Summary of the invention
To solve the above-mentioned problems, it is contemplated that sound groove recognition technology in e is applied to intelligent sound box, Intelligent story device etc.
On the smart machine of interactive voice, locked for the equipment by vocal print.In this way, which only voiceprint typing intelligence is set
The standby talent can wake up machine, carry out corresponding voice operating.There is the case where child for some familys, it can be by adult's
Vocal print locks to equipment, the problem of of causing equipment fault such as thus can arbitrarily wake up to avoid child.
According to the first aspect of the invention, a kind of method for preventing interactive voice equipment by false wake-up is provided, including
Following steps:
Main control device is set for interactive voice equipment;
Interactive voice equipment carries out authorization requests when getting voice wake up instruction, to main control device, is set according to master control
The standby authorized order returned, carries out voice wake-up processing;
Wherein, it is communicated between main control device and interactive voice equipment by one-to-one link.
According to the second aspect of the invention, provide it is a kind of by preventing interactive voice equipment by the device of false wake-up,
Include:
Voiceprint registration module, the vocal print storage for being bound for interactive voice facility registration;
Communication module, for establishing and the one-to-one two-way communication link of interactive voice equipment;
Authorization identifying module, for authorization requests and the voiceprint registration module storage according to the interactive voice equipment received
Vocal print, generate authorized order export to interactive voice equipment.
According to the third aspect of the present invention, provide it is a kind of by preventing interactive voice equipment by the system of false wake-up,
Including at least two interactive voice equipment and main control device, wherein main control device prevents interactive voice equipment from being missed for above-mentioned
The control device of wake-up is in one-to-one connection status with one of interactive voice equipment;
Interactive voice equipment includes
Voice wake-up module, it is when listening to voice wake up instruction that voice wake up instruction is defeated for carrying out wake-up monitoring
Out to authorization request module;With progress voice wake-up processing;
Authorization request module is used for according to voice wake up instruction output authorization requests to main control device, and is set according to master control
The standby authorized order returned calls the voice wake-up module to carry out voice wake-up processing.
According to the fourth aspect of the present invention, a kind of method for realizing anti-false wake-up using above-mentioned system is provided, is wrapped
Include following steps:
The voiceprint registration of interactive voice equipment is carried out on main control device;
Currently controlled interactive voice equipment is set on main control device;
Main control device obtains voiceprint and is matched with the vocal print of registration, according to matching when receiving authorization requests
As a result authorized order is exported to currently controlled interactive voice equipment.
The method, apparatus and system provided according to the present invention can overcome in the prior art in same range, anyone
Any smart machine for being provided with the wake-up word can be waken up, the interaction of equipment is chaotic, influences user experience etc. is caused
Problem carries out authorization control to interactive voice equipment on main control device by sound groove recognition technology in e, is equivalent to interactive voice
A lock in equipment only receives under unlocking condition and correctly to wake up word and can just be waken up, is really achieved equipment and uses
The one-to-one wake-up in family reduces false wake-up rate, and can prevent the smart machine of oneself from being waken up by other people.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.
The present invention can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, member
Part, data structure etc..The present invention can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
In the present invention, the fingers such as " module ", " device ", " system " are applied to the related entities of computer, such as hardware, hardware
Combination, software or software in execution with software etc..In detail, for example, element can with but be not limited to run on processing
Process, processor, object, executable element, execution thread, program and/or the computer of device.In addition, running on server
Application program or shell script, server can be element.One or more elements can be in the process and/or thread of execution
In, and element can be localized and/or be distributed between two or multiple stage computers on one computer, and can be by each
Kind computer-readable medium operation.Element can also according to the signal with one or more data packets, for example, from one with
Another element interacts in local system, distributed system, and/or the network in internet passes through signal and other system interactions
The signals of data communicated by locally and/or remotely process.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise", not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including described want
There is also other identical elements in the process, method, article or equipment of element.
The embodiment of the present invention prevents interactive voice equipment to can be applied to any be configured with voice by the method for false wake-up
The terminal device of function, for example, the terminal devices such as smart phone, tablet computer, smart home, the invention is not limited in this regard,
So that user obtains response more promptly and accurately during using these terminal devices, false wake-up is prevented, is mentioned
Rise user experience.The invention will now be described in further detail with reference to the accompanying drawings.
What Fig. 1 schematically showed a kind of embodiment according to the present invention prevents interactive voice equipment by false wake-up
Method flow diagram.As shown in Figure 1, including the following steps: in the present embodiment
Step S101: main control device is set for interactive voice equipment.Wherein, interactive voice equipment includes intelligent sound box, event
The smart machines such as affairs that should be kept secret and TV are equipped with interactive voice application terminal, such as the language of Si Bichi company on this kind of smart machine
Sound assistant, so that these smart machines can be realized voice interactive function.Main control device, which is embodied as being equipped with, controls the voice
The intelligent terminal of interactive device APP, such as it is embodied as smart phone, it can control any voice of paired connection
Interactive device.It is linked between main control device and interactive voice equipment by one-to-one, such as the mode of Bluetooth pairing connection carries out
Communication guarantees that controlled interactive voice equipment is only to ensure that a main control device is only an interactive voice device authorization
One.
Step S102: interactive voice equipment carries out authorization requests, root when getting voice wake up instruction, to main control device
According to the authorized order that main control device returns, voice wake-up processing is carried out.
Illustratively, device of the interactive voice equipment by its microphone array etc. with audio collection function sends out user
Voice wake up instruction out carries out pickup, such as gets " hello, small slow ", the user speech such as " I will start " instruction.Voice
Interactive device exports the voiceprint of voice wake up instruction or voice wake up instruction to master when getting voice wake up instruction
It controls equipment and carries out authorization requests, which is the voiceprint that the voice wake up instruction issued according to user is got, packet
The information such as tone color, the volume of voice wake up instruction of user's sending are included, voiceprint is obtained according to phonetic order and is referred to now
There is technology realization.Interactive voice equipment carries out wake-up reply process according to the authorized order that the main control device received returns.
Wherein, the authorization requests that interactive voice equipment issues can directly be the voice wake up instruction got, by leading
It controls equipment and carries out vocal print processing and identification, after being also possible to interactive voice equipment progress voiceprint extraction, generated according to voiceprint
Authorization requests.Wherein, it in authorization requests can also include for identifying voice interactive device information, such as interactive voice equipment
Device name.
Voice print database is set up in the main control device, which is stored with individual when user's registration vocal print
The mode of information and voiceprint, voiceprint registration is referred to the prior art.Main control device is receiving authorization requests
When, voiceprint is extracted from acquisition voiceprint in authorization requests or according to the voice wake up instruction in authorization requests, and will
Voiceprint is compared with voice print database, if the voiceprint is present in voice print database, that is, compares successfully, then to this
The voice wake up instruction of user authorizes, and returns to interactive voice device authorization and successfully instructs such as return " success "
Authorized order.Wherein, authorized order is returned to interactive voice equipment, is by obtaining current a pair of establishing just like bluetooth connection
Interactive voice equipment, by the one-to-one connection by interacting.After interactive voice equipment gets authorized order, with regard to basis
Authorized order triggers the answering of the interactive voice equipment, illustratively, if authorized order is " success ", the voice
Interactive device will reply, and thank-you speech is answered in sending, such as issue " hello, owner ", " hello, small field " etc. answers thank-you speech.Later by user
It issues phonetic order and carries out interactive voice.
If the voiceprint is not present in voice print database, that is, failure is compared, then voice of the main control device to the user
Wake up instruction without authorization, return to interactive voice device authorization failure instruction, such as return " failed " authorization refer to
It enables.Interactive voice equipment receives authorization failure instruction, can trigger the instruction of suspend mode, then interactive voice equipment continues to keep suspend mode
State does not make any response.
The method of the embodiment of the present invention by setting main control device, and registers vocal print in main control device, realizes and be based on
Vocal print is to the authorization control of interactive voice equipment, so that the voice that the interactive voice equipment of authorization can be issued by active user
Wake up instruction wakes up, and other interactive voice equipment all can be only in dormant state, can overcome in the prior art in same model
In enclosing, anyone can wake up any intelligent sound interactive device for being provided with the wake-up word, cause the interaction of equipment it is chaotic,
The problems such as influencing user experience.The technical solution of the embodiment of the present invention, by the technology of Application on Voiceprint Recognition be really achieved equipment with
The one-to-one wake-up of user reduces false wake-up rate, and can also prevent the intelligent sound interactive device of oneself from being called out by other people
It wakes up.
Fig. 2 schematically show according to an embodiment of the present invention prevent interactive voice equipment by the control of false wake-up
Device principle block diagram, as shown in Fig. 2,
It by the control device of false wake-up includes voiceprint registration module 201,202 and of communication module that this, which prevents interactive voice equipment,
Authorization identifying module 203.
The vocal print that voiceprint registration module 201 is used for as the binding of interactive voice facility registration, and the voiceprint storage registered.
Illustratively, which for example can be the smart machines such as intelligent sound box, Story machine and TV.Register the side of vocal print
The voiceprint registration method that formula is referred to the prior art is realized.
Communication module 202 is used to establish and the one-to-one two-way communication link of interactive voice equipment, is illustratively embodied as
Communication module bluetooth-capable.
Authorization identifying module 203 is used for authorization requests and voiceprint registration module according to the interactive voice equipment received
The vocal print of 201 storages generates authorized order and exports to interactive voice equipment.
Illustratively, in main control device, that is, the controlling terminal of the device of the present embodiment is installed, it is middle to be handed in advance for voice
Mutual facility registration vocal print library, vocal print inventory contain the voiceprint of user's registration.Main control device is set receiving interactive voice
When standby authorization requests, according to the matching result of voiceprint and vocal print library, awarded to the interactive voice equipment output currently connected
Power instruction, wherein authorization requests include voiceprint or voice messaging, when for voiceprint, directly progress and voiceprint registration
The voiceprint stored in module 201 carries out voice print matching and first extracts voiceprint when for voice messaging, later carry out sound
Line matching, and authorized order is exported according to matching result.Authorized order includes authorizing successfully instruction and authorization failure instruction, if awarding
It weighs successfully, then returns to interactive voice device authorization and successfully instruct, trigger the answering of the interactive voice equipment, which hands over
Mutual equipment will reply, and thank-you speech is answered in sending, and illustratively, " hello, owner ", " hello, small field " etc. answers thank-you speech, later by user
It issues phonetic order and carries out interactive voice.If authorization failure, the instruction of Semantic interaction device authorization failure, the authorization are returned to
Failure command can trigger the instruction of interactive voice device sleeps, then interactive voice equipment continues to keep dormant state, not make any
The specific implementation of the response part is referred to method part, herein without repeating.
It can be overcome in the prior art in same range according to the device of the present embodiment, anyone can wake up setting
The problems such as having any smart machine of the wake-up word, causing the chaotic interaction of equipment, influence user experience.Pass through Application on Voiceprint Recognition
Technology be really achieved equipment and the one-to-one wake-up of user, reduce false wake-up rate, prevent the smart machine of oneself by other people
It wakes up.And the present apparatus can be freely mounted on any intelligent terminal, and support multiple voice interactive device, be had very strong
Practicability.
Fig. 3 schematically show according to an embodiment of the present invention prevent interactive voice equipment by the system of false wake-up
Block diagram, as shown in figure 3,
This prevents interactive voice equipment from including at least two interactive voice equipment 3 and main control device 4 by the system of false wake-up,
Wherein, main control device 4 prevents interactive voice equipment by the control device of false wake-up for above-mentioned, with one of interactive voice
Equipment 3 is in one-to-one connection status by bluetooth connection.
Interactive voice equipment 3 includes voice wake-up module 301 and authorization request module 302.Wherein,
Voice wake-up module 201 is for carrying out wake-up monitoring, when listening to voice wake up instruction by voice wake up instruction
Output is embodied as the audio collecting device with pickup function to authorization request module 302.And the voice wake-up module 201
Voice wake-up processing can also be carried out, i.e., the interactive voice equipment 3 is controlled according to voice wake-up word and carries out corresponding interactive voice.
Authorization request module 302 is used for according to voice wake up instruction output authorization requests to main control device 4, and according to master control
The authorized order that equipment 4 returns calls voice wake-up module 301 to carry out voice wake-up processing, and the processing of the authorization requests can be joined
According to above-mentioned method part.
In the specific implementation, authorization requests can be including voiceprint or can be including voice messaging (i.e. voice wake-up
Instruction).When authorization requests include voiceprint, needs to carry out voiceprint extraction in interactive voice equipment, in this case, award
Power request module 302 is arranged to include Application on Voiceprint Recognition unit 3021, for carrying out Application on Voiceprint Recognition, output sound to voice wake up instruction
Line information is referred to existing sound groove recognition technology in e and realizes.
It may be implemented to overcome in the prior art in same range according to the system of the present embodiment, anyone can wake up
The problems such as being provided with any smart machine of the wake-up word, causing the chaotic interaction of equipment room, influence user experience.Pass through sound
The technology of line identification is really achieved equipment and the one-to-one wake-up of user, reduces false wake-up rate, prevents the smart machine quilt of oneself
Other people wake up.
Fig. 4 schematically shows that utilization according to an embodiment of the present invention prevents interactive voice equipment by false wake-up
System realizes the method flow diagram of anti-false wake-up, as shown in figure 4, the present embodiment includes the following steps:
Step S401: the voiceprint registration of interactive voice equipment is carried out on main control device.User passes through on main control device
The devices such as the microphone with audio collection function export voice, carry out voiceprint registration, and the mode of the voiceprint registration is referred to
The prior art is realized.
Step S402: currently controlled interactive voice equipment is set on main control device.Illustratively, on main control device
Bluetooth function is opened, for matching connection with controlled interactive voice equipment, successful interactive voice equipment will be attached thereto, made
To be currently controlled interactive voice equipment.
Step S403: main control device obtains voiceprint and is matched with the vocal print of registration when receiving authorization requests,
Authorized order is exported to currently controlled interactive voice equipment according to matching result.User issues voice wake up instruction, and master control is set
It after receiving the voice wake up instruction, is matched based on Application on Voiceprint Recognition with the vocal print of registration, is awarded according to the realization of the method for Fig. 1
Power, to start the voice interactive function of interactive voice equipment or continue to keep dormant state.
According to the method for the present embodiment, user easily can freely carry out interactive voice, carry out vocal print binding with it
Interactive voice equipment, can be waken up, guarantee user privacy right and exclusive power.Also, almost due to one-to-one setting
There is no the false wake-up situations of " getting ready to go into action in hundreds ", greatly improve the experience sense of user.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, above-mentioned technology
Scheme substantially in other words can be embodied in the form of software products the part that the relevant technologies contribute, the computer
Software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions to
So that computer equipment (can be personal computer, server or the network equipment etc.) execute each embodiment or
Method described in certain parts of embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.