CN105933765A - Voice unlocking method and device - Google Patents
Voice unlocking method and device Download PDFInfo
- Publication number
- CN105933765A CN105933765A CN201610245100.XA CN201610245100A CN105933765A CN 105933765 A CN105933765 A CN 105933765A CN 201610245100 A CN201610245100 A CN 201610245100A CN 105933765 A CN105933765 A CN 105933765A
- Authority
- CN
- China
- Prior art keywords
- acoustic features
- user
- features information
- user type
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000000284 extract Substances 0.000 claims description 29
- 230000000875 corresponding effect Effects 0.000 description 37
- 230000008859 change Effects 0.000 description 11
- 210000003128 head Anatomy 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 230000001755 vocal effect Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 210000003928 nasal cavity Anatomy 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 210000000515 tooth Anatomy 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/441—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card
- H04N21/4415—Acquiring end-user identification, e.g. using personal code sent by the remote control or by inserting a card using biometric characteristics of the user, e.g. by voice recognition or fingerprint scanning
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4753—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for user identification, e.g. by entering a PIN or password
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention provides a voice unlocking method and device. The voice unlocking method comprises a step of acquiring the voice instruction of a user through a television client, extracting the acoustic characteristic information of the voice instruction, and determining the user type of the user according to the acoustic characteristic information, a step of judging whether the user type coincides with a preset user type, a step of identifying the voice instruction if the user type coincides with the preset user type, and judging whether the voice instruction is corresponding to a preset unlocking instruction according to the corresponding relation between the voice instruction and the preset unlocking instruction, and a step of executing the unlocking operation corresponding to the preset unlocking instruction according to the preset unlocking instruction if the judgment result is that the voice instruction is corresponding to a preset unlocking instruction. Correspondingly, the embodiment of the invention provides the voice unlocking device, according to the technical scheme provided by the embodiment of the invention, while the voice instruction is obtained, the user type is judged, the unlocking is performed when the user type coincides with the preset user type, and while the unlocking operation is facilitated, the execution of an operation by a user which does not meet a requirement is avoided.
Description
Technical field
The present embodiments relate to information interaction process technical field, particularly relate to a kind of speech unlocking side
Method and device.
Background technology
The control mode of traditional tv mainly based on remote controller, infrared connected mode make remote controller and
TV produces and connects, and produces order, thus realize user's control for TV in the way of physical button
System, and along with the development of science and technology, traditional tv the most progressively develops to internet television direction, no matter from
, all there is huge change in the content of TV or the mode of operation of TV, utilizes the biography of remote controller
System control mode seems that some bothers.
At present, the content in TV is more and more abundanter, the most just contains and is not suitable for the interior of low age crowd
Hold, relate to and watch the too much content of multimedia being not suitable for low age crowd in order to avoid child, generally
Way carry out rights management, by arranging the side of password when being and television startup and function are switched
Formula controls user's entering part application permission, and user needs first to carry out the setting of password, and reserved hands
Plane No. code is given for change for the loss of password, when booting up or enter the application of locking, needs
Adjust keyboard, and completed the input of password by directionkeys mobile keyboard cursor up and down and be accomplished
Password unlocks, and operating process is the most loaded down with trivial details, also needs to when forgetting Password be given for change by transmission note
Password.
Therefore, based on technological deficiency of the prior art, a kind of simple and fast easily and can pass through
It is the most urgently to be resolved hurrily that speech recognition technology boots up or enter the interactive controlling scheme of locking application
Technical problem.
Summary of the invention
The embodiment of the present invention provides a kind of voice unlocking method and device, right in order to solve in prior art
When television startup and function carry out rights management when switching, booting up or entering locking
During application, adjust the loaded down with trivial details of keyboard manual manipulation, also evade the needs that forget Password by sending note
Give the diverse and complicated of password for change.
In view of this, the embodiment of the present invention provides a kind of voice unlocking method, including:
Obtained the phonetic order of user by Television clients, extract the acoustic features letter of described phonetic order
Breath, determines the user type of user according to described acoustic features information;
Judge that described user type is the most consistent with pre-set user type;
If described user type is consistent with described pre-set user type, then identify described phonetic order, root
According to described phonetic order and described default unlock instruction between corresponding relation, it is judged that described phonetic order with
Preset unblock instruction the most corresponding;
If the determination result is YES, then according to described default unlock instruction perform with described default unlock instruction to
Corresponding solution latching operation.
Correspondingly the embodiment of the present invention additionally provides a kind of speech unlocking device, including: Television clients,
Described Television clients includes:
Acquisition module, for obtaining the phonetic order of user, extracts the acoustic features letter of described phonetic order
Breath, determines the user type of user according to described acoustic features information;
Judge module, is used for judging that described user type is the most consistent with pre-set user type;
Identification module, if consistent with described pre-set user type for described user type, then identifies institute
State phonetic order, according to described phonetic order and the described default corresponding relation unlocked between instruction, it is judged that
Described phonetic order is the most corresponding with presetting unblock instruction;
Perform module, for if the determination result is YES, then instruct execution with described according to described default unblock
Preset and unlock instruction to corresponding solution latching operation.
The method and device of the speech unlocking that the embodiment of the present invention provides, the phonetic order obtaining user extracts
Acoustic features information in phonetic order, determines user type according to acoustic features information, in user type
In the case of consistent with pre-set user type, identify the phonetic order of user, according to phonetic order with pre-
If the corresponding relation unlocked between instruction, perform to unlock, with presetting, the solution latching operation that instruction is corresponding, solve
When prior art carries out rights management for television startup and function when switching, booting up or
When person enters the application of locking, adjust the loaded down with trivial details of keyboard manual manipulation, also evaded the needs that forget Password and led to
Cross transmission note to give the diverse and complicated of password for change, the technical scheme provided according to embodiments of the present invention, facilitate
User can be prevented effectively from undesirable user while solving latching operation and perform inappropriate operation,
When being unlocked operation, it is ensured that user simple to operation fast, improve the experience of user.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to reality
Execute the required accompanying drawing used in example or description of the prior art to be briefly described, it should be apparent that under,
Accompanying drawing during face describes is some embodiments of the present invention, for those of ordinary skill in the art,
On the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart of the method for speech unlocking in the embodiment of the present invention;
Fig. 2 is the structural representation of the device of speech unlocking in the embodiment of the present invention;
Fig. 3 is the structural representation of the device of a kind of preferably speech unlocking in the embodiment of the present invention;
Fig. 4 is the schematic diagram of the application scenarios of the method for speech unlocking in the embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under not making creative work premise
The every other embodiment obtained, broadly falls into the scope of protection of the invention.
The very trouble that tradition is aobvious in the way of remote controller operation TV, in interactive mode, voice is grasped
The appearance of control becomes the further possibility of TV manipulation especially, and whether (TV is in pass in cold start-up
The voice start-up mode of machine state), or general TV manipulation, terminal can be realized by voice
Control in all directions.
At present, the content in TV is more and more abundanter, the most just contains and is not suitable for the interior of low age crowd
Hold, relate to and watch the too much content of multimedia being not suitable for low age crowd in order to avoid child, generally
Way carry out rights management, by arranging the side of password when being and television startup and function are switched
Formula controls user's entering part application permission, and user needs first to carry out the setting of password, and reserved hands
Plane No. code is given for change for the loss of password, when booting up or enter the application of locking, needs
Adjust keyboard, and completed the input of password by directionkeys mobile keyboard cursor up and down and be accomplished
Password unlocks, and operating process is the most loaded down with trivial details, also needs to when forgetting Password be given for change by transmission note
Password.
If able to booted up or enter the solution latching operation of locking application by speech recognition technology, just
Can eliminate and adjust the loaded down with trivial details of keyboard manual manipulation, also evade the needs that forget Password short by sending
The diverse and complicated of password given for change by letter.
In view of this, the method and device of a kind of speech unlocking is embodiments provided with in solution
The problem stated, describes the embodiment of the embodiment of the present invention in detail below in conjunction with drawings and Examples,
Thereby to the embodiment of the present invention, how application technology means solve technical problem and reach technology effect
The process that realizes can fully understand and implement according to this.
Embodiment one
Fig. 1 is the flow chart of the method for speech unlocking in the embodiment of the present invention, and in conjunction with Fig. 1, the present invention is real
Execute example and a kind of voice unlocking method is provided, including:
Step S101: obtained the phonetic order of user by Television clients, extracts the sound of phonetic order
Learn characteristic information, determine the user type of user according to acoustic features information;
The generation of human speech is a complicated physiology physics between Body Languages maincenter and phonatory organ
Process, the phonatory organ that people uses when speech--tongue, tooth, larynx, lung, nasal cavity in size and
Everyone widely different of form aspect, so the vocal print collection of illustrative plates of any two people is the most variant, due to
Everyone phonatory organ are not quite similar, and therefore, according to the diversity of vocal print in human speech, carry
Take acoustic features information therein, it is possible to distinguish the sound of different people or judge whether it is same people
Sound, the sound distinguishing different people can also distinguish between the age bracket of people, sex etc. feature, this
Inventive embodiments is based on above-mentioned principle, user uses Television clients when, passes through TV
After client obtains the phonetic order of user, through extracting the acoustic features information in phonetic order, really
Determining the user type of user, user type includes but not limited to adult and child, also includes man, female
People, old man etc., after determining the type of user, perform step 102, is extracting phonetic order
During acoustic features information, can extract according to cloud server, and the vocal print feature that will extract
Information is back to Television clients.
Step S102: judge that user type is the most consistent with pre-set user type;
After the user type determining user, it is judged that user type whether with default user type phase
Unanimously, the user type such as preset is adult, when the user type determined by step S101 is for becoming
During people, illustrate that user type is consistent with pre-set user type, then perform step S103, if by step
When the user type that rapid S101 determines is child, user type and pre-set user Type-Inconsistencies are described,
Then phonetic order is not responded, or carry out miscue.
Step S103: if user type is consistent with pre-set user type, then identify phonetic order, root
According to phonetic order and the default corresponding relation unlocked between instruction, it is judged that phonetic order refers to default unblock
Make the most corresponding;
If user type is consistent with pre-set user type, illustrate that user is the user that can carry out operating,
Then being identified the phonetic order of user, the phonetic order that will identify that is carried out with presetting unblock instruction
Contrast, according to phonetic order and the default corresponding relation unlocked between instruction, when phonetic order is with default
Unlock instruction the most corresponding, then it is assumed that the phonetic order of user is correct, perform step S104, if language
Sound instruction is the most corresponding to presetting unblock instruction, then it is assumed that user speech instruction is incorrect, does not responds,
Or prompting error message, presetting and unlocking instruction is that user pre-sets, and user refers to arranging unblock
Making in interface, user inputs arbitrary unblock and instructs, such as: " I is the head of a family ", " I is adult ",
" unlocking " etc., instruct the unblock of input to carry out preserving generating and preset unblock instruction, different should
With arranging similar and different unblock instruction, such as user is by start application, film applications, trip
Play application etc. is provided with unblock instruction, and the unblock instruction that start application is arranged is " I is the head of a family ", electricity
The unblock instruction of shadow application is " I is adult ", and " I is adult " of game application, when user thinks
Start shooting and apply or enter into film applications, during game application, need to be unlocked operation, input
Step S104 can be performed with the default phonetic order unlocking instruction consistent.
Step S104: if the determination result is YES, then perform to refer to default unblock according to default unblock instruction
Make to corresponding solution latching operation.
When the phonetic order of user's input is the most corresponding with presetting unblock instruction, then unlock instruction according to default
Perform to solve latching operation, and then perform power-on operation or enter in TV applications, for according to presetting solution
Lock instruction performs to solve the latching operation embodiment of the present invention preferably, performs according to default unblock instruction and presets solution
Lock instruction, to corresponding solution latching operation, farther includes:
Time at Television clients with off-mode, then perform start solution latching operation according to default unblock instruction,
So that Television clients is carried out cold start-up;Or
Time at Television clients with open state, then perform application solution latching operation according to default unblock instruction,
By being unlocked with the default application unlocking instruction corresponding, to enter application.
Concrete example illustrates, example 1: user is when using television set, and television set is in off-mode,
But television set is connected to power supply, when user input voice instructs " I is the head of a family ", and television set obtains
After the phonetic order of " I is the head of a family ", extract the acoustic features information in user speech instruction,
Determine the user type of user, when the user type determined and the user type preset " are grown up " mutually one
During cause, then " I is the head of a family " phonetic order is contrasted with presetting unblock instruction, refer to according to voice
Order and the corresponding relation preset between unblock instruction, it is judged that " I is the head of a family " unlocks instruction phase with presetting
Unanimously, then television set is unlocked operation, boots up startup, completes the cold start-up of television set.
Example 2: user use television set see a film application time, film applications is in the lock state,
Eject screen locking page, when user input voice instructs " I is adult ", and television set gets that " I is big
People " phonetic order after, extract user speech instruction in acoustic features information, determine user's
User type, when the user type determined " is grown up " consistent with the user type preset, then will
" I is adult " phonetic order contrasts with presetting unblock instruction, solves with presetting according to phonetic order
Corresponding relation between lock instruction, it is judged that " I is adult " is consistent with presetting unblock instruction, then electricity
It is unlocked operation depending on machine, enters into film applications.
The method of the speech unlocking that the embodiment of the present invention provides, the phonetic order extraction voice obtaining user refers to
Acoustic features information in order, determines user type according to acoustic features information, in user type with default
In the case of user type is consistent, identify the phonetic order of user, unlock with presetting according to phonetic order
Corresponding relation between instruction, performs to unlock, with presetting, the solution latching operation that instruction is corresponding, solves existing
When technology carries out rights management for television startup and function when switching, booting up or entering
During the application locked, adjust the loaded down with trivial details of keyboard manual manipulation, also evade the needs that forget Password by sending
Note gives the diverse and complicated of password for change, the technical scheme provided according to embodiments of the present invention, facilitates user and solves
Undesirable user can be prevented effectively from while latching operation and perform inappropriate operation, solve
During latching operation, it is ensured that user simple to operation fast, improve the experience of user.
Below the embodiment of the present invention is described in detail, it should be noted that in the embodiment of the present invention and lifted
Example be only intended to explain the embodiment of the present invention progressive, be not intended as the improper of the embodiment of the present invention
Limiting, example is a part of example in the embodiment of the present invention, is not whole examples, and the present invention is real
Execute the technical field that example applied and include but not limited to intelligent terminal field, such as TV, mobile phone etc., traffic
Field of tool, such as automotive field etc., and other have the technical field of speech identifying function.
For step S101, the embodiment of the present invention is when determining user type, it is preferable that according to sound
Learn characteristic information and determine the user type of user, farther include:
Extract the acoustic features information of phonetic order, and special with the acoustics being pre-stored in acoustic features information bank
Reference breath alignment similarity;
Obtain similarity more than or equal to the acoustic features information in the acoustic features information bank of similarity threshold;
The user type of user is determined according to the acoustic features information in the acoustic features information bank obtained.
After obtaining user speech instruction, extract the acoustic features information in phonetic order, and and acoustic features
Acoustic features in information bank is compared similarity, by similarity more than or equal to similarity threshold
Acoustic features information in acoustic features information bank extracts, according in the acoustic features information bank obtained
Acoustic features information determine the user type of user.
The key condition of the user type being determined user is the acoustic features information in phonetic order and sound
Learn acoustic features information similarity in characteristic information storehouse more than or equal to similarity threshold, carry out similar
Needing to pre-build acoustic features information bank before degree comparison, the embodiment of the present invention preferably, and is pre-stored in
Acoustic features information alignment similarity in acoustic features information bank, the most also includes: set up acoustic features
Information bank, including: gather at least two voice messaging, extract the acoustics of each voice messaging collected
Characteristic information, wherein, voice messaging includes voice messaging and the voice messaging of child of adult;
According to default grouping strategy, the acoustic features information of the voice messaging collected is divided into adult group and
Child's group, and be saved in acoustic features information bank.
When setting up acoustic features information bank, need to gather the voice messaging of user, gather at least two and use
The voice messaging at family, to include voice messaging and the voice messaging of child of adult, will adopt in voice messaging
Collect to user speech information in acoustic features extract, in the user speech information that will extract
Acoustic features information be grouped according to default grouping strategy, default grouping strategy is that user sets in advance
Put, such as, the acoustic features information that the voice messaging of child extracts is divided into child's group, by adult's
The acoustic features information that voice messaging extracts is divided into adult group, it is also possible to extracted by the voice messaging of adult
To acoustic features information be divided into man's group, woman's group etc., the language that will collect according to the difference of sex
After the acoustic features information of message breath is divided into group not according to default grouping strategy, preserve to acoustic features information
In storehouse, in order to follow-up and in phonetic order acoustic features information carries out similarity comparison, needs explanation
It is that the user speech information gathered when setting up acoustic features information bank refers to the voice messaging that user inputs,
Purpose is the acoustic features information for extracting user, and phonetic order includes but not limited to concrete instruction, example
As I wants film, I to watch animated films, and also includes other non-instruction voice, such as weather that user says
The best, mood is pretty good.
After establishing acoustic features information bank, it is possible to determine the type of user, excellent in the embodiment of the present invention
Selection of land, determines the user type of user according to the acoustic features information in the acoustic features information bank obtained,
Including:
If the acoustic features information in the acoustic features information bank obtained is included in adult group, then user class
Type is adult;
If the acoustic features information in the acoustic features information bank obtained is included in child's group, then user class
Type is child.
After obtaining user speech instruction during concrete application, extract the acoustic features information in phonetic order, and
Compare similarity with the acoustic features in acoustic features information bank, by similarity more than or equal to phase
Extract like the acoustic features information in the acoustic features information bank of degree threshold value, and judge to extract
In which packet that acoustic features information in acoustic features information bank is included in acoustic features information bank,
If being included in adult group, then user type is adult, if being included in child's group, then user type is
Child, by that analogy, which the acoustic features information in the acoustic features information bank extracted is included in
In individual packet, then user type is just belonging to any type.
By above-mentioned method, can perform to solve latching operation accordingly by the phonetic order of user, but
The sound that may cause user for various reasons did not corresponded with the actual age, and such as actual age is
Virgin still sound is but as adult, and actual age as child, also has one situation to be likely to lead for adult's sound
Cause maloperation, it is simply that the sound of people can be changed now with a lot of softwares, such as by a child's
After sound typing, through processing the sound becoming adult, or the sound of man is become woman's
Sound, all situations described above, corresponding solution latching operation may be performed likely only according to user speech
Occur maloperation situation, it is therefore necessary to increase some auxiliary measures, such as recognition of face or
Subscriber authentication.
For step S103, in the embodiment of the present invention preferably, if user type and pre-set user class
Type is consistent, also includes:
User is carried out recognition of face, obtains the face characteristic information of user, according to the face characteristic of user
Information determines the user type of user;
If user type is consistent with pre-set user type, then identify phonetic order.
After the user type determining user according to acoustic features information is consistent with pre-set user type, right
User carries out recognition of face operation, is determined the user type of user by the face characteristic information obtaining user,
After the user type determining user according to acoustic features information is consistent with pre-set user type, pass through people
The user type that face identification also determines user is consistent with pre-set user type, then refer to the voice of user
Order is identified.
For example, pre-set user type is adult, as the user being determined user by acoustic features information
When type is for adult, then user is carried out recognition of face, determines that when recognition of face user type is adult,
Then carry out the identification of user speech instruction, during to user's recognition of face, front-facing camera can be used user
Facial information identification, know and can be Real time identification otherwise or know according to preset time period
Not, in order to avoid child to be unlocked operation by voice changer.
When using the terminals such as television set user, can be used in conjunction with several individuals, but have some application to use
When family is not intended to share with other people, then can need when being unlocked operation to carry out authentication, for
For step S103, if user type is consistent with pre-set user type, also include:
Subscriber authentication is carried out according to acoustic features information;
After subscriber authentication is passed through, then identify phonetic order.
After the user type determining user according to acoustic features information is consistent with pre-set user type, also
Need user is carried out authentication, in order to judge that whether the user sending phonetic order is through authorizing
User, the only user through authorizing just can carry out the solution latching operation being correlated with,
When carrying out authentication, in the embodiment of the present invention preferably, use according to acoustic features information
Family authentication, farther includes:
Acoustic features information by acoustic features information with the preset authorization being pre-stored in acoustic features information bank
Alignment similarity, if similarity is more than or equal to similarity threshold, then subscriber authentication is passed through.
Gathering the phonetic order of user, the acoustic features information in the user speech information that will collect is carried out
Extracting, the acoustic features information in the user speech information that will extract is set to the acoustic features authorized
Information also preserves to acoustic features information bank, in order to follow-up carry out authentication.
Embodiment two
Fig. 2 is the structural representation of the device of speech unlocking in the embodiment of the present invention, as shown in Figure 2:
Correspondingly the embodiment of the present invention additionally provides a kind of speech unlocking device, including: Television clients (figure
Not shown in), Television clients includes:
Acquisition module 1, for obtaining the phonetic order of user, extracts the acoustic features information of phonetic order,
The user type of user is determined according to acoustic features information;
Judge module 2, is used for judging that user type is the most consistent with pre-set user type;
Judge module 2 couples with acquisition module 1 phase, when acquisition module 1 determines the user type of user
After, it is judged that user type is contrasted by module 2 with pre-set user type, it is judged that both are the most consistent,
Will determine that result sends to identification module 3.
Identification module 3, if consistent with pre-set user type for user type, then identifies phonetic order,
According to phonetic order and the default corresponding relation unlocked between instruction, it is judged that phonetic order refers to default unblock
Make the most corresponding;
Identification module 3 couples with judge module 2 phase, uses with presetting when judge module 2 judges user type
After family type is consistent, identification module 3 identifies the phonetic order of user, solves with presetting according to phonetic order
Corresponding relation between lock instruction, it is judged that phonetic order is the most corresponding with presetting unblock instruction, will determine that
Result sends to performing module 4.
Perform module 4, for if the determination result is YES, then perform and default solution according to default unblock instruction
Lock instruction is to corresponding solution latching operation.
Perform module 4 to couple with identification module 3 phase, perform module 4 and receive the judgement knot of identification module 3
Really, if the determination result is YES, then unlock instruction execution according to default and preset unblock instruction to corresponding solution
Latching operation, such as default unblock instructs then execution start unblock corresponding with start unblock, and default unblock refers to
Make with to open film applications corresponding, then film applications is unlocked, opens film applications.
The device of the speech unlocking that the embodiment of the present invention provides, obtains the voice of user by acquisition module 1
The acoustic features information in phonetic order is extracted in instruction, determines user type according to acoustic features information, logical
Cross judge module 2 user type the most consistent with pre-set user type, judging user type and presetting
In the case of user type is consistent, identification module 3 identifies the phonetic order of user, according to phonetic order
And the corresponding relation between default unblock instruction, performs module 4 and performs corresponding with presetting unblock instruction
Solve latching operation, solve when carrying out rights management when prior art switches for television startup and function,
When booting up or enter the application of locking, adjust the loaded down with trivial details of keyboard manual manipulation, also evaded and having forgotten
Note password needs to give the diverse and complicated of password for change by transmission note, the technology provided according to embodiments of the present invention
Scheme, facilitate can be prevented effectively from while user solves latching operation undesirable user perform the most proper
When operation, when being unlocked operation, it is ensured that user simple to operation fast, improve use
The experience at family.
Preferably, acquisition module 1, it is further used for:
Extract the acoustic features information of phonetic order, and special with the acoustics being pre-stored in acoustic features information bank
Reference breath alignment similarity;
Obtain similarity more than or equal to the acoustic features information in the acoustic features information bank of similarity threshold;
The user type of user is determined according to the acoustic features information in the acoustic features information bank obtained.
Fig. 3 is the structural representation of the device of a kind of preferably speech unlocking in the embodiment of the present invention, such as figure
Shown in 3:
Preferably, also include: set up module 5, be used for setting up acoustic features information bank, including: gather
At least two voice messaging, extracts the acoustic features information of each voice messaging collected, wherein, language
Message breath includes voice messaging and the voice messaging of child of adult;
According to default grouping strategy, the acoustic features information of the voice messaging collected is divided into adult group and
Child's group, and be saved in acoustic features information bank.
Set up module 5 to couple with acquisition module 1 phase, be used for setting up acoustic features information bank, in order to be used for
Vocal print characteristic information in being instructed by user speech is relative with the vocal print characteristic information in acoustic features information bank
Ratio, determines the identity type of user.
Preferably, acquisition module 1, it is additionally operable to:
If the acoustic features information in the acoustic features information bank obtained is included in adult group, then user class
Type is adult;
If the acoustic features information in the acoustic features information bank obtained is included in child's group, then user class
Type is child.
Preferably, identification module 3, it is additionally operable to:
After the user type determining user according to acoustic features information is consistent with pre-set user type, right
User carries out recognition of face, obtains the face characteristic information of user, and the face characteristic information according to user is true
Determine the user type of user;
If user type is consistent with pre-set user type, then identify phonetic order.
Furthermore it is preferred that perform module 4, it is further used for:
Time at Television clients with off-mode, then perform start solution latching operation according to default unblock instruction,
So that Television clients is carried out cold start-up;Or
Time at Television clients with open state, then perform application solution latching operation according to default unblock instruction,
By being unlocked with the default application unlocking instruction corresponding, to enter application.
The method that Fig. 2-3 shown device can perform embodiment illustrated in fig. 1, the method for the embodiment of the present invention
Corresponding with device characteristic, can be cross-referenced, repeat the most one by one.
Concrete application scenarios:
Below by application scenarios describe the more intuitive understanding embodiment of the present invention technical scheme, with
Lower scene is intended to intuitively illustrate the technical scheme of the embodiment of the present invention, is not intended that the embodiment of the present invention is not
Work as restriction.
Scene one
Fig. 4 is the schematic diagram of the application scenarios of the method for speech unlocking in the embodiment of the present invention, such as Fig. 4 institute
Show:
As a example by using television set, it is adult that user pre-sets user type, and user passes through TV house keeper
The head of a family under menu has locked application and start.
When user enters into the application of locking or boots up, interface can be ejected needs key feeding cipher
Screen locking page, user sends phonetic order " I is the head of a family ", according to " I is the head of a family " vocal print characteristic information,
Judge whether the type of user, such as vocal print feature are child, be not the most unlocked and rest on lock
Screen page, if it is not, be then unlocked operation.
Scene two
Still with scene one as background, when judging the type of user as adult, open the preposition shooting of TV
Head, carries out recognition of face to user, when determining that after recognition of face user type is adult, then carries out
Solve latching operation, if the result of recognition of face is child, then rest on screen locking page.
Scene three
Still with scene one as background, when judging the type of user as adult, in the phonetic order extracted
The acoustic features information comparison of vocal print characteristic information and the preset authorization being pre-stored in acoustic features information bank
Similarity, if similarity is more than or equal to similarity threshold, then subscriber authentication is passed through, then solve
Latching operation.
In sum, the technical scheme that the embodiment of the present invention provides, the phonetic order obtaining user extracts language
Sound instruction in acoustic features information, determine user type according to acoustic features information, user type with
In the case of pre-set user type is consistent, identify the phonetic order of user, according to phonetic order with default
Unlock the corresponding relation between instruction, perform to unlock, with presetting, the solution latching operation that instruction is corresponding, solve
When carrying out rights management when prior art switches for television startup and function, booting up or
When entering the application of locking, adjust the loaded down with trivial details of keyboard manual manipulation, also evaded the needs that forget Password and passed through
Send note and give the diverse and complicated of password for change, the technical scheme provided according to embodiments of the present invention, facilitate use
Family can be prevented effectively from undesirable user while solving latching operation and perform inappropriate operation, is entering
Row solve latching operation time, it is ensured that user simple to operation fast, improve the experience of user.
Device embodiment described above is only schematically, wherein said illustrates as separating component
Unit can be or may not be physically separate, the parts shown as unit can be or
Person may not be physical location, i.e. may be located at a place, or can also be distributed to multiple network
On unit.Some or all of module therein can be selected according to the actual needs to realize the present embodiment
The purpose of scheme.Those of ordinary skill in the art are not in the case of paying performing creative labour, the most permissible
Understand and implement.
Through the above description of the embodiments, those skilled in the art is it can be understood that arrive each reality
The mode of executing can add the mode of required general hardware platform by software and realize, naturally it is also possible to by firmly
Part.Based on such understanding, the portion that prior art is contributed by technique scheme the most in other words
Dividing and can embody with the form of software product, this computer software product can be stored in computer can
Read in storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that one
Computer installation (can be personal computer, server, or network equipment etc.) performs each to be implemented
The method described in some part of example or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, rather than to it
Limit;Although the present invention being described in detail with reference to previous embodiment, the ordinary skill of this area
Personnel it is understood that the technical scheme described in foregoing embodiments still can be modified by it, or
Person carries out equivalent to wherein portion of techniques feature;And these amendments or replacement, do not make corresponding skill
The essence of art scheme departs from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (12)
1. a voice unlocking method, it is characterised in that including:
Obtained the phonetic order of user by Television clients, extract the acoustic features letter of described phonetic order
Breath, determines the user type of user according to described acoustic features information;
Judge that described user type is the most consistent with pre-set user type;
If described user type is consistent with described pre-set user type, then identify described phonetic order, root
According to described phonetic order and described default unlock instruction between corresponding relation, it is judged that described phonetic order with
Preset unblock instruction the most corresponding;
If the determination result is YES, then according to described default unlock instruction perform with described default unlock instruction to
Corresponding solution latching operation.
Method the most according to claim 1, it is characterised in that true according to described acoustic features information
Determine the user type of user, farther include:
Extract the acoustic features information of described phonetic order, and with the sound being pre-stored in acoustic features information bank
Learn characteristic information alignment similarity;
Obtain described similarity more than or equal to the acoustics in the described acoustic features information bank of similarity threshold
Characteristic information;
Determine described in described user according to the acoustic features information in the described acoustic features information bank obtained
User type.
Method the most according to claim 2, it is characterised in that be pre-stored in acoustic features information bank
In acoustic features information alignment similarity, the most also include: set up described acoustic features information bank, bag
Include: gather at least two voice messaging, extract the acoustic features letter of each described voice messaging collected
Breath, wherein, described voice messaging includes voice messaging and the voice messaging of child of adult;
According to default grouping strategy, the acoustic features information of the described voice messaging collected is divided into adult
Group and child's group, and be saved in described acoustic features information bank.
Method the most according to claim 3, it is characterised in that according to the described acoustic features obtained
Acoustic features information in information bank determines the described user type of described user, including:
If the acoustic features information in the described acoustic features information bank obtained is included in described adult group,
The most described user type is adult;
If the acoustic features information in the described acoustic features information bank obtained is included in described child's group,
The most described user type is child.
Method the most according to claim 1, it is characterised in that if described user type is pre-with described
If user type is consistent, also include:
Described user is carried out recognition of face, obtains the face characteristic information of described user, according to described use
The face characteristic information at family determines the described user type of described user;
If described user type is consistent with described pre-set user type, then identify described phonetic order.
6. according to the arbitrary described method of claim 1-5, it is characterised in that according to described default unblock
Instruction performs to instruct to corresponding solution latching operation with described default unblock, farther includes:
Time at described Television clients with off-mode, then perform start according to described default unblock instruction
Solve latching operation, in order to described Television clients is carried out cold start-up;Or
Time at described Television clients with open state, then perform application according to described default unblock instruction
Solve latching operation, in order to will be unlocked with the default described application unlocking instruction corresponding, entrance is described should
With.
7. a speech unlocking device, it is characterised in that including: Television clients, described TV client
End includes:
Acquisition module, for obtaining the phonetic order of user, extracts the acoustic features letter of described phonetic order
Breath, determines the user type of user according to described acoustic features information;
Judge module, is used for judging that described user type is the most consistent with pre-set user type;
Identification module, if consistent with described pre-set user type for described user type, then identifies institute
State phonetic order, according to described phonetic order and the described default corresponding relation unlocked between instruction, it is judged that
Described phonetic order is the most corresponding with presetting unblock instruction;
Perform module, for if the determination result is YES, then instruct execution with described according to described default unblock
Preset and unlock instruction to corresponding solution latching operation.
Device the most according to claim 7, it is characterised in that described acquisition module, uses further
In: extract the acoustic features information of described phonetic order, and with the sound being pre-stored in acoustic features information bank
Learn characteristic information alignment similarity;
Obtain described similarity more than or equal to the acoustics in the described acoustic features information bank of similarity threshold
Characteristic information;
Determine described in described user according to the acoustic features information in the described acoustic features information bank obtained
User type.
Device the most according to claim 8, it is characterised in that also include: set up module, is used for
Set up described acoustic features information bank, including: gather at least two voice messaging, extract each collecting
The acoustic features information of described voice messaging, wherein, described voice messaging includes the voice messaging of adult
Voice messaging with child;
According to default grouping strategy, the acoustic features information of the described voice messaging collected is divided into adult
Group and child's group, and be saved in described acoustic features information bank.
Device the most according to claim 9, it is characterised in that described acquisition module, is additionally operable to:
If the acoustic features information in the described acoustic features information bank obtained is included in described adult group,
The most described user type is adult;
If the acoustic features information in the described acoustic features information bank obtained is included in described child's group,
The most described user type is child.
11. devices according to claim 7, it is characterised in that described identification module, are additionally operable to:
The described user type of described user and described pre-set user is being determined according to described acoustic features information
After type is consistent, described user is carried out recognition of face, obtains the face characteristic information of described user,
Face characteristic information according to described user determines the described user type of described user;
If described user type is consistent with described pre-set user type, then identify described phonetic order.
12. according to the arbitrary described device of claim 7-11, it is characterised in that described execution module,
It is further used for:
Time at described Television clients with off-mode, then perform start according to described default unblock instruction
Solve latching operation, in order to described Television clients is carried out cold start-up;Or
Time at described Television clients with open state, then perform application according to described default unblock instruction
Solve latching operation, in order to will be unlocked with the default described application unlocking instruction corresponding, entrance is described should
With.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610245100.XA CN105933765A (en) | 2016-04-19 | 2016-04-19 | Voice unlocking method and device |
PCT/CN2016/101055 WO2017181610A1 (en) | 2016-04-19 | 2016-09-30 | Voice unlocking method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610245100.XA CN105933765A (en) | 2016-04-19 | 2016-04-19 | Voice unlocking method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105933765A true CN105933765A (en) | 2016-09-07 |
Family
ID=56839333
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610245100.XA Pending CN105933765A (en) | 2016-04-19 | 2016-04-19 | Voice unlocking method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105933765A (en) |
WO (1) | WO2017181610A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017181610A1 (en) * | 2016-04-19 | 2017-10-26 | 乐视控股(北京)有限公司 | Voice unlocking method and device |
CN107483997A (en) * | 2017-08-25 | 2017-12-15 | 四川长虹电器股份有限公司 | Children's lock control system and method |
CN107808085A (en) * | 2017-10-27 | 2018-03-16 | 华勤通讯技术有限公司 | the fingerprint control method and system of intelligent terminal |
CN109859764A (en) * | 2019-01-04 | 2019-06-07 | 四川虹美智能科技有限公司 | A kind of sound control method and intelligent appliance |
CN110024355A (en) * | 2016-09-27 | 2019-07-16 | 华为技术有限公司 | It is a kind of that the method serviced and terminal device are provided |
CN110555922A (en) * | 2018-05-15 | 2019-12-10 | 上海博泰悦臻网络技术服务有限公司 | Vehicle and child lock control method based on voiceprint recognition |
WO2021051403A1 (en) * | 2019-09-20 | 2021-03-25 | 深圳市汇顶科技股份有限公司 | Voice control method and apparatus, chip, earphones, and system |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113349998B (en) * | 2021-05-31 | 2022-11-18 | 力迈德医疗(广州)有限公司 | Rehabilitation equipment control method, device and equipment based on protective tool |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS63298768A (en) * | 1987-05-28 | 1988-12-06 | Matsushita Electric Ind Co Ltd | Information recording disk reproducing device |
US20020029382A1 (en) * | 2000-09-05 | 2002-03-07 | Eric Deniau | Method of locking or unlocking a service on a digital receiver of audiovisual programs and device for implementing the method |
US20070070188A1 (en) * | 2005-05-05 | 2007-03-29 | Amtran Technology Co., Ltd | Method of audio-visual communication using a television and television using the same |
CN103297846A (en) * | 2012-03-01 | 2013-09-11 | 迈实电子(上海)有限公司 | Intelligent television and control system and method thereof |
CN103973892A (en) * | 2014-05-12 | 2014-08-06 | 深圳市威富多媒体有限公司 | Method and device for starting and stopping mobile terminal based on voice and face recognition |
CN104021790A (en) * | 2013-02-28 | 2014-09-03 | 联想(北京)有限公司 | Sound control unlocking method and electronic device |
CN104331651A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Fingerprint- and voice recognition-based control system and equipment |
CN104915586A (en) * | 2014-03-14 | 2015-09-16 | 中国移动通信集团公司 | Screen unlocking method and device of terminal and terminal |
CN105472159A (en) * | 2015-12-17 | 2016-04-06 | 青岛海信移动通信技术股份有限公司 | Multi-user unlocking method and device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
CN103888604A (en) * | 2014-03-10 | 2014-06-25 | 深圳市金立通信设备有限公司 | Method for switching application modes of terminal, and terminal |
CN105335082A (en) * | 2014-07-29 | 2016-02-17 | 小米科技有限责任公司 | Screen unlocking control method and apparatus |
CN105306673A (en) * | 2015-09-07 | 2016-02-03 | 惠州Tcl移动通信有限公司 | Mobile terminal and automatic scene mode adjustment method thereof |
CN105933765A (en) * | 2016-04-19 | 2016-09-07 | 乐视控股(北京)有限公司 | Voice unlocking method and device |
CN105930055A (en) * | 2016-04-19 | 2016-09-07 | 乐视控股(北京)有限公司 | Interface skip management method and apparatus |
-
2016
- 2016-04-19 CN CN201610245100.XA patent/CN105933765A/en active Pending
- 2016-09-30 WO PCT/CN2016/101055 patent/WO2017181610A1/en active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS63298768A (en) * | 1987-05-28 | 1988-12-06 | Matsushita Electric Ind Co Ltd | Information recording disk reproducing device |
US20020029382A1 (en) * | 2000-09-05 | 2002-03-07 | Eric Deniau | Method of locking or unlocking a service on a digital receiver of audiovisual programs and device for implementing the method |
US20070070188A1 (en) * | 2005-05-05 | 2007-03-29 | Amtran Technology Co., Ltd | Method of audio-visual communication using a television and television using the same |
CN103297846A (en) * | 2012-03-01 | 2013-09-11 | 迈实电子(上海)有限公司 | Intelligent television and control system and method thereof |
CN104021790A (en) * | 2013-02-28 | 2014-09-03 | 联想(北京)有限公司 | Sound control unlocking method and electronic device |
CN104915586A (en) * | 2014-03-14 | 2015-09-16 | 中国移动通信集团公司 | Screen unlocking method and device of terminal and terminal |
CN103973892A (en) * | 2014-05-12 | 2014-08-06 | 深圳市威富多媒体有限公司 | Method and device for starting and stopping mobile terminal based on voice and face recognition |
CN104331651A (en) * | 2014-10-08 | 2015-02-04 | 无锡指网生物识别科技有限公司 | Fingerprint- and voice recognition-based control system and equipment |
CN105472159A (en) * | 2015-12-17 | 2016-04-06 | 青岛海信移动通信技术股份有限公司 | Multi-user unlocking method and device |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017181610A1 (en) * | 2016-04-19 | 2017-10-26 | 乐视控股(北京)有限公司 | Voice unlocking method and device |
CN110024355A (en) * | 2016-09-27 | 2019-07-16 | 华为技术有限公司 | It is a kind of that the method serviced and terminal device are provided |
CN107483997A (en) * | 2017-08-25 | 2017-12-15 | 四川长虹电器股份有限公司 | Children's lock control system and method |
CN107808085A (en) * | 2017-10-27 | 2018-03-16 | 华勤通讯技术有限公司 | the fingerprint control method and system of intelligent terminal |
CN110555922A (en) * | 2018-05-15 | 2019-12-10 | 上海博泰悦臻网络技术服务有限公司 | Vehicle and child lock control method based on voiceprint recognition |
CN109859764A (en) * | 2019-01-04 | 2019-06-07 | 四川虹美智能科技有限公司 | A kind of sound control method and intelligent appliance |
WO2021051403A1 (en) * | 2019-09-20 | 2021-03-25 | 深圳市汇顶科技股份有限公司 | Voice control method and apparatus, chip, earphones, and system |
Also Published As
Publication number | Publication date |
---|---|
WO2017181610A1 (en) | 2017-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105933765A (en) | Voice unlocking method and device | |
EP3156928B1 (en) | Iris identification based mobile terminal identity authentication processing method and system | |
EP2753109B1 (en) | Mobile terminal and application program login method thereof | |
CN105930055A (en) | Interface skip management method and apparatus | |
US20130227678A1 (en) | Method and system for authenticating user of a mobile device via hybrid biometics information | |
CN104778416B (en) | A kind of information concealing method and terminal | |
CN105045085B (en) | The control method and intelligent watch of a kind of intelligent watch | |
CN103886237A (en) | Control method and system for electronic device with fingerprint sensor and touch screen | |
US20110157347A1 (en) | Unintrusive biometric capture device, system and method for logical access control | |
CN109729400A (en) | Apparatus control method, device, equipment and storage medium based on sound | |
CN108319837A (en) | Electronic equipment, face template input method and Related product | |
CN108734838B (en) | Intelligent lock with video-based biological feature verification device | |
CN105184133B (en) | A kind of method for authenticating, device and corresponding mobile terminal | |
WO2019062122A1 (en) | Door opening method and device, access control device, and computer readable storage medium | |
WO2015169151A1 (en) | Touch screen unlocking method, device and electronic device, display and mobile terminal | |
WO2013040838A1 (en) | Password validation method and mobile terminal applying same | |
WO2017067507A1 (en) | Method and device for determining a use permission of an apparatus | |
CN104966009A (en) | Information processing method and electronic equipment | |
CN103324947A (en) | Certification method and authentication method | |
CN112286070A (en) | Equipment control method and device and electronic equipment | |
CN105611036A (en) | Method, system and terminal for unlocking verification | |
CN106895552A (en) | The control method of air-conditioning, apparatus and system | |
CN105868601A (en) | Pressure touch screen-based electronic terminal, encryption unlocking controller and method | |
JP2006260461A (en) | Access control system and information processing system using the same | |
CN111966991A (en) | Equipment unlocking method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160907 |