CN106161727A - The typing of a kind of verbal instructions, recognition methods and device - Google Patents
The typing of a kind of verbal instructions, recognition methods and device Download PDFInfo
- Publication number
- CN106161727A CN106161727A CN201510130353.8A CN201510130353A CN106161727A CN 106161727 A CN106161727 A CN 106161727A CN 201510130353 A CN201510130353 A CN 201510130353A CN 106161727 A CN106161727 A CN 106161727A
- Authority
- CN
- China
- Prior art keywords
- password
- verbal instructions
- speech
- record
- speech record
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephone Function (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides the typing of a kind of verbal instructions, recognition methods and device, it is applied to mobile terminal, wherein method includes: prompting user carries out the input of verbal instructions information, and the Speech Record indicating user to input at least n times continuously when inputting verbal instructions information enters password；Obtain the verbal instructions information of user's input and store, from verbal instructions information, extracting each Speech Record enter password；Obtain the speech recognition password of user's input；The speech recognition password that user inputs with the N number of Speech Record prestored, is entered password and compares, when speech recognition password enter with N number of Speech Record any one in password identical time, then judge that speech recognition password is correct.Recording by continuously Speech Record being entered password, speech recognition password and Speech Record being entered any one in password and compares, quickly judge the correctness of speech recognition password.Avoid and problem that typing verbal instructions the longest is repeated several times, improve Consumer's Experience effect.
Description
Technical field
The present invention relates to communication technical field, particularly relate to the typing of a kind of verbal instructions, recognition methods and dress
Put.
Background technology
Existing mobile terminal is when verbal instructions such as typing control instructions, it usually needs user says several times
Identical phonetic order.Such as when user setup verbal instructions, common handling process is: remind user
Say password；After user explains order, user is reminded again to say password, the most repeated multiple times, until
Setting completed.Cause user time-consumingly the longest and need to repeat typing repeatedly when typing verbal instructions, reduce
Consumer's Experience.
Summary of the invention
It is an object of the invention to provide the typing of a kind of verbal instructions, recognition methods and device, keep away
Exempt from problem that typing verbal instructions the longest is repeated several times, improve Consumer's Experience effect.
The present invention provides the input method of a kind of verbal instructions, is applied to mobile terminal, described input method
Including:
Prompting user carries out the input of verbal instructions information, and indicates user inputting described verbal instructions information
Shi Lianxu inputs the Speech Record of at least n times and enters password, and wherein N is the integer more than or equal to 2；
Obtain the described verbal instructions information of user's input and store, carrying from described verbal instructions information
Take each Speech Record and enter password.
Wherein, from described verbal instructions information, extract each Speech Record enter password, particularly as follows:
Speech Record in described verbal instructions information is entered password and carries out segmentation according to Repeating Field, extract segmentation
After each Speech Record enter password.
Wherein, it is thus achieved that after the described verbal instructions information of user's input, described method also includes:
Judge described verbal instructions information the most only including, a Speech Record enters password, when being judged as YES,
Prompting user carries out the input of described verbal instructions information again, until obtaining the voice including at least n times
The described verbal instructions information of typing password also stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
Wherein, extracting after each Speech Record enters password from described verbal instructions information, described method also includes:
Obtain each Speech Record in described verbal instructions information and enter vocal print feature and the voice content of password.
The embodiment of the present invention also provides for the recognition methods of a kind of verbal instructions, is applied to mobile terminal, described side
Method includes:
Obtain the speech recognition password of user's input；
With the N number of Speech Record prestored, the described speech recognition password that user inputs is entered password compare
Right, when described speech recognition password enter with N number of described Speech Record any one in password identical time, then sentence
Disconnected described speech recognition password is correct.
Wherein, the described described speech recognition password that user is inputted and the N number of voice typing prestored
Password is compared, and specifically includes:
Extract vocal print feature and the voice content of described speech recognition password；
Vocal print feature and the voice content of described speech recognition password are entered in password with N number of described Speech Record
Any one Speech Record enter the vocal print feature of password and voice content is compared, when one of them voice typing
The vocal print feature of password and voice content respectively with vocal print feature and the voice content of described speech recognition password
When correspondence is consistent, then judge that described speech recognition password enters password with one of them Speech Record described identical.
The embodiment of the present invention also provides for the input device of a kind of verbal instructions, is applied to mobile terminal, described record
Enter device to include:
First processing module, for pointing out user the input carrying out verbal instructions information, and indicates user defeated
The Speech Record inputting at least n times when entering described verbal instructions information continuously enters password, and wherein N is for being more than
In the integer of 2；
Second processing module, for obtaining the described verbal instructions information of user's input and storing, from institute
Predicate sound password information extracts each Speech Record and enters password.
Wherein, described second processing module is further used for:
Speech Record in described verbal instructions information is entered password and carries out segmentation according to Repeating Field, extract segmentation
After each Speech Record enter password.
Wherein, described second processing module, after obtaining the described verbal instructions information of user's input, is also used
In:
Judge described verbal instructions information the most only including, a Speech Record enters password, when being judged as YES,
Prompting user carries out the input of described verbal instructions information again, until obtaining the voice including at least n times
The described verbal instructions information of typing password also stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
Wherein, described input device also includes:
First acquisition module, enters the vocal print spy of password for obtaining each Speech Record in described verbal instructions information
Seek peace voice content.
The embodiment of the present invention also provides for the identification device of a kind of verbal instructions, is applied to mobile terminal, described knowledge
Other device includes:
Second acquisition module, for obtaining the speech recognition password of user's input；
3rd processing module, N number of with prestore for the described speech recognition password that user is inputted
Speech Record enters password and compares, when described speech recognition password and N number of described Speech Record enter in password
When any one is identical, then judge that described speech recognition password is correct.
Wherein, described 3rd processing module specifically includes:
Extraction unit, for extracting vocal print feature and the voice content of described speech recognition password；
Comparing unit, for by described with N number of to vocal print feature and the voice content of described speech recognition password
Speech Record enters any one Speech Record in password and enters the vocal print feature of password and voice content is compared, when it
In Speech Record enter the vocal print feature of password and voice content respectively with the vocal print of described speech recognition password
Feature corresponding with voice content consistent time, then judge described speech recognition password and one of them Speech Record described
Enter password identical.
Beneficial effects of the present invention: carried out the input of verbal instructions information by prompting user, and indicate user
The Speech Record inputting at least n times when inputting verbal instructions information continuously enters password；Obtain user's input
Verbal instructions information also stores, and extracts each Speech Record and enter password, by voice from verbal instructions information
Identify that the Speech Record of password and storage enters any one in password and compares, quickly judge speech recognition password
Correctness.Avoid and problem that typing verbal instructions the longest is repeated several times, improve Consumer's Experience
Effect.
Accompanying drawing explanation
Fig. 1 represents the flow chart of steps of the input method of embodiment of the present invention verbal instructions；
Fig. 2 represents the flow chart of steps of the recognition methods of embodiment of the present invention verbal instructions
Fig. 3 represents in the recognition methods of the embodiment of the present invention verbal instructions speech recognition password and prestores
N number of Speech Record enter the flow chart of steps that password is compared；
Fig. 4 represents the flow chart of steps of the typing of embodiment of the present invention verbal instructions, recognition methods；
Fig. 5 represents the input device block diagram of embodiment of the present invention verbal instructions；
Fig. 6 represents the identification device block diagram of embodiment of the present invention verbal instructions；
What Fig. 7 represented embodiment of the present invention verbal instructions identifies the block diagram of the 3rd processing module in device.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing and specifically real
Execute example to describe the present invention.
The present invention is directed in prior art mobile terminal when typing verbal instructions, it usually needs user is several times
Say identical verbal instructions, cause user when typing verbal instructions time-consumingly compared with long and to need to repeat typing many
Problem that is secondary, that reduce the effect of Consumer's Experience, it is provided that the typing of a kind of verbal instructions, recognition methods
And device, record by continuously Speech Record being entered password, speech recognition password and Speech Record are entered in password
Any one compare, quickly judge the correctness of speech recognition password.Avoid and typing is repeated several times
The problem that verbal instructions is the longest, improves Consumer's Experience effect.
As it is shown in figure 1, the embodiment of the present invention provides the input method of a kind of verbal instructions, it is applied to mobile whole
End, described input method includes:
Step S100, prompting user carry out the input of verbal instructions information, and indicate user described in input
The Speech Record inputting at least n times during verbal instructions information continuously enters password, and wherein N is more than or equal to 2
Integer；
Step S200, the described verbal instructions information of acquisition user's input also store, from described voice
Password information is extracted each Speech Record and enters password.
Concrete, first mobile terminal points out user to carry out the input of verbal instructions information, and prompting mode is permissible
Show corresponding prompt text, it is also possible to for voice message, voice and literary composition can also be used by screen simultaneously
The mode that word combines.When mobile terminal carries out the input prompt of verbal instructions information to user, suggestion content
At least include: input Speech Record at least twice enters password continuously.Such as: use the side of screen displaying character
When formula is pointed out, there is " input twice Speech Record the most continuously and enter password " on interface in prompting.When adopting
When using voice message, mobile terminal " inputs twice Speech Record by voice broadcast the most continuously and enters password ".
When the mode using voice and word to combine is pointed out, then shown by screen " the most continuous
Input twice Speech Record and enter password " time, carry out voice broadcast simultaneously and " input twice Speech Record the most continuously
Enter password ".After user inputs corresponding verbal instructions information according to prompting, acquisition for mobile terminal user inputs
Verbal instructions information and store, from verbal instructions information, extract two or more voice
Typing password.Use the method to carry out Speech Record and enter the continuous recording of password, it is to avoid it is right that user is repeated several times
Verbal instructions carries out typing, solve time-consumingly the longest, typing be repeated several times cause the problem of poor user experience,
Save the typing time, improve the experience effect of user.
In the above embodiment of the present invention, step S200 extracts each language from described verbal instructions information
Sound typing password, particularly as follows:
Speech Record in described verbal instructions information is entered password and carries out segmentation according to Repeating Field, extract segmentation
After each Speech Record enter password.
Concrete, after mobile terminal obtains verbal instructions information and stores, in addition it is also necessary to verbal instructions is believed
Each Speech Record repeated in breath enters password and carries out segmentation, enters the voice of password due to each Speech Record during segmentation
Content repeats mutually, according to Repeating Field, each Speech Record repeated is entered password and carries out segmentation.Such as, mobile
The Speech Record comprising " griggles griggles griggles " in the verbal instructions information that terminal obtains enters password,
Repeating Field is " griggles ", is divided into " little according to Repeating Field by " griggles griggles griggles "
Fructus Mali pumilae ", " griggles ", " griggles ", complete Speech Record and enter the segmentation of password..
In the above embodiment of the present invention, obtain the described verbal instructions letter of user's input in step s 200
After breath, described method also includes:
Judge described verbal instructions information the most only including, a Speech Record enters password, when being judged as YES,
Prompting user carries out the input of described verbal instructions information again, until obtaining the voice including at least n times
The described verbal instructions information of typing password also stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
Concrete, mobile terminal is after the verbal instructions information obtaining user's input, in addition it is also necessary to verbal instructions
The Speech Record comprised in information enters password and judges, it is to avoid occurs that user not to be noted points out, is inputted
Verbal instructions information only comprises a Speech Record and enters the situation of password.After judgement, when verbal instructions information
In only include that a Speech Record enters password, then need mobile terminal be again with text prompt, voice message or
Any one in the mode that language and characters combines is pointed out.Make user can input correct comprising
Speech Record enters the verbal instructions information of password at least twice, and Speech Record to enter the voice content of password identical.Move
Dynamic terminal obtains the Speech Record including at least twice and enters after the verbal instructions information of password stores, from voice
Password information is extracted each Speech Record and enters password.When judged result is: verbal instructions information includes at least
Two Speech Records enter password, then the verbal instructions information of acquisition stored, and from verbal instructions information
Each Speech Record of extracting directly enters password.
In the above embodiment of the present invention, from described verbal instructions information, extract each in step s 200
After Speech Record enters password, described method also includes:
Obtain each Speech Record in described verbal instructions information and enter vocal print feature and the voice content of password.
Concrete, obtain each Speech Record in verbal instructions information and enter vocal print feature and the voice content of password,
Can be so that follow-up when carrying out speech recognition, the speech recognition password of user's input and Speech Record enter the ratio of password
Right.It should be noted that vocal print not only has specificity, and there is the feature of relative stability.Grow up with
After, the sound of people can keep relatively stablizing for a long time constant.No matter talker is deliberately to imitate other people sound and language
Gas, or whisper in sb.'s ear talk softly, even if imitating remarkably true to life, its vocal print differs the most all the time.Mobile whole
After end obtains vocal print feature, the safety of verbal instructions information can be ensured further, and then protection user uses
The safety of mobile terminal, it is to avoid other people know that voice content unties the situation of verbal instructions.But user exists
Typing Speech Record enters password continuously, due to word speed or difference firmly of enunciating, causes each Speech Record to enter password
Vocal print feature there is fine distinction, so even be same person, in its vocal print feature the most in the same time also
Difference.In acquisition verbal instructions information after voice content, it is simple to speech recognition process inputs with user
Speech recognition password compare.
The embodiment of the present invention also provides for the recognition methods of a kind of verbal instructions, is applied to mobile terminal, such as Fig. 2
Shown in, described method includes:
Step S300, the speech recognition password of acquisition user's input；
Step S400, the described speech recognition password that user is inputted and the N number of voice typing prestored
Password is compared, when described speech recognition password enters any one phase in password with N number of described Speech Record
Meanwhile, then judge that described speech recognition password is correct.
Concrete, during the identification carrying out verbal instructions, it is necessary first to the voice obtaining user's input is known
Other password, after acquisition for mobile terminal speech recognition password, moves speech recognition password eventually with being stored in advance in
N number of Speech Record in end enters password and compares, and whether judges speech recognition password according to comparison result
Correctly.When comparison result be speech recognition password enter with N number of Speech Record any one in password identical time,
Then prove that the speech recognition password that user inputs is correct.When comparison result is speech recognition password and N
Individual Speech Record enters any one in password when being different from, then prove that the speech recognition password of user's input is wrong
By mistake.
In the above embodiment of the present invention, as it is shown on figure 3, the institute's predicate in step S400, user inputted
Sound identification password enters password with the N number of Speech Record prestored and compares, and specifically includes:
Step S401, the vocal print feature extracting described speech recognition password and voice content；
Step S402, by the vocal print feature of described speech recognition password and voice content and N number of described voice
Any one Speech Record in typing password enters the vocal print feature of password and voice content is compared, when wherein one
Individual Speech Record enter the vocal print feature of password and voice content respectively with the vocal print feature of described speech recognition password
Corresponding with voice content consistent time, then judge described speech recognition password and one of them Speech Record entrance described
Make identical.
Concrete, the speech recognition password that user inputs is entered password with the N number of Speech Record prestored and enters
During row comparison, it is necessary first to obtain vocal print feature and the voice content of speech recognition password, then voice is known
Any one Speech Record that the vocal print feature of other password and voice content and N number of Speech Record enter in password enters password
Vocal print feature and voice content compare.When N number of Speech Record enters a Speech Record entrance in password
Vocal print feature and the voice content of order respectively with vocal print feature and the voice content corresponding of speech recognition password
During cause, then show that speech recognition password enters password with one of them Speech Record identical, then show what user inputted
Speech recognition password is correct.
With N number of Speech Record, speech recognition password can be entered password when comparison to compare successively, until
N number of Speech Record unanimously or is entered password comparison by comparison result to be completed.Can also be by speech recognition password and N
Individual Speech Record enters any one in password and compares, when, after a comparison, comparison result unanimously terminates this
Secondary comparison；When, after a comparison, comparison result is inconsistent, mobile terminal by speech recognition password with
N-1 Speech Record enters any one in password and compares, until comparison result is consistent or by N number of Speech Record
Enter the whole comparison of password to complete.
As shown in Figure 4, for typing, the flow chart of steps of recognition methods of embodiment of the present invention verbal instructions:
Step S101, prompting user carry out the input of verbal instructions information；Wherein need clearly when prompting:
The Speech Record inputting at least n times when inputting described verbal instructions information continuously enters password, and N is more than or equal to 2
Integer.
Step S102, the described verbal instructions information of acquisition user's input.
Step S103, judge described verbal instructions information the most only including, a Speech Record enters password, when
When being judged as YES, prompting user carries out the input of described verbal instructions information again, includes at least until obtaining
The Speech Record of n times enters the described verbal instructions information of password and stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
Step S104, obtain each Speech Record in described verbal instructions information and enter vocal print feature and the language of password
Sound content.
Step S105, the speech recognition password of acquisition user's input.
Step S106, the described speech recognition password that user is inputted and the N number of voice typing prestored
Password is compared, when described speech recognition password enters any one phase in password with N number of described Speech Record
Meanwhile, then judge that described speech recognition password is correct.
Enter password at speech recognition password user inputted with the N number of Speech Record prestored to compare
Time, first have to obtain vocal print feature and the voice content of speech recognition password, by the vocal print of speech recognition password
Feature and voice content and N number of Speech Record enter any one Speech Record in password enter password vocal print feature and
Voice content is compared, when one of them Speech Record enter the vocal print feature of password and voice content respectively with language
The vocal print feature of sound identification password corresponding with voice content consistent time, it is determined that speech recognition password and one of them
It is identical that Speech Record enters password.Then terminate whole flow process.
The embodiment of the present invention also provides for the input device of a kind of verbal instructions, is applied to mobile terminal, such as Fig. 5
Shown in, described input device includes:
First processing module 10, for pointing out user the input carrying out verbal instructions information, and indicates user
The Speech Record inputting at least n times when inputting described verbal instructions information continuously enters password, and wherein N is big
In the integer equal to 2；
Second processing module 20, for obtaining the described verbal instructions information of user's input and storing,
From described verbal instructions information, extract each Speech Record enter password.
In the above embodiment of the present invention, described second processing module 20 is further used for:
Speech Record in described verbal instructions information is entered password and carries out segmentation according to Repeating Field, extract segmentation
After each Speech Record enter password.
In the above embodiment of the present invention, described second processing module 20 is obtaining institute's predicate of user's input
After sound password information, it is additionally operable to:
Judge described verbal instructions information the most only including, a Speech Record enters password, when being judged as YES,
Prompting user carries out the input of described verbal instructions information again, until obtaining the voice including at least n times
The described verbal instructions information of typing password also stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
In the above embodiment of the present invention, as it is shown in figure 5, described input device also includes:
First acquisition module 30, enters the sound of password for obtaining each Speech Record in described verbal instructions information
Stricture of vagina feature and voice content.
The embodiment of the present invention also provides for the identification device of a kind of verbal instructions, is applied to mobile terminal, such as Fig. 6
Shown in, described identification device includes:
Second acquisition module 40, for obtaining the speech recognition password of user's input；
3rd processing module 50, for described speech recognition password user inputted and the N prestored
Individual Speech Record enters password and compares, when described speech recognition password and N number of described Speech Record enter in password
Any one identical time, then judge that described speech recognition password is correct.
In the above embodiment of the present invention, as it is shown in fig. 7, described 3rd processing module 50 specifically includes:
Extraction unit 51, for extracting vocal print feature and the voice content of described speech recognition password；
Comparing unit 52, for by the vocal print feature of described speech recognition password and voice content and N number of institute
Any one Speech Record in predicate sound typing password enters the vocal print feature of password and voice content is compared, when
One of them Speech Record enter the vocal print feature of password and voice content respectively with the sound of described speech recognition password
Stricture of vagina feature corresponding with voice content consistent time, then judge described speech recognition password and one of them voice described
Typing password is identical.
The typing of a kind of verbal instructions of the embodiment of the present invention, recognition methods, carry out voice by prompting user
The input of password information, and indicate user to input the language of at least n times continuously when inputting verbal instructions information
Sound typing password；Obtain the verbal instructions information of user's input and store, carrying from verbal instructions information
Take each Speech Record and enter password, the Speech Record of speech recognition password with storage is entered any one in password and carries out
Comparison, quickly judges the correctness of speech recognition password.Avoid that typing verbal instructions is repeated several times is time-consuming
Longer problem, improves Consumer's Experience effect.
It should be noted that the present invention provide verbal instructions typing, identify device be apply above-mentioned side
The device of method, then all embodiments of said method are all applicable to this device, and all can reach same or similar
Beneficial effect.
Above-described is the preferred embodiment of the present invention, it should be pointed out that for the ordinary people of the art
For Yuan, some improvements and modifications can also be made under without departing from principle premise of the present invention, these
Improvements and modifications are the most within the scope of the present invention.
Claims (12)
1. an input method for verbal instructions, is applied to mobile terminal, it is characterised in that described typing side
Method includes:
Prompting user carries out the input of verbal instructions information, and indicates user inputting described verbal instructions information
Shi Lianxu inputs the Speech Record of at least n times and enters password, and wherein N is the integer more than or equal to 2；
Obtain the described verbal instructions information of user's input and store, carrying from described verbal instructions information
Take each Speech Record and enter password.
2. the input method of verbal instructions as claimed in claim 1, it is characterised in that from described voice mouth
Make and information is extracted each Speech Record enter password, particularly as follows:
Speech Record in described verbal instructions information is entered password and carries out segmentation according to Repeating Field, extract segmentation
After each Speech Record enter password.
3. the input method of verbal instructions as claimed in claim 1, it is characterised in that obtain user's input
Described verbal instructions information after, described method also includes:
Judge described verbal instructions information the most only including, a Speech Record enters password, when being judged as YES,
Prompting user carries out the input of described verbal instructions information again, until obtaining the voice including at least n times
The described verbal instructions information of typing password also stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
4. the input method of verbal instructions as claimed in claim 1, it is characterised in that from described voice mouth
Making and extract after each Speech Record enters password in information, described method also includes:
Obtain each Speech Record in described verbal instructions information and enter vocal print feature and the voice content of password.
5. a recognition methods for verbal instructions, is applied to mobile terminal, it is characterised in that described method bag
Include:
Obtain the speech recognition password of user's input；
With the N number of Speech Record prestored, the described speech recognition password that user inputs is entered password compare
Right, when described speech recognition password enter with N number of described Speech Record any one in password identical time, then sentence
Disconnected described speech recognition password is correct.
6. the recognition methods of verbal instructions as claimed in claim 5, it is characterised in that described that user is defeated
The described speech recognition password entered and the N number of Speech Record prestored enter password and compare, and specifically include:
Extract vocal print feature and the voice content of described speech recognition password；
Vocal print feature and the voice content of described speech recognition password are entered in password with N number of described Speech Record
Any one Speech Record enter the vocal print feature of password and voice content is compared, when one of them voice typing
The vocal print feature of password and voice content respectively with vocal print feature and the voice content of described speech recognition password
When correspondence is consistent, then judge that described speech recognition password enters password with one of them Speech Record described identical.
7. an input device for verbal instructions, is applied to mobile terminal, it is characterised in that described typing fills
Put and include:
First processing module, for pointing out user the input carrying out verbal instructions information, and indicates user defeated
The Speech Record inputting at least n times when entering described verbal instructions information continuously enters password, and wherein N is for being more than
In the integer of 2；
Second processing module, for obtaining the described verbal instructions information of user's input and storing, from institute
Predicate sound password information extracts each Speech Record and enters password.
8. the input device of verbal instructions as claimed in claim 7, it is characterised in that described second processes
Module is further used for:
Speech Record in described verbal instructions information is entered password and carries out segmentation according to Repeating Field, extract segmentation
After each Speech Record enter password.
9. the input device of verbal instructions as claimed in claim 7, it is characterised in that described second processes
Module, after obtaining the described verbal instructions information of user's input, is additionally operable to:
Judge described verbal instructions information the most only including, a Speech Record enters password, when being judged as YES,
Prompting user carries out the input of described verbal instructions information again, until obtaining the voice including at least n times
The described verbal instructions information of typing password also stores；
When being judged as NO, the described verbal instructions information obtained is stored, and from described verbal instructions
Information is extracted each Speech Record and enters password.
10. the input device of verbal instructions as claimed in claim 7, it is characterised in that described typing fills
Put and also include:
First acquisition module, enters the vocal print spy of password for obtaining each Speech Record in described verbal instructions information
Seek peace voice content.
The identification device of 11. 1 kinds of verbal instructions, is applied to mobile terminal, it is characterised in that described identification
Device includes:
Second acquisition module, for obtaining the speech recognition password of user's input；
3rd processing module, N number of with prestore for the described speech recognition password that user is inputted
Speech Record enters password and compares, when described speech recognition password and N number of described Speech Record enter in password
When any one is identical, then judge that described speech recognition password is correct.
The identification device of 12. verbal instructions as claimed in claim 11, it is characterised in that at the described 3rd
Reason module specifically includes:
Extraction unit, for extracting vocal print feature and the voice content of described speech recognition password；
Comparing unit, for by described with N number of to vocal print feature and the voice content of described speech recognition password
Speech Record enters any one Speech Record in password and enters the vocal print feature of password and voice content is compared, when it
In Speech Record enter the vocal print feature of password and voice content respectively with the vocal print of described speech recognition password
Feature corresponding with voice content consistent time, then judge described speech recognition password and one of them Speech Record described
Enter password identical.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510130353.8A CN106161727A (en) | 2015-03-24 | 2015-03-24 | The typing of a kind of verbal instructions, recognition methods and device |
| PCT/CN2016/076909 WO2016150369A1 (en) | 2015-03-24 | 2016-03-21 | Method and device for recording and recognising voice password |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510130353.8A CN106161727A (en) | 2015-03-24 | 2015-03-24 | The typing of a kind of verbal instructions, recognition methods and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106161727A true CN106161727A (en) | 2016-11-23 |
Family
ID=56977812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510130353.8A Withdrawn CN106161727A (en) | 2015-03-24 | 2015-03-24 | The typing of a kind of verbal instructions, recognition methods and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106161727A (en) |
| WO (1) | WO2016150369A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020029367A1 (en) * | 2018-08-09 | 2020-02-13 | 平安科技（深圳）有限公司 | Case processing opinion input method and device, computer apparatus, and storage medium |
| CN111145755A (en) * | 2019-12-24 | 2020-05-12 | 北京摩拜科技有限公司 | Method and device for calling unlocking interface of shared bicycle application by voice and terminal equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102404287A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Voiceprint authentication system and method for determining voiceprint authentication threshold value by data multiplexing method |
| CN102815279A (en) * | 2011-06-10 | 2012-12-12 | 沈阳君天科技股份有限公司 | Method and device for directly starting automobile by voice and preventing thievery on basis of embedded system |
| 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 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101685635A (en) * | 2008-09-23 | 2010-03-31 | 吕共欣 | Identity authentication system and method |
| CN102238189B (en) * | 2011-08-01 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Voiceprint password authentication method and system |
| US20130317827A1 (en) * | 2012-05-23 | 2013-11-28 | Tsung-Chun Fu | Voice control method and computer-implemented system for data management and protection |
| CN103546622A (en) * | 2012-07-12 | 2014-01-29 | 百度在线网络技术（北京）有限公司 | Control method, device and system for identifying login on basis of voiceprint |
-
2015
- 2015-03-24 CN CN201510130353.8A patent/CN106161727A/en not_active Withdrawn
-
2016
- 2016-03-21 WO PCT/CN2016/076909 patent/WO2016150369A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102404287A (en) * | 2010-09-14 | 2012-04-04 | 盛乐信息技术（上海）有限公司 | Voiceprint authentication system and method for determining voiceprint authentication threshold value by data multiplexing method |
| CN102815279A (en) * | 2011-06-10 | 2012-12-12 | 沈阳君天科技股份有限公司 | Method and device for directly starting automobile by voice and preventing thievery on basis of embedded system |
| 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 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020029367A1 (en) * | 2018-08-09 | 2020-02-13 | 平安科技（深圳）有限公司 | Case processing opinion input method and device, computer apparatus, and storage medium |
| CN111145755A (en) * | 2019-12-24 | 2020-05-12 | 北京摩拜科技有限公司 | Method and device for calling unlocking interface of shared bicycle application by voice and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016150369A1 (en) | 2016-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106653021B (en) | Voice wake-up control method and device and terminal | |
| US20170323644A1 (en) | Speaker identification device and method for registering features of registered speech for identifying speaker | |
| CN105869640B (en) | Method and device for recognizing voice control instruction aiming at entity in current page | |
| WO2017054122A1 (en) | Speech recognition system and method, client device and cloud server | |
| US20160316366A1 (en) | Electronic device and voiceprint authentication method | |
| CN106782536A (en) | A kind of voice awakening method and device | |
| CN108447471A (en) | Audio recognition method and speech recognition equipment | |
| CN104157286B (en) | A kind of phrasal acquisition methods and device | |
| CN107305575A (en) | The punctuate recognition methods of human-machine intelligence's question answering system and device | |
| CN110111778B (en) | Voice processing method and device, storage medium and electronic equipment | |
| CN104639742B (en) | Method and device for assisting in learning spoken language by mobile terminal | |
| CN104008752A (en) | Speech recognition device and method, and semiconductor integrated circuit device | |
| CN104142796A (en) | Unlocking method of terminal and terminal | |
| CN107437417A (en) | Based on speech data Enhancement Method and device in Recognition with Recurrent Neural Network speech recognition | |
| CN107291704A (en) | Treating method and apparatus, the device for processing | |
| CN110444190A (en) | Method of speech processing, device, terminal device and storage medium | |
| CN107315688A (en) | A kind of Monkey method of testings and device | |
| CN110517668A (en) | A kind of Chinese and English mixing voice identifying system and method | |
| CN104134439A (en) | Method, device and system for obtaining idioms | |
| KR102312993B1 (en) | Method and apparatus for implementing interactive message using artificial neural network | |
| CN104200807B (en) | A kind of ERP sound control methods | |
| CN109545203A (en) | Audio recognition method, device, equipment and storage medium | |
| CN106161727A (en) | The typing of a kind of verbal instructions, recognition methods and device | |
| CN103903615B (en) | A kind of information processing method and electronic equipment | |
| CN105353957A (en) | Information display method and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20161123 |
|
| WW01 | Invention patent application withdrawn after publication |