CN109741755A - Voice wakes up word threshold management device and manages the method that voice wakes up word threshold value - Google Patents
Voice wakes up word threshold management device and manages the method that voice wakes up word threshold value Download PDFInfo
- Publication number
- CN109741755A CN109741755A CN201811591702.6A CN201811591702A CN109741755A CN 109741755 A CN109741755 A CN 109741755A CN 201811591702 A CN201811591702 A CN 201811591702A CN 109741755 A CN109741755 A CN 109741755A
- Authority
- CN
- China
- Prior art keywords
- word
- threshold
- voice
- wakes
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Telephonic Communication Services (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention discloses a kind of voice wake-up word threshold management device, comprising: the first memory module, the voice for storing product wake up word and its test threshold；Threshold value distribution module wakes up word parameter for receiving new project verification, wakes up word and its test threshold according to the voice that new project verification wakes up the product stored in word parameter and the first memory module, wakes up word assigned references threshold value for new project verification.The present invention also provides the management methods that a kind of voice wakes up word threshold value, the device and method provided according to the present invention may be implemented to combine the practical average value for waking up word threshold calculations and obtaining, the wake-up word threshold value obtained is set more to tally with the actual situation, and it can avoid computing repeatedly and wake up word threshold value, the time that management wakes up word threshold value is saved, treatment effeciency is greatly improved.
Description
Technical field
Word technical field is waken up the present invention relates to voice more particularly to a kind of voice wakes up word threshold management device and management
The method of voice wake-up word threshold value.
Background technique
In the prior art, voice being often related to during interactive voice and waking up word, word is waken up by voice and carries out various function
Can interactive voice provide many conveniences for people, still, in order to guarantee that voice wakes up that word is available or utilization rate height, need pair
It carries out threshold calculations, carries out in the process that threshold value determines waking up word to voice, the threshold value of one wake-up word of calculating and test
A large amount of time and human cost are needed, so that treatment process efficiency is too low.
Summary of the invention
Inventor is although a variety of more by the product in long-term summary of experience discovery practical application in practice process
Sample, but different products may be in the presence of having the case where same or similar wake-up word, and this has resulted in computing repeatedly, and due to
As soon as the threshold value that calculating and test wake up word needs a large amount of time and a human cost, energy can be avoided greatly if computed repeatedly
Width improves treatment effeciency, saves time and human cost.Based on this, inventor is according to the rule for waking up word threshold calculations, never
The angle for waking up word there may be same or similar voice with product is set out, and a solution is proposed, to solve existing skill
The problem that the threshold calculations process of wake-up word is complicated present in art, treatment effeciency is low.
In a first aspect, the embodiment of the present invention provides a kind of voice wake-up word threshold management device, comprising:
First memory module, the voice for storing product wake up word and its test threshold；Threshold value distribution module, for connecing
It receives new project verification and wakes up word parameter, word is waken up according to the voice that new project verification wakes up the product stored in word parameter and the first memory module
And its test threshold, word assigned references threshold value is waken up for new project verification.
Second aspect, the embodiment of the present invention provide a kind of method that management voice wakes up word threshold value, comprising:
Configure the first memory module；The first user instruction is received, the language of the product of input is obtained according to the first user instruction
Sound wakes up word and its test threshold is stored to the first memory module；Second user instruction is received, is instructed and is obtained according to second user
New project verification wakes up word parameter；Word and its test threshold are waken up according to the voice that new project verification wakes up the product of word parameter and storage, is
New project verification wakes up word assigned references threshold value.
The third aspect, the present invention provides a kind of electronic equipment comprising: at least one processor, and at least one
The memory of a processor communication connection, wherein memory is stored with the instruction that can be executed by least one processor, instructs quilt
At least one processor executes, so that the step of at least one processor is able to carry out the above method.
Fourth aspect, the present invention provides a kind of storage mediums, are stored thereon with computer program, and the program is by processor
The step of above method is realized when execution.
The beneficial effect of the embodiment of the present invention is: the voice provided according to the present invention wakes up word threshold management device and side
Method, by the first memory module, can store the existing different product tested in market different phonetic wake up word and its
Test threshold (threshold value for having already passed through test), in this way when carrying out product project verification, so that it may which word parameter is waken up according to new project verification
Reference threshold is obtained rapidly with the wake-up word information prestored in the first memory module.As a result, if had in the first memory module close
As wake up word parameter, so that it may directly by simple computation obtain this it is new project verification product wake-up word threshold value, avoid and also
The excess step to be recalculated.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for this field
For those of ordinary skill, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is that the voice of an embodiment of the present invention wakes up word threshold management device principle block diagram；
Fig. 2 is that the voice of another embodiment of the present invention wakes up word threshold management device principle block diagram；
Fig. 3 is that the management voice of an embodiment of the present invention wakes up the method flow diagram of word threshold value；
Fig. 4 is that the management voice of a further embodiment of this invention wakes up the method flow diagram of word threshold value；
Fig. 5 is that the management voice of a further embodiment of this invention wakes up the method flow diagram of word threshold value；
Fig. 6 is the structural schematic diagram of an embodiment of electronic equipment of the invention.
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 method and device that management voice in the embodiment of the present invention wakes up word threshold value can be used for calling out for new product of setting up the project
The generation of awake word, can be configured on terminal device, can configured with display screen or the terminal device on the terminal device
It is projected out display interface and interacts operation for user, for example, smart television, smart phone, tablet computer, PC, intelligent family
Any Intelligent hardware such as residence, projector, new product of setting up the project can be any terminal device with voice interactive function, such as intelligence
Energy TV, smart phone, tablet computer, PC, smart home, projector etc., this is not limited by the present invention.
Fig. 1 schematically shows that voice according to an embodiment of the present invention wakes up word threshold management device, such as Fig. 1 institute
Show, it includes: the first memory module 2, threshold value distribution module 3, product threshold management module which, which wakes up word threshold management device 1,
4 and initial threshold management module 5.
Wherein, the voice that the first memory module 2 is used to store product wakes up word and its test threshold, and illustratively it can be with
Database is embodied as, wherein the voice stored wakes up the corresponding test threshold of word can call out for the different phonetic of each product on the market
The threshold value of awake word calculated and pass through test, since the threshold value that the same voice of different product wakes up word may difference
(i.e. wake-up word is same or similar, but these wake up words be for different product, thus threshold value difference), by identical product
Wake-up word, its corresponding wake-up word phonetic and its corresponding test threshold be stored in same table, it is as follows:
| Product | Voice wakes up word | Voice wakes up word phonetic | Test threshold |
Also, the content of the table with advances in technology, the research and development of new product, the reasons such as the improvement of product will do it reality
Shi Gengxin.It can store a large amount of product voice by the memory module 2 and wake up word threshold data, directly by tabling look-up
It gets, different applications can also be carried out, as big data basis, there is significant application value.
Threshold value distribution module 3 wakes up word parameter for receiving new project verification, wakes up word parameter and the first storage according to new project verification
The voice of the product stored in module 2 wakes up word and its test threshold, wakes up word assigned references threshold value for new project verification.Wherein, newly
It is in user's development or use process that project verification, which wakes up word parameter, and customized voice wakes up word, and parameter includes that voice wakes up word
Chinese characters and pinyin, be input to voice of the invention and wake up in word threshold management device 1, can be inputted by hand-typing
It realizes, the voice of input is waken up into word and is matched with the voice wake-up column of word one in the first memory module 2, in order to which determination is more quasi-
True search result, the column of phonetic one for waking up word also according to voice carry out Secondary Match, by the survey of the different product of successful match
Examination threshold parameter extracts, according to extraction as a result, the test threshold for waking up word to the same voice of different product does average value
It calculates, obtains reference threshold that can be for reference, which, which can be used as newly setting up the project, wakes up the initial threshold investment of word
It uses.Such calculation is simple and fast, and due to being calculated by the test threshold of big data, thus accuracy rate compared with
Height can be used family and obtain the reference threshold that satisfied new project verification wakes up word.
Product threshold management module 4 is used for the user instruction in response to receiving, and the voice of the product received is waken up
Word and its test threshold store to the first memory module 2 or obtain from the first memory module 2 product for meeting instruction condition
Voice wakes up word and its test threshold is presented to the user.When user only wishes to check that the voice that oneself is Product Definition wakes up word
And its when threshold condition, word or its phonetic can be waken up with input product type, voice, be called according to product threshold management module 4
First memory module 2, so that it may which the voice for accurately obtaining similar-type products wakes up word and its test threshold, or gets difference
The same voice of product wakes up the threshold value of word.Also, each voice of the product that in a particular application, can also look at same type wakes up
Same voice wakes up the threshold value distribution of word in the threshold value distribution of word and different types of product, and inquiry mode can refer to
It describes above, herein without repeating.Also, it, can also be defeated by user when user uses the device with the identity of administrator
The voice entered wakes up word and test threshold is added to the first memory module 2, completes the data base updated in extension storage module 2
The effect of plinth is dynamically updated the calculating basic data i.e. threshold data range that can to obtain more to memory module 2
Greatly, numerical value is more accurate.
Initial threshold management module 5 is used for the user instruction in response to receiving, which is embodied as inquiring or storing language
Sound wakes up the threshold value of word, and the voice of the product received is waken up word and its initial threshold is stored or obtained and meets instruction condition
The voice of product wakes up word and its initial threshold is presented to the user.In addition to can be by product threshold management module 4 to product
Except voice wake-up word and its test threshold are managed, as a preferred embodiment, the present embodiment further includes initial threshold management
Module 5 wakes up word with the voice to product and its initial threshold is managed, and specific implementation is referred to product threshold value
Management module 4 is realized, be can receive and is carried out the inquiry that voice wakes up word and its initial threshold for the inquiry instruction of input,
Newly-increased product voice wake-up word and its initial threshold can also be received to be stored, checked with facilitating.Wherein, product voice is called out
Awake word and its initial threshold can be stored in simultaneously in the first memory module, can also be stored separately in the second memory module.
The realization of second memory module is referred to the first memory module, when storing in the first memory module simultaneously, it is only necessary to increase
Add a new column.
It can be realized according to the voice of the present embodiment wake-up word threshold management device and new project verification is obtained by simple computation
The wake-up word threshold value of product reduces the cost consumption of calculating from avoiding the angle computed repeatedly from improving the efficiency of threshold calculations.
And in the implementation of the embodiment of the present invention, calculating reference threshold is that the test threshold based on actual use is calculated,
Obtained reference threshold more meets actual use situation, and availability is higher.And above-mentioned apparatus can also be for user's real-time query
The voice of product wakes up word and its threshold value distribution, facilitates and carries out waking up word management.
In other embodiments, it can also be not provided with above-mentioned initial threshold management module 5, or above-mentioned each module is carried out
Independent assortment, is accordingly arranged and is realized according to demand, the embodiment of the present invention is not intended as the limit to specific implementation form
System.
Fig. 2 schematically shows that the voice of another embodiment according to the present invention wakes up word threshold management device, such as Fig. 2
It is shown,
The device further include: version management module 6, for configuring and the memory space of the matches version information of product.Its
In, the specific implementation of configuration and the memory space of the matches version information of product can be the base in the first memory module 2
The version information of product is added on plinth again, forms following table:
It is also possible to based on product version, the first memory module 2 is divided into different memory spaces, such as divide
For different table data stores, the corresponding version of each table data store.The embodiment of the present invention to specific implementation not into
Row limitation, as long as can satisfy version management demand.
In this way after some product renewings and improvement, corresponding voice wakes up the feelings that the test threshold of word also changes correspondingly
Under condition, accurate threshold information can also be inquired by version management, and based on statistics capable of being carried out by different versions
It calculates, is further ensured that the accuracy of calculated result.
It in this embodiment, may include Release parameter in user instruction, such product threshold management module 4 can be real
It is now the Release parameter being also used to according to user instructions, i.e., can wrap the specific version containing product in the inquiry instruction of user
The voice of the product received is waken up word and its test threshold is stored into corresponding memory space by parameter, in this way can be with shape
Facilitate subsequent threshold query, calculating etc. at the bigger database of more accurate, coverage area.
Equally, initial threshold management module 5 is also used to the Release parameter according to user instructions, by the product received
Voice wakes up word and its initial threshold is stored to corresponding memory space.It equally can be with the version of combination product for initial threshold
Parameter information is stored and is inquired, to realize version management.
The wake-up word threshold value of product can not only quickly be searched by waking up word threshold management device according to the voice of the present embodiment, also
Wake-up word reference threshold of the average value as new project verification product, and the wake-up obtained can be obtained in conjunction with actual product threshold calculations
Word reference threshold more tallies with the actual situation.Word threshold value is waken up in addition, also can avoid computing repeatedly, saves and generates wake-up word threshold value
Time.It is based on version management simultaneously, particular version threshold value can also be inquired, more targetedly.
Fig. 3 schematically shows that device voice according to an embodiment of the present invention wakes up the method flow of word threshold value
Figure, as shown in figure 3, the present embodiment includes the following steps:
Step S301: the first memory module of configuration is implemented as table or other way, by being stored with based on
The test threshold of product for calculating and testing.
Step S302: receiving the first user instruction, wakes up word according to the voice that the first user instruction obtains the product of input
And its test threshold is stored to the first memory module.First user instruction can be that administrator is that the first memory module is added newly
Voice wake up word and test threshold, can thus expand the range of the first memory module, so that test result is more accurate.
Step S303: receiving second user instruction, obtains new project verification according to second user instruction and wakes up word parameter, according to new
Project verification wakes up word parameter and determines that new project verification wakes up word content.Second user instruction is embodied as user and wants to obtain the language of its new project verification
Sound wakes up the instruction of the threshold value of word, specific implementation are as follows: it is corresponding phonetic that the new project verification of user's input, which is waken up word Content Transformation,
Sequence, the pinyin sequence are the parameter that new project verification wakes up word, can determine that multiple groups have same pinyin sequence according to the parameter
Word is waken up, the wake-up word content of multiple groups pinyin sequence can be showed in the form of a list, goes confirmation to meet its mark manually by user
Quasi- content.
Step S304: word and its test threshold are waken up according to the voice that new project verification wakes up the product of word parameter and storage, are
New project verification wakes up word assigned references threshold value.It is determined after waking up word content, can be called out from the voice of the product of storage according to pinyin sequence
Wake up word in match identical pinyin sequence reference wake up word, i.e., according to stored in the first memory module voice wake-up word and its
The reference that phonetic etc. inquires identical pinyin sequence wakes up word, and the test threshold for waking up word to the reference inquired carries out average value
It calculates, obtains reference threshold, the threshold value that reference threshold wakes up word as new project verification is exported.Wherein, the matched ginseng inquired
Examining and waking up word is multiple groups, so according to mean value calculation it can be concluded that accurate test threshold.
The customized voice of quick and easy acquisition may be implemented according to the method for the present embodiment and wake up word threshold value, and obtain
Result out is due to the data that are referred in big data i.e. the first memory module, so accuracy rate is very high, and from repeating
It calculates.And first memory module can be provided the data to grow with each passing hour and be given reference with real-time update.
Fig. 4 schematically shows that the device voice of another embodiment according to the present invention wakes up the method flow of word threshold value
Figure, as shown in figure 4, the present embodiment includes the following steps:
The implementation of step S401 to step S402 are referred to step S301 to step S302.
Step S403: inquiry instruction condition is obtained according to the first user instruction, meets instruction condition from the first memory module
The voice of product wake up word and its test threshold and be presented to the user.User can be by issuing inquiry instruction condition, the instruction
Condition includes: that voice wakes up word content, product, is combined, can be obtained from the first memory module according to different querying conditions
Different information.It will acquire information to be presented to the user in the form of table obtains list etc..
Thus, it is possible to which the voice for user's real-time query different type product wakes up word and its threshold value distribution, facilitate management,
And it can also determine that its customized voice wakes up the information such as the utilization rate of word according to query result.
Fig. 5 schematically shows that the device voice of another embodiment according to the present invention wakes up the method flow of word threshold value
Figure, as shown in figure 5, including the following steps: in the present embodiment
Step 501: the first memory module of configuration.Specific implementation is referred to step S301.
Step S502: the second memory module of configuration.Second memory module be used for store product voice wake up word and its just
Beginning threshold value, shown in following table:
| Product | Voice wakes up word | Initial threshold |
Step S503: receiving third user instruction, wakes up word according to the voice that third user instruction obtains the product of input
And its initial threshold is stored to the second memory module.The specific implementation of the step and step S302 are substantially compatible.In this way may be used
Check that the voice of each product wakes up word threshold condition rapidly to realize.
Step S504: inquiry instruction condition is obtained according to third user instruction, meets instruction condition from the second memory module
The voice of product wake up word and its initial threshold and be presented to the user.Its specific implementation and step S403 are essentially identical, no
It is to joined the version information parameter of product with place, available more query results more targetedly obtain language
The threshold value of sound wake-up word.
In the preferred embodiment, version management, tool can also be carried out by the first memory module and the second memory module
Body realization, which can be, constructs memory space according to version information, and in this case, the wake-up word and its threshold value of product are also right respectively
Answer corresponding version, the user instruction received at this time i.e. second user instruction in further include product version parameter, and according to
The voice that the instruction at family obtains the product that new project verification wakes up word parameter and storage wakes up word and its test threshold is then realized are as follows: according to
New project verification wakes up word parameter and determines that new project verification wakes up word content and product version parameter, and will newly set up the project and wake up word Content Transformation is pair
The pinyin sequence answered wakes up in word according to pinyin sequence and product version parameter from the voice of the product of the respective version of storage
The reference for allotting identical pinyin sequence wakes up word, and reference threshold is calculated according to the test threshold that reference wakes up word, will refer to
Threshold value wakes up the threshold value output of word as new project verification.Specific implementation can refer to above-mentioned.
It wherein,, can be with after the reference for matching identical pinyin sequence wakes up word in another preferred implementation
It wakes up word to reference according to product characteristic to screen, which can pass through user's manual screening.It is above according to ginseng
Reference threshold is calculated in the test threshold for examining wake-up word, is that the test threshold for waking up word according to the reference after screening is calculated
Reference threshold.In this manner it is ensured that the reference threshold obtained is more accurate.Product characteristic be, for example, firmware model it is different thus nothing
Method is applicable in, and the loudspeaker model difference such as used is too big, and the product of the certain specific models matched is caused not fitted equally
With at this time just by the record deletion of these products, to the record progress mean value calculation after remaining i.e. screening, to guarantee to calculate
If Dun reference threshold accuracy.
In some embodiments, the embodiment of the present invention provides a kind of non-volatile computer readable storage medium storing program for executing, described to deposit
Being stored in storage media one or more includes the programs executed instruction, it is described execute instruction can by electronic equipment (including but
It is not limited to computer, server or the network equipment etc.) it reads and executes, for executing any of the above-described device of the present invention
The method of voice wake-up word threshold value.
In some embodiments, the embodiment of the present invention also provides a kind of computer program product, and the computer program produces
Product include the computer program being stored on non-volatile computer readable storage medium storing program for executing, and the computer program includes that program refers to
It enables, when described program instruction is computer-executed, so that the computer is executed any of the above-described device voice and wake up word threshold value
Method.
In some embodiments, the embodiment of the present invention also provides a kind of electronic equipment comprising: at least one processor,
And the memory being connect at least one described processor communication, wherein the memory is stored with can be by described at least one
The instruction that a processor executes, described instruction is executed by least one described processor, so that at least one described processor energy
The method that enough executive device voices wake up word threshold value.
In some embodiments, the embodiment of the present invention also provides a kind of storage medium, is stored thereon with computer program,
It is characterized in that, the method that device voice wakes up word threshold value when which is executed by processor.
The voice of the embodiments of the present invention, which wakes up word threshold management device, can be used for executing the management of the embodiment of the present invention
The method that voice wakes up word threshold value, and the realization management voice for reaching the embodiments of the present invention accordingly wakes up the side of word threshold value
Method technical effect achieved, which is not described herein again.Hardware processor (hardware can be passed through in the embodiment of the present invention
Processor) Lai Shixian related function module.
Fig. 6 is the hard of the electronic equipment that the execution management voice provided for one embodiment of the invention wakes up the method for word threshold value
Part structural schematic diagram, as shown in fig. 6, the equipment includes:
One or more processors 610 and memory 620, in Fig. 6 by taking a processor 610 as an example.
The equipment that executive device voice wakes up the method for word threshold value can also include: input unit 630 and output device
640。
Processor 610, memory 620, input unit 630 and output device 640 can pass through bus or other modes
It connects, in Fig. 6 for being connected by bus.
Memory 620 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module, as the device voice in the embodiment of the present application wakes up the side of word threshold value
Corresponding program instruction/the module of method.Processor 610 is by running the non-volatile software program being stored in memory 620, referring to
Order and module, thereby executing the various function application and data processing of server, i.e. realization above method embodiment device
The method of voice wake-up word threshold value.
Memory 620 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；Storage data area can be stored to be created according to using for phonetic controller
Data etc..In addition, memory 620 may include high-speed random access memory, it can also include nonvolatile memory, example
Such as at least one disk memory, flush memory device or other non-volatile solid state memory parts.In some embodiments, it deposits
Optional reservoir 620 includes the memory remotely located relative to processor 610, these remote memories can pass through network connection
Word threshold management device is waken up to voice.The example of above-mentioned network include but is not limited to internet, intranet, local area network,
Mobile radio communication and combinations thereof.
Input unit 630 can receive the number or character information of input, and generates and wake up word threshold management dress with voice
The related signal of user setting and function control set.Output device 640 may include that display screen etc. shows equipment.
One or more of modules are stored in the memory 620, when by one or more of processors
When 610 execution, the method that the device voice in above-mentioned any means embodiment wakes up word threshold value is executed.
Method provided by the embodiment of the present application can be performed in the said goods, has the corresponding functional module of execution method and has
Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present application.
The electronic equipment of the embodiment of the present application exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment include: audio,
Video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other electronic devices with data interaction function.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.
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.
Claims (13)
1. voice wakes up word threshold management device, comprising:
First memory module, the voice for storing product wake up word and its test threshold；
Threshold value distribution module wakes up word parameter for receiving new project verification, wakes up word parameter and the first memory module according to new project verification
The voice of the product of middle storage wakes up word and its test threshold, wakes up word assigned references threshold value for new project verification.
2. the apparatus according to claim 1, which is characterized in that further include:
Product threshold management module, for the user instruction in response to receiving, by the voice of the product received wake up word and
The voice that its test threshold stored to the first memory module or obtained from the first memory module the product for meeting instruction condition is called out
Awake word and its test threshold are presented to the user.
3. the apparatus of claim 2, which is characterized in that further include
Initial threshold management module, for the user instruction in response to receiving, by the voice of the product received wake up word and
The voice that the storage of its initial threshold or acquisition meet the product of instruction condition wakes up word and its initial threshold is presented to the user.
4. device according to claim 3, wherein described device further include:
Version management module, for configuring and the memory space of the matches version information of product；
The product threshold management module is also used to the Release parameter according to user instructions, and the voice of the product received is called out
Awake word and its test threshold are stored to corresponding memory space；
The initial threshold management module is also used to the Release parameter according to user instructions, and the voice of the product received is called out
Awake word and its initial threshold are stored to corresponding memory space.
5. a kind of method that management voice wakes up word threshold value characterized by comprising
Configure the first memory module；
The first user instruction is received, word is waken up according to the voice that the first user instruction obtains the product of input and its test threshold is deposited
It stores up to the first memory module；
Second user instruction is received, new project verification is obtained according to second user instruction and wakes up word parameter；
Word and its test threshold are waken up according to the voice that new project verification wakes up the product of word parameter and storage, wakes up word point for new project verification
With reference threshold.
6. according to the method described in claim 5, it is characterized in that, the basis, which is newly set up the project, wakes up the product of word parameter and storage
Voice wake up word and its test threshold, waking up word assigned references threshold value for new project verification includes:
Word parameter, which is waken up, according to new project verification determines that new project verification wakes up word content；
To newly set up the project and wake up word Content Transformation is corresponding pinyin sequence:
The reference wake-up word that identical pinyin sequence is matched in word is waken up from the voice of the product of storage according to pinyin sequence；
Reference threshold is calculated according to the test threshold that reference wakes up word, the threshold value of word is waken up using reference threshold as new project verification
Output.
7. method according to claim 5 or 6, which is characterized in that further include:
Configure the second memory module；
Third user instruction is received, word is waken up according to the voice that third user instruction obtains the product of input and its initial threshold is deposited
It stores up to the second memory module.
8. the method according to the description of claim 7 is characterized in that further include:
Inquiry instruction condition is obtained according to the first user instruction, the voice for meeting the product of instruction condition from the first memory module is called out
Awake word and its test threshold are presented to the user；Or/and
Inquiry instruction condition is obtained according to third user instruction, the voice for meeting the product of instruction condition from the second memory module is called out
Awake word and its initial threshold are presented to the user.
9. according to the method described in claim 5, it is characterized in that, further including
The first memory module and/or the second memory module are configured according to the version information of product；
When receiving the first user instruction and/or third user instruction, according to the first user instruction and/or third user instruction
The voice of product is waken up word according to Release parameter and its threshold value is stored to respective stored by the Release parameter for obtaining the product of input
The corresponding position of module.
10. according to the method described in claim 9, it is characterized in that, the basis, which is newly set up the project, wakes up the production of word parameter and storage
The voice of product wakes up word and its test threshold, wakes up word assigned references threshold value for new project verification and includes:
Word parameter, which is waken up, according to new project verification determines that new project verification wakes up word content and product version parameter；
To newly set up the project and wake up word Content Transformation is corresponding pinyin sequence:
It is matched from the voice wake-up word of the product of the respective version of storage according to pinyin sequence and product version parameter identical
The reference of pinyin sequence wakes up word；
Reference threshold is calculated according to the test threshold that reference wakes up word, the threshold value of word is waken up using reference threshold as new project verification
Output.
11. according to the method described in claim 10, it is characterized in that, match identical pinyin sequence reference wake up word it
Afterwards, word is waken up to reference also according to product characteristic to screen,
Reference threshold is calculated in the test threshold for waking up word according to reference, is the survey that word is waken up according to the reference after screening
Examination threshold calculations obtain reference threshold.
12. a kind of electronic equipment comprising: at least one processor, and connect at least one described processor communication
Memory, wherein the memory be stored with can by least one described processor execute instruction, described instruction by it is described extremely
A few processor executes, so that at least one described processor is able to carry out any one of claim 5-11 the method
The step of.
13. a kind of storage medium, is stored thereon with computer program, which is characterized in that the realization when program is executed by processor
The step of any one of claim 5-11 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811591702.6A CN109741755B (en) | 2018-12-25 | 2018-12-25 | Voice awakening word threshold management device and method for managing voice awakening word threshold |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811591702.6A CN109741755B (en) | 2018-12-25 | 2018-12-25 | Voice awakening word threshold management device and method for managing voice awakening word threshold |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109741755A true CN109741755A (en) | 2019-05-10 |
| CN109741755B CN109741755B (en) | 2021-04-16 |
Family
ID=66359831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811591702.6A Active CN109741755B (en) | 2018-12-25 | 2018-12-25 | Voice awakening word threshold management device and method for managing voice awakening word threshold |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109741755B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10827028B1 (en) | 2019-09-05 | 2020-11-03 | Spotify Ab | Systems and methods for playing media content on a target device |
| CN112397060A (en) * | 2019-07-31 | 2021-02-23 | 北京声智科技有限公司 | Voice instruction processing method, system, device and medium |
| CN112863545A (en) * | 2021-01-13 | 2021-05-28 | 北京字节跳动网络技术有限公司 | Performance test method and device, electronic equipment and computer readable storage medium |
| US11094319B2 (en) | 2019-08-30 | 2021-08-17 | Spotify Ab | Systems and methods for generating a cleaned version of ambient sound |
| CN113488050A (en) * | 2021-07-09 | 2021-10-08 | 北京有竹居网络技术有限公司 | Voice awakening method and device, storage medium and electronic equipment |
| US11308959B2 (en) | 2020-02-11 | 2022-04-19 | Spotify Ab | Dynamic adjustment of wake word acceptance tolerance thresholds in voice-controlled devices |
| US11328722B2 (en) | 2020-02-11 | 2022-05-10 | Spotify Ab | Systems and methods for generating a singular voice audio stream |
| CN115376524A (en) * | 2022-07-15 | 2022-11-22 | 荣耀终端有限公司 | Voice awakening method, electronic equipment and chip system |
| CN116030817A (en) * | 2022-07-18 | 2023-04-28 | 荣耀终端有限公司 | Voice wakeup method, equipment and storage medium |
| US11822601B2 (en) | 2019-03-15 | 2023-11-21 | Spotify Ab | Ensemble-based data comparison |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02300800A (en) * | 1989-05-15 | 1990-12-12 | Ricoh Co Ltd | Speech recognition device |
| CN103678675A (en) * | 2013-12-25 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Method, server and system for achieving searching through Pinyin |
| CN104899491A (en) * | 2015-05-28 | 2015-09-09 | 广东欧珀移动通信有限公司 | Data transfer method and apparatus thereof |
| WO2017180087A1 (en) * | 2016-04-11 | 2017-10-19 | Hewlett-Packard Development Company, L.P. | Waking computing devices based on ambient noise |
| CN206990122U (en) * | 2017-05-26 | 2018-02-09 | 上海展扬通信技术有限公司 | Protection system and communication terminal for communication terminal |
-
2018
- 2018-12-25 CN CN201811591702.6A patent/CN109741755B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02300800A (en) * | 1989-05-15 | 1990-12-12 | Ricoh Co Ltd | Speech recognition device |
| CN103678675A (en) * | 2013-12-25 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Method, server and system for achieving searching through Pinyin |
| CN104899491A (en) * | 2015-05-28 | 2015-09-09 | 广东欧珀移动通信有限公司 | Data transfer method and apparatus thereof |
| WO2017180087A1 (en) * | 2016-04-11 | 2017-10-19 | Hewlett-Packard Development Company, L.P. | Waking computing devices based on ambient noise |
| CN206990122U (en) * | 2017-05-26 | 2018-02-09 | 上海展扬通信技术有限公司 | Protection system and communication terminal for communication terminal |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11822601B2 (en) | 2019-03-15 | 2023-11-21 | Spotify Ab | Ensemble-based data comparison |
| CN112397060A (en) * | 2019-07-31 | 2021-02-23 | 北京声智科技有限公司 | Voice instruction processing method, system, device and medium |
| CN112397060B (en) * | 2019-07-31 | 2024-02-23 | 北京声智科技有限公司 | Voice instruction processing method, system, equipment and medium |
| US11551678B2 (en) | 2019-08-30 | 2023-01-10 | Spotify Ab | Systems and methods for generating a cleaned version of ambient sound |
| US11094319B2 (en) | 2019-08-30 | 2021-08-17 | Spotify Ab | Systems and methods for generating a cleaned version of ambient sound |
| US10827028B1 (en) | 2019-09-05 | 2020-11-03 | Spotify Ab | Systems and methods for playing media content on a target device |
| US11810564B2 (en) | 2020-02-11 | 2023-11-07 | Spotify Ab | Dynamic adjustment of wake word acceptance tolerance thresholds in voice-controlled devices |
| US11328722B2 (en) | 2020-02-11 | 2022-05-10 | Spotify Ab | Systems and methods for generating a singular voice audio stream |
| US11308959B2 (en) | 2020-02-11 | 2022-04-19 | Spotify Ab | Dynamic adjustment of wake word acceptance tolerance thresholds in voice-controlled devices |
| CN112863545B (en) * | 2021-01-13 | 2023-10-03 | 抖音视界有限公司 | Performance test method, device, electronic equipment and computer readable storage medium |
| CN112863545A (en) * | 2021-01-13 | 2021-05-28 | 北京字节跳动网络技术有限公司 | Performance test method and device, electronic equipment and computer readable storage medium |
| CN113488050A (en) * | 2021-07-09 | 2021-10-08 | 北京有竹居网络技术有限公司 | Voice awakening method and device, storage medium and electronic equipment |
| CN113488050B (en) * | 2021-07-09 | 2024-03-26 | 北京有竹居网络技术有限公司 | Voice wakeup method and device, storage medium and electronic equipment |
| CN115376524A (en) * | 2022-07-15 | 2022-11-22 | 荣耀终端有限公司 | Voice awakening method, electronic equipment and chip system |
| CN116030817A (en) * | 2022-07-18 | 2023-04-28 | 荣耀终端有限公司 | Voice wakeup method, equipment and storage medium |
| CN116030817B (en) * | 2022-07-18 | 2023-09-19 | 荣耀终端有限公司 | Voice wakeup method, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109741755B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741755A (en) | Voice wakes up word threshold management device and manages the method that voice wakes up word threshold value | |
| US11295035B2 (en) | Application freezing management method, device and terminal | |
| US10284705B2 (en) | Method and apparatus for controlling smart device, and computer storage medium | |
| CN108319599A (en) | A kind of interactive method and apparatus | |
| CN109844855A (en) | The multiple calculating of task, which is acted on behalf of, to be executed | |
| CN107766891B (en) | User gender identification method and device, storage medium and electronic equipment | |
| WO2018006472A1 (en) | Knowledge graph-based human-robot interaction method and system | |
| CN106384591A (en) | Method and device for interacting with voice assistant application | |
| US11514368B2 (en) | Methods, apparatuses, and computing devices for trainings of learning models | |
| CN103577207A (en) | Loading method and loading device for interface components in custom interface system | |
| CN109101216A (en) | Audio method of adjustment, device, electronic equipment and storage medium | |
| JP2019120935A (en) | Method for providing service using plural wake word in artificial intelligence device and system thereof | |
| EP3799036A1 (en) | Speech control method, speech control device, electronic device, and readable storage medium | |
| CN110019729A (en) | Intelligent answer method and storage medium, terminal | |
| CN110019728A (en) | Automatic interaction method and storage medium, terminal | |
| US20170161928A1 (en) | Method and Electronic Device for Displaying Virtual Device Image | |
| WO2017107531A1 (en) | Volume adjustment method and terminal device | |
| US20230028830A1 (en) | Robot response method, apparatus, device and storage medium | |
| CN108650248A (en) | A kind of intention value-added system based on block chain Yu AR visualization techniques | |
| CN108648142A (en) | Image processing method and device | |
| CN105335466A (en) | Audio data retrieval method and apparatus | |
| US20170188214A1 (en) | Method and electronic device for sharing multimedia information | |
| US20210098012A1 (en) | Voice Skill Recommendation Method, Apparatus, Device and Storage Medium | |
| CN110600021A (en) | Outdoor intelligent voice interaction method, device and system | |
| CN106204207A (en) | A kind of bill generates method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: Sipic Technology Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee before: AI SPEECH Ltd. |
|
| CP01 | Change in the name or title of a patent holder |