CN104598122B - A kind of terminal - Google Patents
A kind of terminal Download PDFInfo
- Publication number
- CN104598122B CN104598122B CN201410714989.2A CN201410714989A CN104598122B CN 104598122 B CN104598122 B CN 104598122B CN 201410714989 A CN201410714989 A CN 201410714989A CN 104598122 B CN104598122 B CN 104598122B
- Authority
- CN
- China
- Prior art keywords
- target text
- user
- voice
- terminal
- phonetic feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
Abstract
The embodiment of the invention discloses a kind of terminals, comprising: input unit, for receiving the unlock instruction of user's input, unlock instruction is used to release the operation locking of terminal；Selecting unit, for extracting target text, and displaying target text from default dictionary；Recording unit, for opening voice recording function, record user first reads aloud voice；Processing unit, for judging that the phonetic feature of the phonetic feature for reading aloud voice standard pronunciation whether corresponding with target text is consistent, if so, releasing the operation locking of terminal；Prompt information is read again if it is not, then providing, and is returned to execute and described recorded the step of reading aloud voice of the user.Using the present invention, the speech unlocking instruction of user's input can receive, and judge whether the bright pronunciation of user is consistent with the standard pronunciation of target text, if being consistent, success is unlocked, if not being consistent, user is then prompted to read again, it can be achieved that improving the pronunciation level of user during speech unlocking.
Description
Technical field
The present invention relates to electronic technology field more particularly to a kind of terminals.
Background technique
With the development of mobile terminal and intelligent interaction, speech unlocking has become a kind of widely used unlocking method.It is existing
There is the scheme of speech unlocking to have very much, can come by comparing the phonetic feature of user and pre-set received pronunciation feature real
Existing speech unlocking function.For example, parsing recorded speech by recording user speech to generate recording feature, and it is special to compare recording
Whether sign is consistent with the phonetic feature of standard pronunciation, if be consistent, speech unlocking success is determined, otherwise, it is determined that speech unlocking
Failure.In another example the problem of being preset by display, user say answer, the phonetic feature of the terminal recognition answer, and with
The phonetic feature of pre-set model answer compares, if the two phonetic feature is consistent, speech unlocking is successful, otherwise voice
Unlock failure.
But during above-mentioned speech unlocking, user causes speech unlocking to fail often due to pronunciation is nonstandard, and
Need the speech unlocking process new again by triggerings such as keys, poor user experience.
Summary of the invention
The embodiment of the present invention provides a kind of terminal, which can receive the speech unlocking instruction of user's input, and judge
Whether the bright pronunciation of user is consistent with the standard pronunciation of target text, if being consistent, unlocks success, if not being consistent, prompts to use
It reads again, it can be achieved that improving the pronunciation level of user during speech unlocking at family.
The embodiment of the invention discloses a kind of terminal, which includes:
Input unit, for receiving the unlock instruction of user's input, the unlock instruction is used to release the operation lock of terminal
It is fixed；
Selecting unit for extracting target text from default dictionary, and shows the target text；
Recording unit, for opening voice recording function, record the user first reads aloud voice；
Processing unit, for judging the phonetic feature standard whether corresponding with the target text for reading aloud voice
The phonetic feature of pronunciation is consistent, if so, releasing the operation locking of the terminal；Prompt information is read again if it is not, then providing,
And it returns to execute and described records the step of reading aloud voice of the user.
Specifically, the terminal further include: first control unit, for executing the unlatching voice in the recording unit
After the step of recording function, the number that the user reads aloud the target text is recorded；If the user reads aloud the mesh
The number for marking text is more than preset times, then releases the operation locking of the terminal.
Specifically, the terminal further include: the second control unit, for executing the unlatching voice in the recording unit
After the step of recording function, preset timer is opened, for recording the working time of the recording function；If the recording
The working time of function is more than preset operating time, then releases the operation locking of the terminal.
The unlock instruction that the embodiment of the present invention is inputted by receiving user, extracts target text from default dictionary, opens
Open voice recording function, record the voice of reading aloud of user, and judge to read aloud voice phonetic feature whether with target text pair
The phonetic feature for the standard pronunciation answered is consistent, if so, releasing the operation locking of terminal；If it is not, user is then prompted to read again, and return
Described in receipt row record user the step of reading aloud voice, it can be achieved that during speech unlocking improve user pronunciation level.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, embodiment will be described below
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the flow diagram of the first embodiment of voice unlocking method provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of the second embodiment of voice unlocking method provided in an embodiment of the present invention；
Fig. 3 is the flow diagram of the 3rd embodiment of voice unlocking method provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram of the first embodiment of terminal provided in an embodiment of the present invention；
Fig. 5 is the structural schematic diagram of the second embodiment of terminal provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of the 3rd embodiment of terminal provided in an embodiment of the present invention；
Fig. 7 is the structural schematic diagram of the fourth embodiment of terminal provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It is the flow diagram of the first embodiment of voice unlocking method provided in an embodiment of the present invention, the party referring to Fig. 1
Method includes:
Step S101: the unlock instruction of user's input is received.
Specifically, unlock instruction can be used for releasing the operation locking of terminal, operation locking is that terminal is to prevent in suspend mode shape
Set state is misused under state, it just can be with operating terminal after unlock.In practical application, unlock instruction is either press
The instruction of power button triggering unlock is also possible to press the instruction of the unlock of specific unlock combination button triggering, not limit here
System.Here, after the unlock instruction for receiving user's input, preset speech unlocking program can be called, for verifying user's
Whether the phonetic feature for reading aloud voice is consistent with the phonetic feature of the standard pronunciation of target text, if being consistent, releases terminal
Otherwise operation locking cannot release the operation locking of terminal.
Step S103: target text, and displaying target text are extracted from default dictionary.
Specifically, after the unlock instruction for receiving user target text can be extracted from default dictionary, and on the screen
Displaying target text, for prompting user to read aloud target text.Here, target text may include multiple lists in default dictionary
Word, i.e. target text can be sentence, paragraph or article, and in practical application, target text can also be single letter, here
With no restriction.
Here, the target text of multilingual can be provided by presetting in dictionary, for example, default dictionary includes the target of English
The target text of text and German.In the specific implementation, default dictionary is either pre-stored dictionary, is also possible to external word
Library, for example, default dictionary can be with on-line joining process to external Baidu's dictionary.Example is only a kind of realization side of the embodiment of the present invention
Formula, can be different in actual use, should not be construed as limiting.
In the specific implementation, target text can be extracted from default dictionary at random.Furthermore it is also possible to according to the bright of user
Read record extracts target text, for example, in default dictionary, selects text that user do not read aloud at random as target text,
In another example selecting at random that user has read aloud but pronouncing non-type text as target text in default dictionary.It is optional
, in the specific implementation, target word can also be extracted according to preset order, which can be the pronunciation of user setting
Learning sequence is also possible to the stationary arrangement sequence of the text in default dictionary, here with no restriction.
Step S105: voice recording function is opened, record user reads aloud voice.
Specifically, terminal can open voice recording function, to remember after prompting ownership goal word or simultaneously
It employs family and voice is read aloud for target word.
In the specific implementation, terminal can open included sound-recording function record user read aloud voice, the can also be opened
The sound-recording function record user's of tripartite's recording application reads aloud voice.In the specific implementation, the recording for reading aloud voice of record user
File can be reserved for preset path；For third party's recording application, record user the recording file for reading aloud voice can be reserved for
The specified path of third party's recording application.
Step S107: the phonetic feature of the phonetic feature standard pronunciation whether corresponding with target text of voice is read aloud in judgement
It is consistent.
Specifically, record user read aloud voice after, may compare the phonetic feature and target text of reading aloud voice
The phonetic feature of corresponding standard pronunciation can determine that pronunciation of the user for target text if the two phonetic feature is consistent
Otherwise standard can determine that user is nonstandard for the pronunciation of target text.
In practical application, if the voice of the phonetic feature for reading aloud voice of user standard pronunciation corresponding with target text
Feature is not consistent, i.e. user is nonstandard for the pronunciation of target text, then can provide user reads aloud the corresponding association's list of voice
Word；The phonetic feature of the standard pronunciation of association's word is consistent with the phonetic feature for reading aloud voice of user, i.e. association's word
It is the most similar word of practical pronunciation with user.It should be noted that the form of the composition of association's word can be with the structure of target text
It is consistent at form, for example, if target text is letter, correspondingly, association's word can be association's letter；If target text
It is phrase, correspondingly, association's word can be associative phrase.
It should be noted that step S107 and step S105 can also be executed parallel, for example, target text is one long section
Fall, terminal can while user reads aloud the long paragraph, judge user whether pronunciation standard, if user pronunciation is nonstandard,
Prompt can be provided in time, to inform which sentence of user or pronunciation of words are wrong.For step S107 and step S105
Execution sequence with no restriction, do not influence the substantive content of the embodiment of the present invention.
Here, when the phonetic feature phase for judging the phonetic feature for reading aloud voice standard pronunciation corresponding with target text
Step S109 then can be performed in symbol；Otherwise, step S111 can be executed, and continues to record user and reads aloud voice, for holding again
Row step S107.
In the specific implementation, if the voice of the phonetic feature for reading aloud voice of user standard pronunciation corresponding with target text
Feature is not consistent, i.e. the pronunciation of user is nonstandard, then can enter pronunciation training process, that is, repeat step S105 to step
S107, until the phonetic feature of the phonetic feature for reading aloud voice of new record standard pronunciation corresponding with target text is consistent, i.e.,
The pronunciation standard of user.
Step S109: the operation locking of terminal is released.
Specifically, if the first time of user read aloud the phonetic feature for reading aloud voice of target text and the mark of target text
The phonetic feature of quasi- pronunciation is consistent, then can be determined that speech unlocking success, releases the operation locking of terminal.
In addition, if user read aloud in speech training processes above-mentioned the phonetic feature for reading aloud voice of target text with
The phonetic feature of the standard pronunciation of target text is consistent, it is possible to determine that speech unlocking success releases the operation locking of terminal.
Step S111: it provides and reads prompt information again.
Specifically, if the phonetic feature for the reading aloud voice standard corresponding with target text that user reads aloud target text is read
The phonetic feature of sound is not consistent, and can provide the information of the standard pronunciation of target text, for example, showing the sound of the target text
Mark, or read aloud the standard pronunciation of the target text.
In the specific implementation, if the first time of user read aloud the phonetic feature and target text for reading aloud voice of target text
The phonetic feature of standard pronunciation be not consistent, then can be determined that speech unlocking fails, stressed prompt information be provided.
In addition, if user read aloud in speech training processes above-mentioned the phonetic feature for reading aloud voice of target text with
The phonetic feature of the standard pronunciation of target text is not consistent, it is possible to determine that speech unlocking failure provides stressed prompt information.
It should be noted that reading prompt information again can also include other prompt informations, for example, prompting user by dialog box
Again target text is read aloud, in another example, prompt user to read aloud target text again by voice messaging.Example is only of the invention real
A kind of implementation of example is applied, can be different in actual use, it should not be construed as limiting.
Further, the embodiment of the present invention can record user and read aloud target text after opening voice recording function
Number；If the number that user reads aloud target text is more than preset times, the operation locking of terminal is released.Practical application
In, if the number that user reads aloud target text in speech training processes is more than preset times, even if user reads aloud target text
The pronunciation of word is nonstandard, can also release the operation locking of terminal, and terminates speech training processes.Optionally, as other one
Kind embodiment, the embodiment of the present invention can open preset timer, for recording the record after opening voice recording function
The working time of function processed；If the working time of the recording function is more than preset operating time, the operation lock of terminal is released
It is fixed.In practical application, if the duration that user carries out voice training is more than preset time, even if user reads aloud target text
Pronunciation it is nonstandard, the operation locking of terminal can also be released, and terminate speech training processes.
Further, the default dictionary in the embodiment of the present invention may include the first sub- dictionary and the second sub- dictionary；This
The step S103 of inventive embodiments can be with specifically: selects target text from the second sub- dictionary；After step S107, if
Judge that the phonetic feature of the phonetic feature for reading aloud voice standard pronunciation corresponding with target text is consistent, target text can be moved
To the first sub- dictionary.In practical application, user can be had been able to according to the bright read record of user by the target text of pronunciation standard
Word is placed in the first sub- dictionary, and extracts target text from the second sub- dictionary, i.e., does not reresent user and read aloud and have been able to
The word etc. of standard.
Referring to fig. 2, be voice unlocking method provided in an embodiment of the present invention second embodiment flow diagram, the party
Method includes:
Step S201: the unlock instruction of user's input is received.
Specifically, unlock instruction executes preset speech unlocking program for triggering, in the specific implementation, defeated receiving user
After the unlock instruction entered, user can be prompted to read aloud target text, for verify user the phonetic feature for reading aloud voice whether
It is consistent with the phonetic feature of the standard pronunciation of target text, if being consistent, releases the operation locking of terminal, otherwise, cannot release
The operation of terminal locks.
Step S203: target text is selected from the second sub- dictionary of default dictionary.
Specifically, default dictionary may include the first sub- dictionary and the second sub- dictionary, wherein can be used in the first sub- dictionary
Storage user has been able to word or phrase of pronunciation standard etc., the second dictionary can be used for storing user fail pronunciation standard or
Not yet verify word or the phrase etc. of user pronunciation.In the specific implementation, can determine whether user's after user reads aloud target text
Pronunciation whether standard can be by mesh if the phonetic feature for the target text that user reads aloud is consistent with the phonetic feature of standard pronunciation
Mark text moves to the first sub- dictionary, to be the first sub- dictionary and the second sub- dictionary to distinguish default dictionary.It, can in practical application
To extract target text from the second sub- dictionary, the list for failing pronunciation standard to prompt user to read aloud or not yet verifying pronunciation
Word or phrase etc..
In the specific implementation, target text can be extracted from the second sub- dictionary at random.It optionally, can also be according to default
Sequence extracts target word, which can be the pronunciation training sequence of user setting, is also possible to the second sub- dictionary
In text stationary arrangement sequence, here with no restriction.
Step S205: voice recording function is opened, record user reads aloud voice.
Specifically, terminal can open voice recording function, to remember after prompting ownership goal word or simultaneously
It employs family and voice is read aloud for target word.
In the specific implementation, terminal can open included sound-recording function record user read aloud voice, the can also be opened
The sound-recording function record user's of tripartite's recording application reads aloud voice.In the specific implementation, the recording for reading aloud voice of record user
File can be reserved for preset path；For third party's recording application, record user the recording file for reading aloud voice can be reserved for
The specified path of third party's recording application.
In practical application, after opening voice recording function, also recordable user reads aloud the number of target text；If
The number that user reads aloud target text is more than preset times, then releases the operation locking of terminal, and terminates speech training processes.It can
Choosing, alternatively embodiment can also open preset timer, for remembering after opening voice recording function
Record the working time of the recording function；If the working time of the recording function is more than preset operating time, terminal is released
Operation locking, and terminate speech training processes.
Step S207: the phonetic feature of the phonetic feature standard pronunciation whether corresponding with target text of voice is read aloud in judgement
It is consistent.
Specifically, record user read aloud voice after, may compare the phonetic feature and target text of reading aloud voice
The phonetic feature of corresponding standard pronunciation can determine that pronunciation of the user for target text if the two phonetic feature is consistent
Otherwise standard can determine that user is nonstandard for the pronunciation of target text.
In practical application, if user reads aloud the language of the phonetic feature standard pronunciation corresponding with target text of target text
Sound feature is not consistent, i.e. user is nonstandard for the pronunciation of target text, then can provide user reads aloud the corresponding association of voice
Word；The phonetic feature of the standard pronunciation of association's word is consistent with the phonetic feature for reading aloud voice of user, i.e. association's list
Word is the most similar word of practical pronunciation with user.It should be noted that the form of the composition of association's word can be with target text
The form of the composition is consistent, for example, if target text is letter, correspondingly, association's word can be association's letter；If target is literary
Word is phrase, correspondingly, association's word can be associative phrase.
It should be noted that step S207 and step S205 can also be executed parallel, for example, target text is one long section
Fall, terminal can while user reads aloud the long paragraph, judge user whether pronunciation standard, if user pronunciation is nonstandard,
Prompt can be provided in time, to inform which sentence of user or pronunciation of words are wrong.For step S207 and step S205
Execution sequence with no restriction, do not influence the substantive content of the embodiment of the present invention.
Here, when the phonetic feature phase for judging the phonetic feature for reading aloud voice standard pronunciation corresponding with target text
Step S209 then can be performed in symbol；Otherwise, step S213 can be executed, and continues to record user and reads aloud voice, for holding again
Row step S207.
In the specific implementation, if user reads aloud the language of the phonetic feature standard pronunciation corresponding with target text of target text
Sound feature is not consistent, i.e. the pronunciation of user is nonstandard, then can enter pronunciation training process, that is, repeat step S205 extremely
Step S207, until the phonetic feature phase of the phonetic feature for reading aloud voice of new record standard pronunciation corresponding with target text
Symbol, the i.e. pronunciation standard of user.
Step S209: the operation locking of terminal is released.
Specifically, if user reads aloud the voice spy of the phonetic feature standard pronunciation corresponding with target text of target text
Sign is consistent, then can release the operation locking of terminal.
Specific implementation, if the first time of user reads aloud the phonetic feature of reading aloud voice and target text of target text
The phonetic feature of standard pronunciation is consistent, then can be determined that speech unlocking success, releases the operation locking of terminal；In addition, if with
The phonetic feature for reading aloud voice of target text and the standard pronunciation of target text are read aloud in speech training processes above-mentioned in family
Phonetic feature be consistent, it is possible to determine that speech unlocking success, release terminal operation locking.
Step S211: target text is moved into the first sub- dictionary.
Specifically, default dictionary may include the first sub- dictionary and the second sub- dictionary, wherein can be used in the first sub- dictionary
Storage user has been able to word or phrase of pronunciation standard etc., the second dictionary can be used for storing user fail pronunciation standard or
Not yet verify word or the phrase etc. of user pronunciation.If user reads aloud the phonetic feature and target for reading aloud voice of target text
The phonetic feature of the standard pronunciation of text is consistent, then target text can be moved to the first sub- dictionary, to preset dictionary to distinguish
For the first sub- dictionary and the second sub- dictionary.
Step S213: it provides and reads prompt information again.
Specifically, if the phonetic feature for the reading aloud voice standard corresponding with target text that user reads aloud target text is read
The phonetic feature of sound is not consistent, and can provide the information of the standard pronunciation of target text, for example, showing the sound of the target text
Mark, or read aloud the standard pronunciation of the target text.
In the specific implementation, if the first time of user read aloud the phonetic feature and target text for reading aloud voice of target text
The phonetic feature of standard pronunciation be not consistent, then can be determined that speech unlocking fails, stressed prompt information be provided；In addition, if
User reads aloud the phonetic feature for reading aloud voice of target text in speech training processes above-mentioned and the standard of target text is read
The phonetic feature of sound is not consistent, it is possible to determine that speech unlocking failure provides stressed prompt information.
It should be noted that reading prompt information again can also include other prompt informations, for example, prompting user by dialog box
Again target text is read aloud, in another example, prompt user to read aloud target text again by voice messaging.Example is only of the invention real
A kind of implementation of example is applied, can be different in actual use, it should not be construed as limiting.
It is the flow diagram of the 3rd embodiment of voice unlocking method provided in an embodiment of the present invention referring to Fig. 3, it should
Method includes:
Step S301: speech pattern is preset.
Specifically, speech pattern can also be preset before the unlock instruction for receiving user's input；The voice mould
Formula is used to indicate the mode of the phonetic feature of the corresponding standard pronunciation of target text；In practical application, same target text is not
Standard pronunciation under same language system is different, for example, Americanese says that the phonetic feature of " There " and Indian English are said
The phonetic feature of " There " is different.
In the specific implementation, the speech pattern can both be preset by user, it can also be according to the system parameter of terminal
It obtains, for example, setting should if the version number of mobile phone or other systems parameter indicate that the mobile phone is the mobile phone of India's standard
The speech pattern of mobile phone is India's speech pattern.Example is only a kind of implementation of the embodiment of the present invention, can in actual use
With difference, should not be construed as limiting.
Step S303: the unlock instruction of user's input is received.
Specifically, unlock instruction executes preset speech unlocking program for triggering, in the specific implementation, defeated receiving user
After the unlock instruction entered, user can be prompted to read aloud target text, for verify user the phonetic feature for reading aloud voice whether
It is consistent with the phonetic feature of the standard pronunciation of target text, if being consistent, releases the operation locking of terminal, otherwise, cannot release
The operation of terminal locks.
Step S305: target text, and displaying target text are extracted from default dictionary.
Specifically, after the unlock instruction for receiving user target text can be extracted from default dictionary, and on the screen
Displaying target text, for prompting user to read aloud target text.Here, target text may include multiple lists in default dictionary
Word, i.e. target text can be sentence, paragraph or article, and in practical application, target text can also be single letter, here
With no restriction.
Step S307: voice recording function is opened, record user reads aloud voice.
Specifically, terminal can open voice recording function, to remember after prompting ownership goal word or simultaneously
It employs family and voice is read aloud for target word.
In the specific implementation, terminal can open included sound-recording function record user read aloud voice, the can also be opened
The sound-recording function record user's of tripartite's recording application reads aloud voice.In the specific implementation, the recording for reading aloud voice of record user
File can be reserved for preset path；For third party's recording application, record user the recording file for reading aloud voice can be reserved for
The specified path of third party's recording application.
Step S309: the phonetic feature mark whether corresponding with the target text under above-mentioned speech pattern of voice is read aloud in judgement
The phonetic feature of quasi- pronunciation is consistent.
Here, the corresponding standard pronunciation of target text is that the corresponding standard of language system of aforementioned voice mode instruction is read
Sound.In practical application, standard pronunciation of the same target text under different language systems is different, for example, Americanese is said
The phonetic feature and Indian English of " There " say that the phonetic feature of " There " is different.Therefore, in the bright of record user
After reading voice, the phonetic feature that may compare the standard pronunciation that the phonetic feature for reading aloud voice is indicated with aforementioned voice mode is
It is no to be consistent, if the two phonetic feature is consistent, it can determine that user for the pronunciation standard of target text, otherwise, can determine that use
Family is nonstandard for the pronunciation of target text.
Here, when judging that corresponding with the target text under the aforementioned voice mode standard of the phonetic feature for reading aloud voice reads
The phonetic feature of sound is consistent, then step S311 can be performed；Otherwise, it can execute step 313, and continue to record user and read aloud language
Sound, for executing step S309 again.In the specific implementation, pronunciation training mistake can be entered if the pronunciation of user is nonstandard
Journey repeats step S307 to step S309, until user pronunciation standard.
Step S311: the operation locking of terminal is released.
Specifically, if user's phonetic feature for reading aloud target text is corresponding with the target text under aforementioned voice mode
The phonetic feature of standard pronunciation is consistent, then can release the operation locking of terminal.
Specific implementation, if the first time of user reads aloud the phonetic feature for reading aloud voice and aforementioned voice mould of target text
The phonetic feature of the standard pronunciation of target text under formula is consistent, then can be determined that speech unlocking success, release the operation of terminal
Locking；In addition, if user reads aloud the phonetic feature and aforementioned voice for reading aloud voice of target text in speech training processes
The phonetic feature of the standard pronunciation of target text under mode is consistent, it is possible to determine that speech unlocking success releases the operation of terminal
Locking.
Step S313: it provides and reads prompt information again.
Specifically, if user read aloud target text the phonetic feature for reading aloud voice and aforementioned voice mode under target
The phonetic feature of the corresponding standard pronunciation of text is not consistent, and can provide the information of the standard pronunciation of target text, for example, display
The phonetic symbol of the target text, or read aloud the standard pronunciation of the target text.
Referring to fig. 4, be terminal provided in an embodiment of the present invention first embodiment structural schematic diagram, it is as shown in Figure 4
Terminal 40 can include: input unit 401, selecting unit 403, recording unit 405 and processing unit 407, in which:
Input unit 401, can be used for receiving the unlock instruction of user's input, and unlock instruction is used to release the operation lock of terminal
It is fixed；
Selecting unit 403 can be used for from default dictionary extracting target text, and displaying target text；
Recording unit 405 can be used for opening voice recording function, and record user first reads aloud voice；
Processing unit 407 can be used for the phonetic feature standard pronunciation whether corresponding with target text for judging to read aloud voice
Phonetic feature be consistent, if so, release terminal operation locking；Prompt information is read again if it is not, then providing, and is returned and executed note
Employ the step of reading aloud voice of family.
Further, terminal 40 may also include that association's unit, if phonetic feature and target text for reading aloud voice
The phonetic feature of corresponding standard pronunciation is not consistent, then provides and read aloud the corresponding association's word of voice；The standard for associating word is read
The phonetic feature of sound is consistent with the phonetic feature for reading aloud voice.
Further, terminal 40 may also include that first control unit, for opening voice recording in recording unit 405
After function, record user reads aloud the number of target text；If the number that user reads aloud target text is more than preset times,
Release the operation locking of terminal.
Further, terminal 40 may also include that the second control unit, for opening voice recording in recording unit 405
After function, preset timer is opened, for recording the working time of recording function；If the working time of recording function is more than
Preset operating time then releases the operation locking of terminal.
Further, selecting unit 403 can be specifically used for: random extracts target text from default dictionary.
It should be noted that target text may include multiple words in default dictionary, i.e. target text can be sentence, section
It falls or article, in practical application, target text can also be single letter, here with no restriction.
It is the structural schematic diagram of the second embodiment of terminal provided in an embodiment of the present invention referring to Fig. 5, as shown in Figure 5
Terminal 40 is including: input unit 401, selecting unit 403, except recording unit 405 and processing unit 407, be may also include that
Taxon 409, in which:
Taxon 409, can be used for processing unit 407 judge read aloud voice phonetic feature whether with target text pair
After the phonetic feature for the standard pronunciation answered is consistent, if the phonetic feature for reading aloud voice standard pronunciation corresponding with target text
Phonetic feature be consistent, then target text is moved into the first sub- dictionary.
It should be noted that above-mentioned default dictionary may include the first sub- dictionary and the second sub- dictionary；Selecting unit 403 can be specific
For: from the second sub- dictionary extract target text.In the specific implementation, selecting unit 403 can be random from the second sub- dictionary
Middle extraction target text.
Further, terminal 40 may also include that association's unit, if phonetic feature and target text for reading aloud voice
The phonetic feature of corresponding standard pronunciation is not consistent, then provides and read aloud the corresponding association's word of voice；The standard for associating word is read
The phonetic feature of sound is consistent with the phonetic feature for reading aloud voice.
Further, terminal 40 may also include that first control unit, for opening voice recording in recording unit 405
After function, record user reads aloud the number of target text；If the number that user reads aloud target text is more than preset times,
Release the operation locking of terminal.
Further, terminal 40 may also include that the second control unit, for opening voice recording in recording unit 405
After function, preset timer is opened, for recording the working time of recording function；If the working time of recording function is more than
Preset operating time then releases the operation locking of terminal.
It should be noted that target text may include multiple words in default dictionary, i.e. target text can be sentence, section
It falls or article, in practical application, target text can also be single letter, here with no restriction.
It is the structural schematic diagram of the 3rd embodiment of terminal provided in an embodiment of the present invention referring to Fig. 6, it is as shown in FIG. 6
Terminal 40 is including: input unit 401, selecting unit 403, except recording unit 405 and processing unit 407, be may also include that
Setting unit 411, in which:
Setting unit 411 can be used for before the unlock instruction that input unit 401 receives user's input, preset language
Sound mode；Speech pattern is used to indicate the mode of the phonetic feature of the corresponding standard pronunciation of target text；
Further, processing unit 407 can be specifically used for: judgement read aloud voice phonetic feature whether under speech pattern
The phonetic feature of the corresponding standard pronunciation of target text be consistent.When judging that user reads aloud the language for reading aloud voice of target text
The phonetic feature of sound feature standard pronunciation corresponding with the target text under aforementioned voice mode is not consistent, and processing unit 407 can
To provide the information of the standard pronunciation of target text, for example, showing the phonetic symbol of the target text, or the target text is read aloud
Standard pronunciation.
It should be noted that target text may include multiple words in default dictionary, i.e. target text can be sentence, section
It falls or article, in practical application, target text can also be single letter, here with no restriction.
It is the structural schematic diagram of the fourth embodiment of terminal provided in an embodiment of the present invention referring to Fig. 7.Wherein, such as Fig. 7 institute
Show, terminal 100 may include: at least one processor 1001, such as CPU, at least one bus 1002, at least one network connects
Mouthful: network interface 1003, a phonographic recorder: phonographic recorder 1004, memory 1005, a display screen 1006 and user interface
1007.Wherein, bus 1002 is for realizing the communication connection between these components；Network interface optionally may include standard
Wireline interface, wireless interface (such as WI-FI interface)；Network interface 1003 may include the wired network interface or standard of standard
Radio network interface；Memory 1005 can be high speed RAM memory, be also possible to non-labile memory (non-
Volatile memory), for example, at least a magnetic disk storage, memory 1005 optionally can also be that at least one is located at
Storage device far from aforementioned processor 1001；Display screen 1006 may include Organic Electricity laser display screen (Organic
Light-Emitting Diode, OLED)；User interface 1007 may include touch screen (Touch Screen), optional user
Interface 1007 can also include standard wireline interface and wireless interface.As shown in fig. 7, as a kind of computer storage medium
It may include operating system, network communication module, Subscriber Interface Module SIM and speech unlocking program in memory 1005.
In terminal 100 shown in Fig. 7, phonographic recorder 1004 is used to record that user to read aloud target text reads aloud voice；Place
Reason device 1001 can be used for calling the speech unlocking program stored in memory 1005, and execute following operation:
The unlock instruction of user's input is received by user interface 1007, unlock instruction is used to release the operation lock of terminal
It is fixed；
Target text is extracted from default dictionary, and passes through 1006 displaying target text of display screen；
Voice recording function is opened, reads aloud voice using the record user of phonographic recorder 1004；
Judge that the phonetic feature for the phonetic feature standard pronunciation whether corresponding with target text for reading aloud voice is consistent, if
It is the operation locking for then releasing terminal；Prompt information is read again if it is not, can then provide by display screen 1006, and is returned and held
Row is described to record the step of reading aloud voice of the user.
Further, after processor 1001 executes the step of unlatching voice recording function, user can also be recorded
Read aloud the number of target text；If the number that user reads aloud target text is more than preset times, the operation lock of terminal is released
It is fixed.
Further, it after processor 1101 executes the step of unlatching voice recording function, can also open pre-
If timer, for recording the working time of the recording function；If the working time of recording function is more than default work
Between, then release the operation locking of terminal.
Further, above-mentioned default dictionary includes the first sub- dictionary and the second sub- dictionary；Processor 1101 executes described
It may particularly include from the step of extracting target text in default dictionary: extracting target text from the second sub- dictionary；It is specific real
In existing, processor 1101 executes the language of the phonetic feature standard pronunciation whether corresponding with target text for judging to read aloud voice
After the step of sound feature is consistent, if the phonetic feature of the phonetic feature for reading aloud voice standard pronunciation corresponding with target text
It is consistent, then target text can be moved to the first sub- dictionary.
Further, if the phonetic feature of the phonetic feature for reading aloud voice standard pronunciation corresponding with target text not
It is consistent, then processor 1101 can be provided by display screen 1006 and read aloud the corresponding association's word of voice；The standard for associating word is read
The phonetic feature of sound is consistent with the phonetic feature for reading aloud voice.
Further, before the unlock instruction for receiving user's input by user interface 1007, processor 1101 can
To preset speech pattern；The speech pattern is used to indicate the mould of the phonetic feature of the corresponding standard pronunciation of target text
Formula；In the specific implementation, processor 1101 executes the phonetic feature mark whether corresponding with target text for judging to read aloud voice
The step of phonetic feature of quasi- pronunciation is consistent may particularly include: processor 1101 judge read aloud voice phonetic feature whether with language
The phonetic feature of the corresponding standard pronunciation of the target text under sound mode is consistent.
Further, processor 1101, which executes described the step of extracting target text from default dictionary, specifically to wrap
Include: processor 1101 it is random extract target text from default dictionary.
Further, processor 1101, which executes described the step of extracting target text from default dictionary, specifically to wrap
Include: processor 1101 it is random extract target text from default dictionary.
Further, processor 1101 execute it is described provide read again prompt information the step of may particularly include: processor
1101 provide the information of the standard pronunciation of target text.
It should be noted that above-mentioned target text may include multiple words in default dictionary, i.e. target text can be sentence
Son, paragraph or article, in practical application, target text can also be single letter, here with no restriction；Processor 1001 is held
Capable step can be with reference to the specific implementation in above-mentioned Fig. 1 to Fig. 3 embodiment of the method, and which is not described herein again.
In conclusion implementing the embodiment of the present invention, it can receive the unlock instruction of user's input, extracted from default dictionary
Target text out opens voice recording function, records the voice of reading aloud of user, and judge to read aloud voice phonetic feature whether
The phonetic feature of standard pronunciation corresponding with target text is consistent, if so, releasing the operation locking of terminal；If it is not, then prompting
User reads again, and returns and execute using the step of reading aloud voice, it can be achieved that improving during speech unlocking for the record user
The pronunciation level at family.
The step of method of the embodiment of the present invention, sequentially can be adjusted according to actual needs, merges or delete.This hair
The module of the terminal of bright embodiment can be integrated according to actual needs, further division or deletion.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (9)
1. a kind of terminal characterized by comprising
Input unit, for receiving the unlock instruction of user's input, the unlock instruction is used to release the operation locking of terminal；
Selecting unit for extracting target text from default dictionary, and shows the target text；
Recording unit, for opening voice recording function, record the user first reads aloud voice；
Processing unit, for judging the phonetic feature standard pronunciation whether corresponding with the target text for reading aloud voice
Phonetic feature is consistent, if so, releasing the operation locking of the terminal；Prompt information is read again if it is not, then providing, and is returned
It executes and described records the step of reading aloud voice of the user；The stressed prompt information includes that the standard of the target text is read
The information of sound.
2. terminal as described in claim 1, which is characterized in that further include: first control unit, in the recording unit
After the step of executing the unlatching voice recording function, the number that the user reads aloud the target text is recorded；If institute
Stating user and reading aloud the number of the target text is more than preset times, then releases the operation locking of the terminal.
3. terminal as described in claim 1, which is characterized in that further include: the second control unit, in the recording unit
After the step of executing the unlatching voice recording function, preset timer is opened, for recording the work of the recording function
Time；If the working time of the recording function is more than preset operating time, the operation locking of the terminal is released.
4. terminal as described in claim 1, which is characterized in that the default dictionary includes the first sub- dictionary and the second sub- word
Library；The selecting unit is specifically used for: extracting the target text from the described second sub- dictionary；
The terminal further include: taxon, for executing the voice for reading aloud voice described in the judgement in the processing unit
After the step of phonetic feature of feature standard pronunciation whether corresponding with the target text is consistent, if described read aloud voice
The phonetic feature of phonetic feature standard pronunciation corresponding with the target text be consistent, then the target text is moved to described
First sub- dictionary.
5. terminal as described in claim 1, which is characterized in that further include: association's unit, if for the voice of reading aloud
The phonetic feature of phonetic feature standard pronunciation corresponding with the target text is not consistent, then it is corresponding to read aloud voice described in offer
Associate word；The phonetic feature of the standard pronunciation of association's word is consistent with the phonetic feature for reading aloud voice.
6. terminal as described in claim 1, which is characterized in that further include: setting unit, for being executed in the input unit
Before the step of unlock instruction for receiving user's input, speech pattern is preset；The speech pattern is used to indicate institute
State the mode of the phonetic feature of the corresponding standard pronunciation of target text；
The processing unit is specifically used for: read aloud described in judgement voice phonetic feature whether under the speech pattern described in
The phonetic feature of the corresponding standard pronunciation of target text is consistent.
7. terminal as described in claim 1, which is characterized in that the selecting unit is specifically used for: random presets from described
The target text is extracted in dictionary.
8. terminal as claimed in claim 4, which is characterized in that the selecting unit is specifically used for: random from described second
The target text is selected in sub- dictionary.
9. terminal as described in claim 1, which is characterized in that the target text includes multiple lists in the default dictionary
Word.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410714989.2A CN104598122B (en) | 2014-11-29 | 2014-11-29 | A kind of terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410714989.2A CN104598122B (en) | 2014-11-29 | 2014-11-29 | A kind of terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104598122A CN104598122A (en) | 2015-05-06 |
| CN104598122B true CN104598122B (en) | 2019-05-14 |
Family
ID=53123952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410714989.2A Active CN104598122B (en) | 2014-11-29 | 2014-11-29 | A kind of terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104598122B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104639742B (en) * | 2015-01-06 | 2018-04-10 | 广东小天才科技有限公司 | The spoken method and device of mobile terminal CAL |
| CN106022045A (en) * | 2016-05-23 | 2016-10-12 | 努比亚技术有限公司 | Information processing device and method |
| CN107463815A (en) * | 2016-06-06 | 2017-12-12 | 中兴通讯股份有限公司 | Method for authenticating and device |
| WO2018023254A1 (en) * | 2016-07-31 | 2018-02-08 | 杨洁 | Use feedback method and unlocking system for unlocking mobile phone by reading word |
| WO2018023255A1 (en) * | 2016-07-31 | 2018-02-08 | 杨洁 | Method for pushing information when reading vocabulary to unlock mobile phone and unlocking system |
| WO2018023256A1 (en) * | 2016-07-31 | 2018-02-08 | 杨洁 | Mobile phone unlocking method and unlocking system by reading word |
| CN106921655B (en) * | 2017-01-26 | 2021-01-29 | 华为技术有限公司 | Service authorization method and device |
| CN111008001A (en) * | 2019-12-25 | 2020-04-14 | 珠海市魅族科技有限公司 | Mobile terminal operation method and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1700199A (en) * | 2004-05-20 | 2005-11-23 | 英保达股份有限公司 | Language learning system and method thereof |
| CN101079189A (en) * | 2007-03-20 | 2007-11-28 | 无敌科技(西安)有限公司 | Chinese pronunciation correction listening-writing study method and system |
| CN101393694A (en) * | 2008-10-21 | 2009-03-25 | 无敌科技(西安)有限公司 | Chinese character pronunciation studying device with pronunciation correcting function of Chinese characters, and method therefor |
| CN102799408A (en) * | 2012-07-09 | 2012-11-28 | 上海斐讯数据通信技术有限公司 | Mobile terminal with voice-operated unlocking function and voice-operated unlocking method for mobile terminals |
| CN103310666A (en) * | 2013-05-24 | 2013-09-18 | 深圳市九洲电器有限公司 | Language learning device |
| CN103531200A (en) * | 2013-10-29 | 2014-01-22 | 宇龙计算机通信科技(深圳)有限公司 | Voice unlocking method and terminal |
| CN103729584A (en) * | 2012-10-16 | 2014-04-16 | 北京千橡网景科技发展有限公司 | Method and device used for unlocking screen |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310790A (en) * | 2012-03-08 | 2013-09-18 | 富泰华工业（深圳）有限公司 | Electronic device and voice identification method |
-
2014
- 2014-11-29 CN CN201410714989.2A patent/CN104598122B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1700199A (en) * | 2004-05-20 | 2005-11-23 | 英保达股份有限公司 | Language learning system and method thereof |
| CN101079189A (en) * | 2007-03-20 | 2007-11-28 | 无敌科技(西安)有限公司 | Chinese pronunciation correction listening-writing study method and system |
| CN101393694A (en) * | 2008-10-21 | 2009-03-25 | 无敌科技(西安)有限公司 | Chinese character pronunciation studying device with pronunciation correcting function of Chinese characters, and method therefor |
| CN102799408A (en) * | 2012-07-09 | 2012-11-28 | 上海斐讯数据通信技术有限公司 | Mobile terminal with voice-operated unlocking function and voice-operated unlocking method for mobile terminals |
| CN103729584A (en) * | 2012-10-16 | 2014-04-16 | 北京千橡网景科技发展有限公司 | Method and device used for unlocking screen |
| CN103310666A (en) * | 2013-05-24 | 2013-09-18 | 深圳市九洲电器有限公司 | Language learning device |
| CN103531200A (en) * | 2013-10-29 | 2014-01-22 | 宇龙计算机通信科技(深圳)有限公司 | Voice unlocking method and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104598122A (en) | 2015-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104598122B (en) | A kind of terminal | |
| CN102955908B (en) | Create the method and apparatus that rhythm password and carrying out according to rhythm password is verified | |
| JP5172682B2 (en) | Generating words and names using N-grams of phonemes | |
| CN101523373B (en) | Character position-based password recovery | |
| CN105185379A (en) | Voiceprint authentication method and voiceprint authentication device | |
| CN106886692A (en) | Application program using method and device and electronic equipment | |
| CN104598791A (en) | Voice unlocking method | |
| CN107622054A (en) | The error correction method and device of text data | |
| US9449163B2 (en) | Electronic device and method for logging in application program of the electronic device | |
| CN105929974B (en) | A kind of Password Input management method and mobile terminal | |
| CN104142796B (en) | The unlocking method and terminal of a kind of terminal | |
| CN101441869A (en) | Method and terminal for speech recognition of terminal user identification | |
| CN107644172A (en) | The guard method of content displaying and device | |
| CN108604268B (en) | A kind of voice unlocking method and terminal of terminal | |
| CN106503523A (en) | Method and mobile terminal that a kind of mobile terminal is logged in | |
| CN107025393A (en) | A kind of method and device of resource transfer | |
| CN110010121A (en) | Verify method, apparatus, computer equipment and the storage medium of the art that should answer | |
| CN109857505A (en) | Execution method, apparatus, terminal and the storage medium of operation | |
| CN108038361A (en) | Dual system recognition methods, mobile terminal and storage medium based on vocal print | |
| CN107068149A (en) | unlocking method and device | |
| CN103543905B (en) | The method and device at the interface of Voice command terminal | |
| CN104699745B (en) | Instantaneous speech power and speech output method | |
| CN107463814A (en) | A kind of mobile terminal verification method, system and mobile terminal | |
| WO2017024835A1 (en) | Voice recognition method and device | |
| JP2007310819A (en) | Password generation method with improved resistance to password analysis, and authentication apparatus using this password |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210224 Address after: 518057 Desai Science and Technology Building, 9789 Shennan Avenue, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province, 17th Floor (15th Floor of Natural Floor) 1702-1703 Patentee after: Shenzhen Microphone Holdings Co.,Ltd. Address before: 518040 21 floor, east block, Times Technology Building, 7028 Shennan Road, Futian District, Shenzhen, Guangdong. Patentee before: DONGGUAN GOLDEX COMMUNICATION TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |