is sent to the sample collection server and carries out result comparison by S11, the calling terminal;
The check code that S12, the sample collection server are obtained by step S3 is by instant character sample and sample collection service
The grapholect sample stored in device is compared;
If S13, successful match, to calling terminal send storaged voice sample request, and to user terminal feedback validation at
The message of function, while successfully notifying that the calling terminal receives deposit speech samples to third-party platform push user's checking
Request after, by speech samples deposit sample database the corresponding storehouse of text sample in;
If S14, it fails to match, the instruction for abandoning the speech samples is sent to calling terminal, and send and verify to user terminal
Failure news, while to the notice of third-party platform push user's checking failure, calling terminal, which receives, abandons speech samples
After notice, by the data dump of the speech samples.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910065909.8A CN109785834B (en) | 2019-01-24 | 2019-01-24 | Voice data sample acquisition system and method based on verification code |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910065909.8A CN109785834B (en) | 2019-01-24 | 2019-01-24 | Voice data sample acquisition system and method based on verification code |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109785834A true CN109785834A (en) | 2019-05-21 |
CN109785834B CN109785834B (en) | 2021-06-11 |
Family
ID=66502214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910065909.8A Active CN109785834B (en) | 2019-01-24 | 2019-01-24 | Voice data sample acquisition system and method based on verification code |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109785834B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223429A (en) * | 2019-06-19 | 2019-09-10 | 上海应用技术大学 | Voice access control system |
CN111128136A (en) * | 2019-11-28 | 2020-05-08 | 星络智能科技有限公司 | User-defined voice control method, computer equipment and readable storage medium |
CN112381512A (en) * | 2020-11-15 | 2021-02-19 | 周岳 | Verification system and verification method |
CN112422377A (en) * | 2020-10-26 | 2021-02-26 | 深圳Tcl新技术有限公司 | Intelligent terminal control method and device and computer readable storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107104803A (en) * | 2017-03-31 | 2017-08-29 | 清华大学 | It is a kind of to combine the user ID authentication method confirmed with vocal print based on numerical password |
US9986394B1 (en) * | 2017-06-26 | 2018-05-29 | Amazon Technologies, Inc. | Voice-based messaging |
-
2019
- 2019-01-24 CN CN201910065909.8A patent/CN109785834B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107104803A (en) * | 2017-03-31 | 2017-08-29 | 清华大学 | It is a kind of to combine the user ID authentication method confirmed with vocal print based on numerical password |
US9986394B1 (en) * | 2017-06-26 | 2018-05-29 | Amazon Technologies, Inc. | Voice-based messaging |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223429A (en) * | 2019-06-19 | 2019-09-10 | 上海应用技术大学 | Voice access control system |
CN111128136A (en) * | 2019-11-28 | 2020-05-08 | 星络智能科技有限公司 | User-defined voice control method, computer equipment and readable storage medium |
CN112422377A (en) * | 2020-10-26 | 2021-02-26 | 深圳Tcl新技术有限公司 | Intelligent terminal control method and device and computer readable storage medium |
CN112381512A (en) * | 2020-11-15 | 2021-02-19 | 周岳 | Verification system and verification method |
Also Published As
Publication number | Publication date |
---|---|
CN109785834B (en) | 2021-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109785834A (en) | A kind of voice data sample acquisition system and its method based on identifying code | |
CN101467204B (en) | Method and system for bio-metric voice print authentication | |
US8812319B2 (en) | Dynamic pass phrase security system (DPSS) | |
CN109473106A (en) | Vocal print sample collection method, apparatus, computer equipment and storage medium | |
CN104185868B (en) | Authentication voice and speech recognition system and method | |
AU2004300140B2 (en) | System and method for providing improved claimant authentication | |
KR101963993B1 (en) | Identification system and method with self-learning function based on dynamic password voice | |
US6529871B1 (en) | Apparatus and method for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases | |
US7222072B2 (en) | Bio-phonetic multi-phrase speaker identity verification | |
US20050138391A1 (en) | Biometric multimodal centralized authentication service | |
CN102413100A (en) | Voice-print authentication system having voice-print password picture prompting function and realization method thereof | |
CN111883140A (en) | Authentication method, device, equipment and medium based on knowledge graph and voiceprint recognition | |
CN108062464A (en) | Terminal control method and system based on Application on Voiceprint Recognition | |
US20080195395A1 (en) | System and method for telephonic voice and speech authentication | |
CN109873907A (en) | Call processing method, device, computer equipment and storage medium | |
CN107895576A (en) | The identification of service robot starts method and device | |
CN109636937A (en) | Voice Work attendance method, device and terminal device | |
CN109920435A (en) | A kind of method for recognizing sound-groove and voice print identification device | |
US20060085189A1 (en) | Method and apparatus for server centric speaker authentication | |
CN109729067A (en) | Voice punch card method, device, equipment and computer storage medium | |
Beigi | Challenges of LargeScale Speaker Recognition | |
CN109783822B (en) | Data sample identification system and method based on verification code | |
CN105718781A (en) | Method for operating terminal equipment based on voiceprint recognition and terminal equipment | |
KR20210117827A (en) | Voice service supply system and supply method using artificial intelligence | |
CN113593580B (en) | Voiceprint recognition method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |