CN107527615A - Information processing method, device, equipment, system and server - Google Patents
Information processing method, device, equipment, system and server Download PDFInfo
- Publication number
- CN107527615A CN107527615A CN201710823091.2A CN201710823091A CN107527615A CN 107527615 A CN107527615 A CN 107527615A CN 201710823091 A CN201710823091 A CN 201710823091A CN 107527615 A CN107527615 A CN 107527615A
- Authority
- CN
- China
- Prior art keywords
- intelligent sound
- sound box
- noise reduction
- voice signal
- signal
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0316—Speech enhancement, e.g. noise reduction or echo cancellation by changing the amplitude
- G10L21/0364—Speech enhancement, e.g. noise reduction or echo cancellation by changing the amplitude for improving intelligibility
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- User Interface Of Digital Computer (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
This application provides a kind of information processing method, device, equipment, system and server, after effective voice signal of scene where intelligent sound box collects, the application will utilize the parameter of the space model of the scene, noise reduction process is carried out to effective voice signal, substantially increase noise reduction, guarantee intelligent sound box can be accurate from effective voice signal and quickly recognizes target sound signal, so as to respond the target sound signal, performs predetermined registration operation.It can be seen that the phonetic order that user sends can be also recognized accurately away from intelligent sound box, intelligent sound box in user in the application, the reliability and control efficiency of Voice command are improved.
Description
Technical field
Present application relates generally to smart home application field, more particularly to a kind of information processing method, device,
Equipment, system and server.
Background technology
With the development of Internet technology, product of the smart home as Internet of Things, it is using house as platform, utilizes synthesis
Wiring technique, the network communications technology, security precautions technology, automatic control technology, audio frequency and video technology etc., life staying idle at home is relevant
Facility (such as audio & video equipment, illuminator, airconditioning control, safety-protection system, video server, network home appliance) is connected to one
Rise, build the management system of efficient housing facilities and family's schedule affairs, make smart home that not only there is traditional inhabitation work(
Can, have both building, network service, information household appliances, equipment automatization, there is provided comprehensive information exchange function, improve household
Security, convenience, comfortableness, artistry, and realize the living environment of environmental protection and energy saving.
In actual applications, it will usually which multiple intelligent sound boxes are set, so that user is surfed the Net by voice, as program request is sung
Bent, online shopping;Or intelligent home device is controlled, such as open curtain, refrigerator temperature is set, without for each
Remote control corresponding to intelligent home device setting is controlled, very convenient.
However, during the use of intelligent sound box, generally require user and send language in intelligent sound box certain limit
Sound instructs, and intelligent sound box could be recognized accurately user and send from the voice signal comprising environmental sound signal collected
Phonetic order, once exceeding the scope, will be unable to that the phonetic order that user sends is recognized accurately, greatly reduce voice control
The reliability and control efficiency of system.
The content of the invention
In view of this, the invention provides a kind of information processing method, device, equipment, system and server, bonding apparatus
The parameter of the space model of place scene, to the noise reduction process of the effective voice signal collected under the scene, improve
Noise reduction, it ensure that the promptness and accuracy for controlling controlled device to act by voice mode.
In order to realize foregoing invention purpose, this application provides following technical scheme:
A kind of information processing method, methods described include:
Effective voice signal of scene where gathering intelligent sound box;
Using the parameter of the space model of the scene received, the effectively voice signal is carried out at noise reduction
Reason, identify the target sound signal that effectively voice signal includes;
The target sound signal is responded, controls the intelligent sound box to perform predetermined registration operation.
Preferably, methods described also includes:
It is determined that None- identified goes out target sound signal from the effectively voice signal, prompt message, the prompting are exported
Information is used for instruction user and adjusts the intelligent sound box in the locus of the scene.
Preferably, the response target sound signal, controls the intelligent sound box to perform predetermined registration operation, including:
The target sound signal is analyzed, determines controlled device and control instruction, and triggers described controlled pair
As responding the control instruction.
A kind of information processing method, methods described include:
The space model of the place scene of electronic equipment structure is received, determines multiple intelligent sound boxes in the building
At least one of spatial model is laid out;
Obtain effective voice signal that any one intelligent sound box under various layouts collects under this scenario;
Using the parameter of the space model, noise reduction process is carried out to the effectively voice signal;
Based on noise reduction process result, determine at least one target layout of the multiple intelligent sound box, and will described at least
A kind of target layout sends to the electronic equipment and exported.
Preferably, methods described also includes:
Obtain the audio signal that any one intelligent sound box exports under various layouts;
Using the parameter of the space model, the audio information of the audio signal is obtained;
It is described to be based on noise reduction process result, at least one target layout of the multiple intelligent sound box is determined, including:
Using the comparing result of noise reduction process result and multiple audio information of acquisition, the multiple intelligent sound box is determined
At least one target layout.
A kind of information processor, described device include:
Sound acquisition module, effective voice signal for scene where gathering intelligent sound box;
Noise reduction process module, for the parameter of the space model using the scene received, to described effective
Voice signal carries out noise reduction process, identifies the target sound signal that effectively voice signal includes;
Control module, for responding the target sound signal, the intelligent sound box is controlled to perform predetermined registration operation.
A kind of information processor, described device include:
First determining module, the space model of the place scene for receiving electronic equipment structure, is determined multiple
Intelligent sound box is laid out at least one of described space model;
First obtains module, has for obtain that any one intelligent sound box under various layouts collects under this scenario
Imitate voice signal;
Noise reduction process module, for the parameter using the space model, the effectively voice signal is dropped
Make an uproar processing;
Second determining module, for based on noise reduction process result, determining at least one target of the multiple intelligent sound box
Layout;
Data transmission module, exported at least one target layout to be sent to the electronic equipment.
A kind of message processing device, the equipment include:
Communication module;
Sound collector, effective voice signal for scene where gathering;
Memory, program as described above is realized for storing;
Processor, for loading and performing described program, including:
Using the parameter of the space model of the scene received, the sound collector is collected effective
Voice signal carries out noise reduction process, identifies the target sound signal that effectively voice signal includes;
The target sound signal is responded, performs predetermined registration operation.
A kind of server, the server include:
Communication module;
Memory, for storing the program of information processing method as described above;
Processor, for loading and performing described program, including:
The space model of the place scene of electronic equipment structure is received, determines multiple intelligent sound boxes in the building
At least one of spatial model is laid out;
Obtain effective voice signal that any one intelligent sound box under various layouts collects under this scenario;
Using the parameter of the space model, noise reduction process is carried out to the effectively voice signal;
Based on noise reduction process result, at least one target layout of the multiple intelligent sound box is determined, and is led to by described
At least one target layout is sent to the electronic equipment and exported by letter module.
A kind of information processing system, the system include:Server, electronic equipment and at least one intelligent sound box, its
In:
The electronic equipment, for building the space model of place scene, determine the ginseng of the space model
Number;
The intelligent sound box is above- mentioned information processing equipment;
The server is above-mentioned server.
As can be seen here, compared with prior art, this application provides a kind of information processing method, device, equipment, system and
Server, after intelligent sound box collects effective voice signal of place scene, the application will utilize the space of the scene
The parameter of model, noise reduction process is carried out to effective voice signal, the target sound that effective voice signal includes is recognized accurately
Signal, so as to respond the target sound signal, meet to be actually needed, such as control intelligent sound box to play audio-frequency information, or control it
He performs predetermined registration operation etc. by intelligent home device.It can be seen that when the application carries out noise reduction process to effective voice signal, it is known that when
The influence that noise signal and space in preceding scene are propagated voice signal, even if user sends language away from intelligent sound box
Sound signal, it can also ensure intelligent sound box accurately from the effective voice signal for including the voice signal and environmental sound signal
In, the voice signal that target sound signal such as user sends is recognized accurately, improves reliability and the control of Voice command
Efficiency.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of flow chart for information processing method that the embodiment of the present application provides;
Fig. 2 is a kind of space model schematic that the embodiment of the present application provides;
Fig. 3 is the flow chart for another information processing method that the embodiment of the present application provides;
Fig. 4 is the flow chart for another information processing method that the embodiment of the present application provides;
Fig. 5 is arrangement schematic diagram of the intelligent sound box of the embodiment of the present application offer in space model;
Fig. 6 is a kind of signaling process figure for information processing method that the embodiment of the present application provides;
Fig. 7 is a kind of structure chart for information processor that the embodiment of the present application provides;
Fig. 8 is the structure chart for another information processor that the embodiment of the present application provides;
Fig. 9 is the structure chart for another information processor that the embodiment of the present application provides;
Figure 10 is the structure chart for another information processor that the embodiment of the present application provides;
Figure 11 is a kind of hardware structure diagram for message processing device that the embodiment of the present application provides;
Figure 12 is a kind of hardware structure diagram for server that the embodiment of the present application provides;
Figure 13 is a kind of structure chart for information processing system that the embodiment of the present application provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
With the fast development of smart home, increasing household starts to quote intellectualizing system and equipment, to people
Daily life, work, amusement etc. bring convenience.In actual applications, user refers to typically by voice or control
The modes such as order, corresponding intelligent home device is triggered into working condition or is stopped, on the other hand, would generally be in inhabitation or work
Multiple intelligent sound boxes are placed in the places such as work, and it can not only have the playing function of traditional audio amplifier, also, can also be used as user
By the instrument of phonetic accessing internet, the control to intelligent home device can also be realized, it is very convenient and practical.
Wherein, during the use of intelligent sound box, typically by the voice signal that sends of collection user, complete corresponding
Operation, and it is determined that behind position of the intelligent sound box in place, will not generally move again, so, when user needs
Start the air-conditioning in parlor, it is necessary near the intelligent sound box placed up to parlor, say corresponding phonetic order, intelligent sound box ability
The phonetic order is accurately responded, starts air-conditioning;If user distance intelligent sound box is distant, due to place scene noise jamming with
And wall is to interference etc. caused by voice signal reflection, diffusion etc., it will reduces the voice that intelligent sound box identification user sends and refers to
The accuracy of order.
In order to improve above mentioned problem, applicant proposes to be combined tango technologies with intelligent sound box, utilizes tango technology structures
The space model in place where building intelligent sound box, it is current to what is collected so as to utilize the parameter of the space model
Effective voice signal of scene carries out noise reduction process, and then ensures intelligent sound box from effective voice signal after noise reduction, accurately
Target sound signal is identified, and responds the target sound signal, controls the intelligent sound box to perform predetermined registration operation, meets user couple
The use demand of intelligent home device.
Moreover, the application can also utilize the space model in the place of structure, diverse location intelligent sound box pair is simulated
The recognition effect of the sound of user's output, it is complete with for reference so as to provide the arrangement of the intelligent sound box in the place
Into the arrangement of multiple intelligent sound boxes in actual place, optimal audio and optimal noise reduction are obtained.
Wherein, tango technologies are a kind of augmented reality (Augmented Reality, abbreviation AR), and it can coordinate
Unique electronic equipment and SDK (Software Development Kit, SDK), easily makes in the application
With AR technologies, it generally has the function of moving tracing, regional learning and the aspect of depth perception three, can specifically pass through movement
Tracking function detects the position and orientation of electronic equipment, improves the degree of accuracy of moving tracing by regional learning, memory space is believed
Cease (doing indoor navigation), modeling is scanned finally by deep learning, the three dimensions mould in place where obtaining electronic equipment
Block, and can be adjusted according to the change of user perspective and action, building process of the application to space model
It is not detailed
In order that the above objects, features and advantages of the present invention can be more obvious understandable, below in conjunction with the accompanying drawings and specifically
The present invention is further detailed explanation for embodiment.
Reference picture 1, a kind of flow chart of the information processing method provided for the embodiment of the present application, the present embodiment is mainly from intelligence
The angle of energy audio amplifier carries out the description of information processing method, and this method may comprise steps of:
Step S101, effective voice signal of scene where collection intelligent sound box;
In the practical application of the embodiment of the present application, the situation of at least one intelligent sound box is provided with current place
Under, when user needs the intelligent home device in the place in certain space to perform certain operation, if desired for starting or stoping the intelligence
Can home equipment, or when adjusting working condition of the intelligent home device etc., user can send accordingly in the space
Phonetic order, it is desirable to the intelligent sound box in the space identifies and responds, and meets that user requires.
Based on this, effective voice signal of scene, effective voice signal can refer to where intelligent sound box can gather it
Intelligent sound box is under current scene, all voice signals that can collect, the human voice signal sent such as user, place environment
Environmental sound signal, the voice signal reflected by wall human voice signal and/or environmental sound signal etc., the application is implemented
The content that effective voice signal that example collects to intelligent sound box includes is not construed as limiting.
Wherein, for the intelligent sound box of same position, in different scenes (such as different periods, different weather, different geographical positions
Put, such as individual stays alone, multiple happilys gather scene) under effective voice signal for collecting can be different, even if under Same Scene,
After the user different from the distance of the intelligent sound box sends human voice signal, effective voice signal that the intelligent sound box collects also may be used
Can be different;In addition, intelligent sound box and send phonetic order customer location it is constant, if the spatial surface material of place scene is not
Together, because different materials are different to dispositions such as acoustic absorption/reflections, it is also possible to the effective sound for causing the intelligent sound box to collect
Sound signal is different, and the application will not enumerate herein.
It should be noted that it is determined that after the position of intelligent sound box and its scene, in the information processing that the present embodiment provides
During, the above-mentioned possibility being related to, which influences the factor that effective voice signal that intelligent sound box collects changes, no longer to be changed
Become, so as to ensure the reliability of the information processing scheme of the embodiment of the present application offer.
Step S102, using the parameter of the space model of the scene received, effective voice signal is carried out
Noise reduction process, identify the target sound signal that effective voice signal includes;
With reference to above-mentioned analysis, the building of scene where the embodiment of the present application can utilize tango technique constructions intelligent sound box
Spatial model, as user open electronic equipment image capture device (such as camera) after, the electronic equipment can be held and passed through
Display screen, each space in place where browsing, using the matching software of the special sensor of electronic equipment outfit, paint
Make the threedimensional model in the place, i.e. space model.The application is not detailed to the method for obtaining space model.
Optionally, the space model of scene where the intelligent sound box obtained for the embodiment of the present application, it can be
The current spatial in place builds where the space model in the whole place where intelligent sound box or the intelligent sound box
Build spatial model.
By taking a house as an example, intelligent sound box can be the house some bedroom in place intelligent sound box, this feelings
Under condition, the space model of acquisition can be the space model in whole house, and the space model can pass through structure
The electronic equipment built is presented, and can be by changing the visual angle of electronic equipment, the space model that adjustment display screen is presented
Three-dimensional image information, it is very convenient and interesting.Certainly, the space model that the present embodiment obtains can also be intelligent sound box
The threedimensional model in place bedroom, as shown in Fig. 2 but and be confined to this, it can be presented on mobile terminals, allow the user to
The more intuitively overall structure in house.
Optionally, after the space model of scene where the application obtains intelligent sound box by mobile terminal, Ke Yizhi
Connect and send its relevant information (such as various parameters of the space model) to corresponding intelligent sound box, or receiving intelligence
Can audio amplifier send acquisition instruction after, then will feedback of the information corresponding with the intelligent sound box to the intelligent sound box, the application is to intelligence
The method for the parameter that energy audio amplifier obtains space model does not limit.
Wherein, the parameter of space model can include bulk, space buildings structure to sound reflection, diffusion,
Related data, the current spatial air such as absorb to sound propagation velocity etc., specifically can according to noise reduction algorithm it needs to be determined that, this
Apply for that the content that includes to the space model parameter is not construed as limiting, can be one in the above-mentioned several parameters enumerated or
It is multiple combination or other, the present embodiment will not enumerate herein.
In the embodiment of the present application, intelligent sound box obtains the effective voice signal for needing identifying processing, and place scene
Space model parameter after, prefabricated noise reduction algorithm can be utilized, it is effective to this with reference to the parameter of space model
Voice signal carries out noise reduction process, so as to which the target sound signal that effective voice signal includes be recognized accurately, i.e., for intelligence
The phonetic order that energy audio amplifier is sent.
Step S103, responds the target sound signal, and control intelligent sound box performs predetermined registration operation.
, can be by dividing the target sound signal after intelligent sound box determines to be directed to its target sound signal
Analysis, determines its corresponding phonetic order, so as to perform the phonetic order, completes predetermined registration operation, i.e., corresponding with the phonetic order
Operation.Such as music instruction, intelligent sound box can be controlled to play the song to prestore or the online broadcasting music of networking etc.;Cooling
Instruction, intelligent sound box can be controlled to send cooling order to air-conditioning associated with it, so as to reduce the temperature of air-conditioning output, drop
Temperature of low current environment etc..
Optionally, in the embodiment of the present application, can according to pre-establish each intelligent sound box and each intelligent home device it
Between incidence relation, that is to say, that can predefine each intelligent sound box can realize control to which intelligent home device
System, so, after intelligent sound box obtains phonetic order, can directly control corresponding intelligence according to the incidence relation pre-established
Can the corresponding operation of home equipment execution.
In actual applications, the application can utilize device identification and function information of each intelligent home device etc., really
Incidence relation between fixed at least one intelligent home device and the intelligent sound box in place space, and determine each intelligent home device
Function type, so, after intelligent sound box obtains phonetic order, could according to the type of the phonetic order, realize pair with should
The control of the intelligent home device with corresponding function of intelligent sound box association.
It should be noted that representation of the application to each intelligent sound box and the incidence relation of each intelligent home device,
And intelligent sound box is not construed as limiting to the transmission means of the information such as intelligent home device transmission control instruction, request.
In summary, in the embodiment of the present application, it is identified to effective voice signal of place scene in intelligent sound box
Before, the parameter of the space model of the scene will be obtained, determine current scene noise signal and space to sound
The influence of signal transmission, noise reduction process is carried out based on these influence factors, then to effective voice signal, improves noise reduction,
So that the target sound signal in effective voice signal can be recognized accurately in intelligent sound box, and then ensure the intelligent sound box
The target sound signal can in time and be accurately responded, controls the intelligent sound box to perform predetermined registration operation, meets user to intelligent family
Occupy the use demand of equipment.
Illustrated herein by taking the bedroom scene shown in Fig. 2 as an example, if intelligent sound box is placed on the table shown in Fig. 2 by user
On son, subscriber station in the bedroom but and not up to beside intelligent sound box, say " turn on TV " this target sound signal, intelligence
Energy audio amplifier will gather effective voice signal comprising the target sound signal, with reference to the ginseng of the space model in the bedroom
Number, noise reduction process is carried out to effective voice signal, so as to by identifying the target sound signal described in user, afterwards, intelligence
Energy audio amplifier can be by being analyzed the target sound signal, and the order of TV is opened in generation, and should by wireless network
Order sends to the TV in bedroom, triggering TV and opened, and afterwards, can also continue request program in this manner, very
It is convenient and interesting.
Intelligent sound box is additionally, since when carrying out noise reduction process, combines the parameter of the space model in bedroom, significantly
The accuracy to target sound signal identification is improved, ensure that intelligent sound box can in time and accurately respond the language of user's output
Sound signal.
Reference picture 3, a kind of flow chart of the information processing method provided for the embodiment of the present application, this method can include:
Step S301, effective voice signal of scene where collection intelligent sound box;
Step S302, the parameter of the space model of scene, right using the parameter of acquisition where obtaining the intelligent sound box
Effective voice signal carries out noise reduction process;
Step S303, it is determined that target sound signal whether is identified from effective voice signal after noise reduction process, if so,
Into step S304, if it is not, performing step S306;
Step S304, the target sound signal is analyzed, determines controlled device and control instruction;
Optionally, with reference to the description of above method embodiment appropriate section, can pre-establish each intelligent home device with
Incidence relation between intelligent sound box, so, by analyzing target sound signal, after determining its content, it may be determined that
What is currently associated with the intelligent sound box responds the intelligent home device of the target sound signal.It can be seen that it is determined that controlled device can
, specifically can be according to target sound to be the intelligent home device or intelligent sound box itself in space residing for intelligent sound box
The content of signal determines that the application is not limited this.
Step S305, the control instruction is sent to controlled device, so that the controlled device responds the control instruction;
In the embodiment of the present application, the parameter of the space model in space is currently located with reference to intelligent sound box, is realized
To the reliable noise reduction of effective voice signal, that is, the noise reduction to effective voice signal is improved, such as user distance intelligent sound box
In the case that remote position sends phonetic order, if ambient noise is larger, traditional noise reduction algorithm is likely to the sound of user
Signal confirms as noise signal, causes intelligent sound box can not obtain target sound signal, and this processing side that the application provides
Case, due to combining the parameter of space model, it can effectively avoid the voice signal of user being mistakenly considered noise signal, from
And ensure that intelligent sound box can be recognized accurately target sound signal.
, can be by analyzing the target sound signal, so as to basis after intelligent sound box obtains target sound signal
Analysis result, controlled device and control instruction are determined, now, if the controlled device is intelligent sound box itself, can utilize should
Control instruction control corresponding device action, such as controls the music player in the intelligent sound box to play the music that prestores, or pass through nothing
Line communication module connects music servers, online to play music etc..
If controlled device is not intelligent sound box, can by wirelessly or non-wirelessly mode, by obtained control instruction send to
Controlled device, after controlled device receives control instruction, the control instruction can be responded and perform response operation.As controlled device is
TV, control instruction are volume adjusting instructions, after the volume adjusting instruction that television reception to intelligent sound box is sent, can be adjusted accordingly
The output volume of whole TV, it is not necessary to remote control adjustment television sound volume is reused, it is very convenient.
It should be noted that the application is to utilizing target sound signal, it is determined that responding controlled pair of the target sound signal
As and control instruction processing method, and the transmission method that control instruction is sent to controlled device do not limit.
Step S306, export prompt message.
In the present embodiment, if target sound signal could not be recognized accurately in intelligent sound box, can export comprising the identification
As a result prompt message, it is used to refer to user and adjusts intelligent sound box in the locus of current scene, afterwards, re-emit identical
Phonetic order, return to step S301, until the intelligent sound box can fast and accurately identify target sound signal.
It can be seen that the application can help user's reasonable Arrangement intelligent sound box each sky in place by this reminding method
Between position, to obtain optimal noise reduction and optimal audio, obtain the optimal placement side of multiple intelligent sound boxes in the place
Case, so in general, user optional position in space where intelligent sound box send phonetic order, and intelligent sound box combines
The parameter of space model, the target sound signal for representing the phonetic order can be accurately identified, substantially increases user's body
Test, the life and work to user bring convenience and enjoyment.
As shown in figure 4, the flow chart of another information processing method provided for the embodiment of the present application, with above-mentioned each implementation
Unlike example, the present embodiment is the information processing method of station in server side description, in the present embodiment, on intelligent sound
The processing method of case is referred to the description of above-described embodiment appropriate section, and the present embodiment will not be described in detail herein.Based on this, this reality
The information processing method for applying example offer may comprise steps of:
Step S401, the space model of the place scene of electronic equipment structure is received, determines multiple intelligent sound boxes
A variety of layouts in the space model;
Wherein, the method on electronic equipment structure space model is referred to retouching for above-described embodiment appropriate section
State, it is not described here in detail for the present embodiment.
Optionally, in this application, different types of space structure can be directed in advance, and corresponding at least one intelligence is set
The layout of energy audio amplifier, the layout at least one intelligent sound box that can be specifically determined by experiment under different spaces structure, but simultaneously
It is not limited to a kind of this implementation.Wherein, different types of space structure can refer to different space structures, and be directed to
Same space structure, if environmental difference where it is larger, the layout of at least one intelligent sound box set to it can be different,
The same building structure being such as located in suburb and downtown area, when determining the layout of intelligent sound box in the house, due to influenceing intelligence
The factor of audio amplifier identification target sound signal accuracy is different, and the layout of the intelligent sound box frequently resulted in is also different.
Based on this, in the embodiment of the present application, server receives the space mould of the place scene of electronic equipment structure
After type, the corresponding relation as above to prestore can be utilized, it is determined that under this space model, at least the one of multiple intelligent sound boxes
Kind layout.
Step S402, obtain effective sound letter that any one intelligent sound box under various layouts collects under the scene
Number;
In the embodiment of the present application, can be every to what is obtained in order to determine the noise reduction of intelligent sound box under various layouts
One layout is verified, that is to say, that according to each layout of determination, multiple intelligent sounds are arranged in space model
After case, it can simulate and send phonetic order for any one intelligent sound box under this layout, and obtain the intelligent sound box and exist
The effective voice signal collected under the scene.
Step S403, using the parameter of the space model, noise reduction process is carried out to effective voice signal;
The effective voice signal collected for any one obtained intelligent sound box under certain scene, it can utilize and build
Parameter of the space module under the scene is built, noise reduction process is carried out to it, so as to improve noise reduction.
Optionally, in the embodiment of the present application, each intelligent sound box under various layouts can be obtained according to the method described above
The effective voice signal collected, and scene when intelligent sound box gathers effective voice signal is directed to, determine space model
Corresponding parameter, complete to effective voice signal.It can be seen that for each layout of above-mentioned determination, multiple intelligence can be obtained
Effective voice signal under the respective scene that energy audio amplifier collects respectively, noise reduction process is being carried out to these effective voice signals
When, the parameter of the space model of institute's foundation can be different, specifically can according to locus where respective intelligent sound box with
And current scene determines, the embodiment of the present application is no longer described in detail one by one herein.
It should be noted that parameter of the application to utilization space model, the space pair as where intelligent sound box
Sound propagation velocity in the reflection parameters and absorption parameter of voice signal, current environment etc., enters to effective voice signal
Capable noise-reduction method does not limit.
Step S404, based on noise reduction process result, determine at least one target layout of multiple intelligent sound boxes;
Optionally, in the embodiment of the present application, the noise reduction process result in step S404 can refer under each layout, more
Individual intelligent sound box can also refer to based on this multiple effective sound to the noise reduction process result of the effective voice signal each collected
The noise reduction process result of signal, obtained overall noise reduction, i.e., noise reduction corresponding to each layout, the application is to herein
The content that includes of noise reduction process result be not construed as limiting.
In actual applications, the noise reduction standard for meeting to require, so, the drop in the case where obtaining various layouts can be preset
After result of making an uproar, it can determine whether the layout meets noise reduction requirement, if full by being contrasted with default noise reduction standard
Can be to regard this layout as a kind of target layout;Conversely, no longer multiple intelligent sound boxes will be entered using this layout type
Row arrangement.
, can be with it should be noted that the application is that the content of noise reduction requirement is not construed as limiting to the noise reduction standard for meeting to require
Requirement etc. for different places, different scenes, different places purposes, different user determines that the application will not be described in detail herein.
Step S405, at least one target layout of determination is sent to electronic equipment and exported.
In the present embodiment, due to the target layout according to above-mentioned determination, this multiple intelligent sound box, energy are set in the place
Enough make this multiple intelligent sound box that there is preferable audio and noise reduction, refer to so that each intelligent sound box accurately identifies voice
Order, completes the Voice command to intelligent home device.So server is directed to the place that needs to arrange intelligent sound box and its current
Scene, it is determined that after at least one target layout, at least one target layout can be sent to electronic equipment and exported, for
Family refers to.
Now, user can therefrom select a kind of layout type liked, and arrange this multiple intelligent sound box;It can also refer to
At least one target layout of offer, determine that a kind of new layout type is arranged to multiple intelligent sound boxes, the application is to this
Do not limit.
Wherein, the target layout provided for user's reference server, situation about being arranged using new layout, user
It can be drilled in the space model that electronic equipment is presented, that is to say, that user can be according to new layout, in electricity
Each intelligent sound box is arranged in the space model that sub- equipment is presented, can also be to can be visually seen the effect of this layout
The arrangement of each intelligent sound box is adjusted in the space model, to determine to meet the layout that user requires.
For example, electronic equipment structure space model can be as shown in Figure 5 3-D view, in the graphics
As in, user can choose any object to move by touching, and to adjust the layout in whole space, meet user to room
The arrangement requirement in room.Based on this, server is directed to multiple intelligent sound boxes of the space model extremely to electronic equipment feedback
After a few target layout, user selects any one target layout, and electronic equipment can be by the way of as shown in Figure 5, will
The effect of this target layout shows, so that user can be visually seen entirety of this target layout in whole building space
Effect.During this period, user can be looked into by adjusting the viewing visual angle of space model into each room in whole house
Layout effect is seen, at the same time, user can like according to itself, the position of the intelligent sound box in each room be adjusted, such as Fig. 5 institutes
Show, user can drag intelligent sound box to the optional position in place space until satisfied with hand.It should be noted that on to building
The method of adjustment for building multiple intelligent sound boxes in spatial model is not limited to mode shown in Fig. 5.
Optionally, can be according to this layout after user is laid out the layout that effect determines space use by outward appearance
Mode is arranged to real space, afterwards, is sent phonetic order for the intelligent sound box in each room, is verified this layout type
Audio and noise reduction, the information process of intelligent sound box is referred to above-mentioned Fig. 1 and Fig. 3 pairs in specific verification process
The description for the embodiment answered, the present embodiment will not be repeated here.
By above-mentioned checking, if the intelligent sound box in certain room is to results such as the response speed of phonetic order and audios
It is unsatisfactory for, can suitably adjusts the position of intelligent sound box or using aforesaid way adjustment layout;If satisfied, it can continue to experience
The control effect of the intelligent sound box in other rooms, so that the layout in the house can either meet user's requirement from outward appearance, again
The requirement of user can be met from Voice command effect.
As another embodiment of the application, because user is in space walk process, the building of electronic equipment presentation
It is synchronous that the 3-D view of spatial model can arrive space actual scene with user, and the actual viewing visual angle of user and electronic equipment
The visual angle of the 3-D view of presentation can also be synchronous, and therefore, user adjusts intelligent sound on space model as shown in Figure 5
After the layout of case, phonetic order can be directly sent, effective voice signal of scene as residing for gathering electronic equipment, so as to simulate
The intelligent sound box of place space arrangement is to the noise reduction process result of effective voice signal, if in time and can be recognized accurately
Target sound signal, completes the Voice command to controlled device desired by user, and then according to the analog result of electronic equipment, really
Whether the layout of the intelligent sound box in the fixed space is reasonable.
Certainly, can be by this cloth after user adjusts the layout of intelligent sound box on space model as shown in Figure 5
Office is sent to server, and simplation verification is carried out according to the method described above by server, and the result is fed back into electronic equipment, is had
Body process the present embodiment will not be described in detail herein.
With reference to aforesaid way, this application provides a kind of preferred embodiment of information processing method, but this is not limited to
The implementation method of embodiment description, the signaling process figure of the information processing method shown in reference picture 6, can include:
Step S601, the space model of scene where electronic equipment structure;
In the embodiment of the present application, electronic equipment can utilize the space mould of its place scene of tango technique constructions
Type, the related content on tango technologies and space model are referred to the description of above-described embodiment appropriate section, this
It is not described here in detail for embodiment.
Wherein, building structure, surrounding environment (such as air in place space can be included on the scene residing for electronic equipment
Environment, location, whether clamour etc.), present period (morning, noon, afternoon, night, various seasons or red-letter day etc.) etc., this
Apply being not construed as limiting the implication that the scene represents.
Step S601, electronic equipment send the space model and its parameter to server;
Step S602, server determine that multiple intelligent sound boxes are laid out at least one of the space model;
It should be noted that the process for determining at least one layout corresponding to space model on server can join
According to the description of above method embodiment appropriate section, the present embodiment will not be described here.
Step S603, server obtain effective sound that any one intelligent sound box collects under the scene under various layouts
Sound signal and the audio signal of output;
In the embodiment of the present application, server can be simulated in each layout, each intelligent sound box under required scene,
For identical voice signal, effective voice signal that intelligent sound box collects is obtained, and the intelligent sound box is under the scene,
The audio signal exported by identical configuration parameter.The application is not detailed to the analogy method of server.
Optionally, in order to ensure the reliability of target layout that server provides, the application can also be above-mentioned according to determining
At least one layout is arranged to multiple intelligent sound boxes, effective voice signal that each intelligent sound box is collected and its output
Audio-frequency information is sent to server, so that server carries out subsequent authentication.
Step S604, the parameter of server by utilizing space model, the effective sound letter collected to each intelligent sound box
Number noise reduction process is carried out, and obtain the audio information of the audio signal of each intelligent sound box output;
The embodiment of the present application is utilized to noise reduction algorithm as built to the reflection parameters of voice signal, absorption parameter, and/or working as
Preceding air is not limited the noise reduction process method of effective voice signal the parameter of the space model such as sound propagation velocity
It is fixed.
, can be empty in the building by simulating each intelligent sound box for the audio information of the audio signal of intelligent sound box output
Between the situation of playing audio signal of model determine, audio can also be played in actual space by intelligent sound box and is believed
Number, detection obtains corresponding audio information, acquisition methods of the application to the audio information of each intelligent sound box playing audio signal
Do not limit.Wherein, the audio information can include the data such as pitch, loudness of a sound, the duration of a sound, tone color, but be not limited thereto.
The comparing result of multiple audio information of step S605, server by utilizing noise reduction process result and acquisition, it is determined that
This multiple intelligent sound box is at least one of space model target layout;
In the present embodiment practical application, it is determined that intelligent sound box arrangement when, be generally desirable to arrangement after intelligent sound box
In time and the target sound signal for controlled device can be accurately identified, and enable intelligent sound box that there is optimal audio amplifier,
So the application can select at least one target layout based on this 2 points from a variety of layouts initially determined that, as this two
The proportion of aspect, user preferences can be based on and adjusted, the application is not limited this.
It can be seen that for same building space, when different user arranges multiple intelligent sound boxes wherein, server finally determines
At least one target layout may be different.
Step S606, server send at least one target layout of determination to electronic equipment;
Step S607, electronic equipment detect the instruction for any one target layout, are working as according to the target layout
Multiple intelligent sound boxes are arranged in the space model of preceding presentation.
In the embodiment of the present application, after electronic equipment receives at least one target layout of server feedback, Yong Huke
To select one by one, the effect of each target layout is checked, i.e., is arranged according to each target layout in space model
Multiple intelligent sound boxes, so that user can be visually seen the arrangement effect of each target layout scheme, and then select a kind of target layout side
Case or with reference at least one target layout scheme, completes the arrangement to multiple intelligent sound boxes of actual space.
Wherein, because server it is determined that during target layout, is being parameter simulation intelligence with reference to space model
Audio amplifier is to the noise reduction process process of effective voice signal, so as to ensure that the sound of each intelligent sound box under the target layout determined
Effect.
Optionally, the space model that user can be presented according to electronic equipment, increases in the space model
Or intelligent sound box is deleted, or the position of the existing intelligent sound box of adjustment, electronic equipment detect that these operations of user (detect this
The quantity of intelligent sound box in scene and/or position change) after, corresponding fresh information can be generated, afterwards, by this more
Fresh information is sent to server, so that the parameter of server by utilizing fresh information adjustment space model, so as to improve it
It is determined that accuracy during target layout scheme.
To sum up, in the embodiment of the present application, either server is in the space model for determination, it is determined that wherein more
During the target layout of individual intelligent sound box, or the arrangement in the multiple intelligent sound boxes of completion, realized by intelligent sound box to intelligent family
In the Voice command application for occupying equipment, noise reduction is carried out to obtained effective voice signal comprising phonetic order and noise signal
During processing, the application will combine the parameter of space model under current scene, and noise reduction process is carried out to effective voice signal,
Noise reduction is substantially increased, so as to ensure accurate and identify the target sound signal that effective voice signal includes in time, is obtained
To corresponding phonetic order, control controlled device performs respective operations.
Reference picture 7, a kind of structure chart of the information processor provided for the embodiment of the present application, the in the present embodiment dress
Put and can apply to intelligent sound box, can specifically include:
Sound acquisition module 71, effective voice signal for scene where gathering intelligent sound box;
Noise reduction process module 72, for the parameter of the space model using the scene received, have to described
Imitate voice signal and carry out noise reduction process, identify the target sound signal that effectively voice signal includes;
Wherein, the parameter of space model can include bulk, space buildings to sound reflection, diffusion, absorption
Etc. related data, current spatial air to sound propagation velocity etc..
Optionally, as shown in figure 8, the device can also include:
Reminding module 74, for determining that None- identified goes out target sound signal from the effectively voice signal, output carries
Show information;
Wherein, the prompt message is used for the instruction user adjustment intelligent sound box in the locus of the scene, this Shen
Please the way of output to the prompt message and comprising content be not construed as limiting, can such as be exported by voice mode, can also
Directly export buzzer etc..
Control module 73, for responding the target sound signal, the intelligent sound box is controlled to perform predetermined registration operation.
Optionally, as shown in figure 8, the control module 73 can include:
Analytic unit 731, for analyzing the target sound signal, determine controlled device and control instruction;
Data transmission unit 732, for the control instruction to be sent to controlled device, trigger the controlled device response institute
Control instruction is stated, performs predetermined registration operation.
It should be noted that the function implementation process on above-mentioned each module/unit in the present apparatus, is referred to above-mentioned side
The description of method embodiment appropriate section, the present embodiment will not be described in detail herein.
To sum up, in the embodiment of the present application, after effective voice signal of scene where collecting intelligent sound box, it will utilize
The parameter of the space model of the scene, noise reduction process is carried out to effective voice signal, improves noise reduction, ensureing should
Intelligent sound box in time and accurately can not go out the target sound signal that effective voice signal includes, so as to respond target sound letter
Number, control intelligent sound box performs predetermined registration operation, such as phonetic order is sent to other controlled devices, to cause other controlled devices to hold
Row corresponding actions;Or meet user speech demand for control directly in response to phonetic order by the intelligent sound box.
As shown in figure 9, the structure chart of another information processor provided for the application, the device can apply to take
Be engaged in device, specifically with including:
First determining module 91, the space model of the place scene for receiving electronic equipment structure, it is determined that more
Individual intelligent sound box is laid out at least one of described space model;
First obtains module 92, collects under this scenario for obtaining any one intelligent sound box under various layouts
Effective voice signal;
Noise reduction process module 93, for the parameter using the space model, the effectively voice signal is carried out
Noise reduction process;
Second determining module 94, for based on noise reduction process result, determining at least one mesh of the multiple intelligent sound box
Mark layout;
Data transmission module 95, exported at least one target layout to be sent to the electronic equipment.
It should be noted that obtaining the processing procedure after at least one target layout on electronic equipment, it is referred to
The description of embodiment of the method appropriate section is stated, the present embodiment will not be described here.
Optionally, as shown in Figure 10, the device can also include:
Second obtains module 96, for obtaining the audio signal that any one intelligent sound box exports under various layouts;
Audio acquisition module 97, for utilizing the parameter of the space model, obtain the audio of the audio signal
Information;
Correspondingly, above-mentioned second determining module 94 can include:
Comparison unit 941, for multiple audio information of acquisition to be contrasted, obtain comparing result;
Determining unit 942, for the comparing result using noise reduction process result and multiple audio information, determine multiple intelligence
At least one target layout of energy audio amplifier.
As another embodiment of the application, on the basis of the various embodiments described above, the device can also include:
3rd obtains module, the fresh information for the space model detected for obtaining electronic equipment;
Wherein, the fresh information can be quantity and/or the position of the intelligent sound box under scene where electronic equipment detects
Put what is claimed when changing, the content that the application includes to the modification information is not construed as limiting.
Adjusting module, for utilizing the fresh information, adjust the parameter of the space model.
In summary, in the embodiment of the present application, the place scene of tango technique constructions can be utilized based on electronic equipment
Space model, experiment obtains the placement scheme of the multiple intelligent sound boxes of at least one arrangement, and at least one be laid out with
And space module is sent to server storage, so, after server obtains the space model of electronic equipment transmission,
Corresponding at least one layout can be determined, afterwards, will obtain each intelligent sound box under various layouts may collect it is effective
Voice signal, and using the parameter of the space model, noise reduction process is carried out to effective voice signal, so as to according to each
The noise reduction process result of multiple intelligent sound boxes of kind layout, at least one target layout is determined, and sent defeated to electronic equipment
Go out, with for reference, completion current scene ensures each intelligent sound box after the completion of arrangement to the arrangement of multiple intelligent sound boxes
The parameter of space model can be utilized, in time and the target sound that is recognized accurately in the effective voice signal collected
Signal, realize the Voice command to controlled device.
The above-mentioned virtual bench that intelligent sound box and server are mainly described from the angle of virtual architecture, below from hardware knot
The structure of entity device corresponding to structure description.
Reference picture 11, a kind of hardware structure diagram of the message processing device provided for the embodiment of the present application, the equipment can be with
It is intelligent sound box, can specifically includes:Communication module 111, sound collector 112, memory 113 and processor 114, its
In:
Above-mentioned communication module 111, sound collector 112, memory 113 and processor 114 can pass through communication bus
Information exchange is realized, realizes the information processing method that the application provides, and for the composition structure of the message processing device, not
Several parts that the present embodiment is enumerated are confined to, image acquisition device, buzzer, charging inlet etc. can also be included as needed
Deng.
Communication module 111 can be wireless communication module and/or wire communication module, as WIFI module, GPRS module,
Gsm module etc., it can specifically be determined according to the message processing device and the communication mode of other equipment.
For example in the embodiment of the present application, communication module 111 can wirelessly be realized and set with various smart homes
Standby communication, specifically can by wireless router and/or other Wireless Telecom Equipments, with when smart home in the scene
The data interaction of equipment.Data alternatively, it is also possible to wirelessly obtain message processing device are sent to server, are connect
Receive instruction or information of server feedback etc..
Sound collector 112 is used for effective voice signal of scene where gathering, the language sent in this scenario such as user
Phonetic order signal that sound signal or other equipment are sent, environmental sound signal of the scene etc..
Memory 113, the program of the above-mentioned information processing method from the description of intelligent sound box angle is realized for loading.
In the embodiment of the present application, as needed, the memory 113 can also store what sound collector 112 collected
Caused intermediate data in effective voice signal, and the parameter of the space model received and the program process
Etc..
Optionally, the memory 113, which can store, realizes tut acquisition module, noise reduction process module, control module
Can be specifically high-speed RAM memory Deng the program code of program function module, or nonvolatile memory (non-
Volatile memory), for example, at least magnetic disk storage etc..
Processor 114 can be central processor CPU or be specific integrated circuit ASIC (Application
Specific Integrated Circuit), or it is arranged to implement the integrated electricity of one or more of the embodiment of the present application
Road, the application are not construed as limiting to the composition structure of the processor 114.
In the embodiment of the present application, processor 114 can be used for loading and performing said procedure, including:
Using the parameter of the space model of the scene received, the sound collector is collected effective
Voice signal carries out noise reduction process, identifies the target sound signal that effectively voice signal includes;
The target sound signal is responded, performs predetermined registration operation.
Optionally, processor 114, which performs said procedure, can also realize following steps:
It is determined that None- identified goes out target sound signal from the effectively voice signal, prompt message, the prompting are exported
Information is used for instruction user and adjusts the intelligent sound box in the locus of the scene.
As can be seen here, the message processing device that the application provides will combine place scene after effective voice signal is obtained
Space model parameter, noise reduction process is carried out to the effective voice signal, noise reduction is substantially increased, improves this
Equipment identifies the accuracy and effect of target sound signal, ensures that the equipment can be realized fast and accurately and smart home is set
Standby Voice command, improve the accuracy and reliability of controlled device Voice command.
Reference picture 12, a kind of hardware structure diagram of the server provided for the embodiment of the present application, the server can include:
Communication module 121, memory 122 and processor 123, wherein:
Communication module 121 can be wireless communication module and/or wire communication module, in the present embodiment, can service
Device can realize the communication to other equipments such as electronic equipment, intelligent sound boxes by the communication module 121, and the application is to the communication
The structure of module 121 does not limit.
Memory 122 can be high-speed RAM memory either nonvolatile memory, in the embodiment of the present application, its
It can store and realize that above-mentioned first determining module, first obtain module, noise reduction process module, the second determining module and data and passed
The program code of the function of the functional modules such as defeated module, you can the above-mentioned information processing from server side description is realized with storage
The program of method.
Processor 123 can be used for loading and perform the program of the storage of memory 122, including:
The space model of the place scene of electronic equipment structure is received, determines multiple intelligent sound boxes in the building
At least one of spatial model is laid out;
Obtain effective voice signal that any one intelligent sound box under various layouts collects under this scenario;
Using the parameter of the space model, noise reduction process is carried out to the effectively voice signal;
Based on noise reduction process result, at least one target layout of the multiple intelligent sound box is determined, and is led to by described
At least one target layout is sent to the electronic equipment and exported by letter module.
Optionally, the configuration processor of processor 123 can also realize following steps:
Obtain the audio signal that any one intelligent sound box exports under various layouts;
Using the parameter of the space model, the audio information of the audio signal is obtained;
Using the comparing result of noise reduction process result and multiple audio information of acquisition, the multiple intelligent sound box is determined
At least one target layout.
In summary, server can combine the parameter of the space model for the scene for needing to arrange intelligent sound box, right
Effective voice signal that simulation intelligent sound box collects carries out noise reduction process, so that according to noise reduction process result, it is determined that providing
There are preferable audio and noise reduction, arrange at least one target layout of multiple intelligent sound boxes in the scene, and send extremely
Electronic equipment, with for reference, so as to ensure that there is optimal audio amplifier and noise reduction to the intelligent sound box arranged in actual scene
Effect, realize the accurate and Rapid Speech control to the intelligent home device of the scene.
With reference to above-mentioned Fig. 2 and Fig. 5, the embodiment of the present application additionally provides a kind of information processing system, as shown in fig. 13 that
The structure chart of information processing system, the system can include server 131, electronic equipment 132 and at least one intelligent sound box
132, wherein:
Electronic equipment 131 can have the mobile terminals such as mobile phone, the iPad of tango functions, and in the present embodiment, it can
For the space model of scene where structure, the parameter of the space model is determined, the building can also be exported
Spatial model, and at least one target layout that multiple intelligent sound boxes are arranged for the space model of server feedback
Etc..
The composition structure and its function of server 131 are referred to the description of above-mentioned server example, and the present embodiment exists
This is not repeated.
The composition structure and its function of intelligent sound box 132 are referred to the description of above- mentioned information processing equipment embodiment, this
Embodiment will not be described here.In actual applications, the contour structures of the intelligent sound box 132 are any, such as animal-shaped, cartoon character
Thing moulding etc..
In addition, it is necessary to explanation, the data of above-mentioned electronic equipment, server and intelligent sound box in information processing system
Interaction, the description of above method embodiment appropriate section is referred to, it is not described here in detail for the present embodiment.
Moreover, the composition of the information processing system provided for the application, it is not limited to each equipment of foregoing description, also
Various intelligent home devices can be included and realize auxiliary equipment of radio communication etc., the application no longer arranges one by one herein
Lift.
To sum up, in the embodiment of the present application, when effective voice signal to collecting carries out noise reduction process, where combining
The parameter of the space model of scene, improves noise reduction, so as to improve to carrying out Voice command to controlled device
Accuracy and efficiency.
Finally, it is necessary to illustrate, in the various embodiments described above, such as first, second or the like relational terms are only
Only be used for operating an operation, unit or module with another, unit or module make a distinction, and not necessarily require or secretly
Show any this actual relation or order between these units, operation or module be present.Moreover, term " comprising ", " bag
Containing " or any other variant thereof is intended to cover non-exclusive inclusion, so that process, method including a series of elements
Or system not only includes those key elements, but also the other element including being not expressly set out, or also include to be this
Process, method or the intrinsic key element of system.In the absence of more restrictions, limited by sentence "including a ..."
Key element, it is not excluded that other identical element in the process including the key element, method or system also be present.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be and other
The difference of embodiment, between each embodiment identical similar portion mutually referring to.For device disclosed in embodiment,
For equipment and system, due to its with embodiment disclosed in method it is corresponding, so description is fairly simple, related part referring to
Method part illustration.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, the composition and step of each example are generally described according to function in the above description.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specialty
Technical staff can realize described function using distinct methods to each specific application, but this realization should not
Think to exceed scope of the present application.
Directly it can be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
1. a kind of information processing method, it is characterised in that methods described includes:
Effective voice signal of scene where gathering intelligent sound box;
Using the parameter of the space model of the scene received, noise reduction process is carried out to the effectively voice signal,
Identify the target sound signal that effectively voice signal includes;
The target sound signal is responded, controls the intelligent sound box to perform predetermined registration operation.
2. according to the method for claim 1, it is characterised in that methods described also includes:
It is determined that None- identified goes out target sound signal from the effectively voice signal, prompt message, the prompt message are exported
The intelligent sound box is adjusted in the locus of the scene for instruction user.
3. according to the method for claim 1, it is characterised in that the response target sound signal, control the intelligence
Energy audio amplifier performs predetermined registration operation, including:
The target sound signal is analyzed, determines controlled device and control instruction, and triggers the controlled device and rings
Answer the control instruction.
4. a kind of information processing method, it is characterised in that applied to server, methods described includes:
The space model of the place scene of electronic equipment structure is received, determines multiple intelligent sound boxes in the space
At least one of model is laid out;
Obtain effective voice signal that any one intelligent sound box under various layouts collects under this scenario;
Using the parameter of the space model, noise reduction process is carried out to the effectively voice signal;
Based on noise reduction process result, at least one target layout of the multiple intelligent sound box is determined, and by least one
Target layout sends to the electronic equipment and exported.
5. according to the method for claim 4, it is characterised in that methods described also includes:
Obtain the audio signal that any one intelligent sound box exports under various layouts;
Using the parameter of the space model, the audio information of the audio signal is obtained;
It is described to be based on noise reduction process result, at least one target layout of the multiple intelligent sound box is determined, including:
Using the comparing result of noise reduction process result and multiple audio information of acquisition, the multiple intelligent sound box is determined extremely
A kind of few target layout.
6. a kind of information processor, it is characterised in that described device includes:
Sound acquisition module, effective voice signal for scene where gathering intelligent sound box;
Noise reduction process module, for the parameter of the space model using the scene received, to effective sound
Signal carries out noise reduction process, identifies the target sound signal that effectively voice signal includes;
Control module, for responding the target sound signal, the intelligent sound box is controlled to perform predetermined registration operation.
7. a kind of information processor, it is characterised in that described device includes:
First determining module, the space model of the place scene for receiving electronic equipment structure, determines multiple intelligence
Audio amplifier is laid out at least one of described space model;
First obtains module, the effective sound collected under this scenario for obtaining any one intelligent sound box under various layouts
Sound signal;
Noise reduction process module, for the parameter using the space model, the effectively voice signal is carried out at noise reduction
Reason;
Second determining module, for based on noise reduction process result, determining at least one target layout of the multiple intelligent sound box;
Data transmission module, exported at least one target layout to be sent to the electronic equipment.
8. a kind of message processing device, it is characterised in that the equipment includes:
Communication module;
Sound collector, effective voice signal for scene where gathering;
Memory, for storing the program realized as described in claim 1-3 any one;
Processor, for loading and performing described program, including:
Using the parameter of the space model of the scene received, the effective sound collected to the sound collector
Signal carries out noise reduction process, identifies the target sound signal that effectively voice signal includes;
The target sound signal is responded, performs predetermined registration operation.
9. a kind of server, it is characterised in that the server includes:
Communication module;
Memory, for storing the program of information processing method as claimed in claims 4 and 5;
Processor, for loading and performing described program, including:
The space model of the place scene of electronic equipment structure is received, determines multiple intelligent sound boxes in the space
At least one of model is laid out;
Obtain effective voice signal that any one intelligent sound box under various layouts collects under this scenario;
Using the parameter of the space model, noise reduction process is carried out to the effectively voice signal;
Based on noise reduction process result, at least one target layout of the multiple intelligent sound box is determined, and passes through the communication mould
At least one target layout is sent to the electronic equipment and exported by block.
10. a kind of information processing system, it is characterised in that the system includes:Server, electronic equipment and at least one intelligence
Energy audio amplifier, wherein:
The electronic equipment, for building the space model of place scene, determine the parameter of the space model;
The intelligent sound box is the message processing device described in claim 8;
The server is the server described in claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710823091.2A CN107527615B (en) | 2017-09-13 | 2017-09-13 | Information processing method, device, equipment, system and server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710823091.2A CN107527615B (en) | 2017-09-13 | 2017-09-13 | Information processing method, device, equipment, system and server |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107527615A true CN107527615A (en) | 2017-12-29 |
CN107527615B CN107527615B (en) | 2021-01-15 |
Family
ID=60735881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710823091.2A Active CN107527615B (en) | 2017-09-13 | 2017-09-13 | Information processing method, device, equipment, system and server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107527615B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108447506A (en) * | 2018-03-06 | 2018-08-24 | 深圳市沃特沃德股份有限公司 | Method of speech processing and voice processing apparatus |
CN108461084A (en) * | 2018-03-01 | 2018-08-28 | 广东美的制冷设备有限公司 | Speech recognition system control method, control device and computer readable storage medium |
CN108597536A (en) * | 2018-03-20 | 2018-09-28 | 成都星环科技有限公司 | A kind of interactive system based on acoustic information positioning |
CN109346066A (en) * | 2018-09-26 | 2019-02-15 | 珠海格力电器股份有限公司 | A kind of method and device of voice de-noising |
CN109511041A (en) * | 2018-12-28 | 2019-03-22 | 歌尔科技有限公司 | A kind of method, apparatus and earphone of the booting setting of earphone |
CN109688036A (en) * | 2019-02-20 | 2019-04-26 | 广州视源电子科技股份有限公司 | A kind of control method of intelligent appliance, device, intelligent appliance and storage medium |
CN109889956A (en) * | 2019-02-25 | 2019-06-14 | 深圳市奇脉电子技术有限公司 | A kind of pinpoint accuracy noise reduction configuration mode of active noise reduction equipment |
CN109991864A (en) * | 2019-03-13 | 2019-07-09 | 佛山市云米电器科技有限公司 | Home automation scenery control system and its control method based on image recognition |
WO2020003695A1 (en) * | 2018-06-25 | 2020-01-02 | ソニー株式会社 | Information processing device, information processing method, and information processing system |
CN110677776A (en) * | 2019-09-26 | 2020-01-10 | 恒大智慧科技有限公司 | Volume adjusting method and device, intelligent sound box and storage medium |
CN111161704A (en) * | 2018-10-22 | 2020-05-15 | 联想图像(天津)科技有限公司 | Control method of electronic equipment and electronic equipment |
CN112929096A (en) * | 2021-01-27 | 2021-06-08 | 嘉兴中科声学科技有限公司 | Sound signal processing method and device and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5764777A (en) * | 1995-04-21 | 1998-06-09 | Bsg Laboratories, Inc. | Four dimensional acoustical audio system |
US20080243278A1 (en) * | 2007-03-30 | 2008-10-02 | Dalton Robert J E | System and method for providing virtual spatial sound with an audio visual player |
CN104967717A (en) * | 2015-05-26 | 2015-10-07 | 努比亚技术有限公司 | Noise reduction method and apparatus in terminal voice interaction mode |
CN106898348A (en) * | 2016-12-29 | 2017-06-27 | 北京第九实验室科技有限公司 | It is a kind of go out acoustic equipment dereverberation control method and device |
CN107016990A (en) * | 2017-03-21 | 2017-08-04 | 腾讯科技(深圳)有限公司 | Audio signal generation method and device |
CN107092357A (en) * | 2017-04-21 | 2017-08-25 | 厦门中智信系统集成有限公司 | The real border Architectural Equipment management system of holography based on virtual reality |
-
2017
- 2017-09-13 CN CN201710823091.2A patent/CN107527615B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5764777A (en) * | 1995-04-21 | 1998-06-09 | Bsg Laboratories, Inc. | Four dimensional acoustical audio system |
US20080243278A1 (en) * | 2007-03-30 | 2008-10-02 | Dalton Robert J E | System and method for providing virtual spatial sound with an audio visual player |
CN104967717A (en) * | 2015-05-26 | 2015-10-07 | 努比亚技术有限公司 | Noise reduction method and apparatus in terminal voice interaction mode |
CN106898348A (en) * | 2016-12-29 | 2017-06-27 | 北京第九实验室科技有限公司 | It is a kind of go out acoustic equipment dereverberation control method and device |
CN107016990A (en) * | 2017-03-21 | 2017-08-04 | 腾讯科技(深圳)有限公司 | Audio signal generation method and device |
CN107092357A (en) * | 2017-04-21 | 2017-08-25 | 厦门中智信系统集成有限公司 | The real border Architectural Equipment management system of holography based on virtual reality |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108461084A (en) * | 2018-03-01 | 2018-08-28 | 广东美的制冷设备有限公司 | Speech recognition system control method, control device and computer readable storage medium |
CN108447506A (en) * | 2018-03-06 | 2018-08-24 | 深圳市沃特沃德股份有限公司 | Method of speech processing and voice processing apparatus |
CN108597536A (en) * | 2018-03-20 | 2018-09-28 | 成都星环科技有限公司 | A kind of interactive system based on acoustic information positioning |
WO2020003695A1 (en) * | 2018-06-25 | 2020-01-02 | ソニー株式会社 | Information processing device, information processing method, and information processing system |
CN109346066B (en) * | 2018-09-26 | 2021-04-16 | 珠海格力电器股份有限公司 | Voice noise reduction method and device |
CN109346066A (en) * | 2018-09-26 | 2019-02-15 | 珠海格力电器股份有限公司 | A kind of method and device of voice de-noising |
CN111161704A (en) * | 2018-10-22 | 2020-05-15 | 联想图像(天津)科技有限公司 | Control method of electronic equipment and electronic equipment |
CN109511041A (en) * | 2018-12-28 | 2019-03-22 | 歌尔科技有限公司 | A kind of method, apparatus and earphone of the booting setting of earphone |
CN109511041B (en) * | 2018-12-28 | 2020-06-26 | 歌尔科技有限公司 | Earphone starting setting method and device and earphone |
CN109688036A (en) * | 2019-02-20 | 2019-04-26 | 广州视源电子科技股份有限公司 | A kind of control method of intelligent appliance, device, intelligent appliance and storage medium |
CN109889956A (en) * | 2019-02-25 | 2019-06-14 | 深圳市奇脉电子技术有限公司 | A kind of pinpoint accuracy noise reduction configuration mode of active noise reduction equipment |
CN109991864A (en) * | 2019-03-13 | 2019-07-09 | 佛山市云米电器科技有限公司 | Home automation scenery control system and its control method based on image recognition |
CN110677776A (en) * | 2019-09-26 | 2020-01-10 | 恒大智慧科技有限公司 | Volume adjusting method and device, intelligent sound box and storage medium |
CN110677776B (en) * | 2019-09-26 | 2021-08-17 | 星络智能科技有限公司 | Volume adjusting method and device, intelligent sound box and storage medium |
CN112929096A (en) * | 2021-01-27 | 2021-06-08 | 嘉兴中科声学科技有限公司 | Sound signal processing method and device and electronic equipment |
CN112929096B (en) * | 2021-01-27 | 2022-07-12 | 嘉兴中科声学科技有限公司 | Sound signal processing method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN107527615B (en) | 2021-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107527615A (en) | Information processing method, device, equipment, system and server | |
CN103488134B (en) | Location-based device is automatically brought into operation | |
CN108390859A (en) | A kind of interphone extension intelligent robot | |
CN105163241B (en) | Audio frequency playing method and device, electronic equipment | |
CN104469670B (en) | A kind of method based on mobile terminal locations switching audio pattern and mobile terminal | |
CN103988523B (en) | Sound is carried out with playback apparatus and its method for shaping | |
CN106507240A (en) | A kind of physical location of the speaker by speaker system is associated to the method for speaker identifier | |
CN106346487A (en) | Interactive VR sand table show robot | |
CN108597530A (en) | Sound reproducing method and device, storage medium and electronic device | |
CN107277260A (en) | A kind of contextual model method of adjustment, device and mobile terminal | |
CN106773766A (en) | Smart home house keeper central control system and its control method with learning functionality | |
CN107728482A (en) | Control system, control process method and device | |
CN102436621A (en) | Systems and methods for displaying housing estate landscape data and generating housing estate landscape display data | |
CN109597481A (en) | AR virtual portrait method for drafting, device, mobile terminal and storage medium | |
US10291986B1 (en) | Intelligent audio for physical spaces | |
CN109977731A (en) | A kind of recognition methods of scene, identification equipment and terminal device | |
CN107801120B (en) | A kind of method, device and mobile terminal of determining speaker placement position | |
CN110072177B (en) | Space division information acquisition method and device and storage medium | |
CN109089057A (en) | Glass fragmentation faced special efficacy experiencing system, method and device | |
CN106911956A (en) | A kind of audio data play method, device and mobile terminal | |
CN108958155A (en) | Stereo garage control method, system and computer readable storage medium | |
CN107452069A (en) | A kind of virtual house ornamentation system based on mobile Internet and cloud platform | |
CN205880712U (en) | System for change indoor scene | |
CN105809781A (en) | Visiting request responding method and visiting request responding device | |
CN102136178A (en) | Guard server, guard system using the guard server and guard method |
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 |