CN106782522A - Sound control method and speech control system - Google Patents
Sound control method and speech control system Download PDFInfo
- Publication number
- CN106782522A CN106782522A CN201510815428.6A CN201510815428A CN106782522A CN 106782522 A CN106782522 A CN 106782522A CN 201510815428 A CN201510815428 A CN 201510815428A CN 106782522 A CN106782522 A CN 106782522A
- Authority
- CN
- China
- Prior art keywords
- speech
- voice
- speech data
- module
- user
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000009434 installation Methods 0.000 claims abstract description 54
- 230000004044 response Effects 0.000 claims abstract description 29
- 230000009471 action Effects 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims description 55
- 230000015654 memory Effects 0.000 claims description 35
- 230000001755 vocal effect Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 17
- 230000005236 sound signal Effects 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 19
- 230000007613 environmental effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000000465 moulding Methods 0.000 description 2
- 241001062009 Indigofera Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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 TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- 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)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention provides a kind of sound control method and speech control system, and the sound control method is applied to the phonetic controller for being linked to Local Area Network.The sound control method comprises the following steps:Speech data is received by world-wide web;Speech recognition action is performed to speech data to obtain the control instruction in speech data;The speech response information for reacting on control instruction is transmitted by world-wide web;According to control instruction at least one electronic installation is controlled with by Local Area Network.Sound control method and speech control system that the present invention is provided, the user that distal end can be made way for can be operated using voice to voice assistant module, and then other electronic installations being located in the same area network are controlled by voice assistant module, so as to realize the distal end voice control function of voice assistant.
Description
Technical field
The invention relates to a kind of sound control method, and far-end operation is available in particular to one kind
The sound control method and speech control system of voice assistant.
Background technology
Being provided with personal voice assistance system operating system on the market at present more.These people voice assistants
System has the spy of hommization and simple operations due to sound control in addition to the function that can provide answer
Point, controls the mode of other devices more and more universal using acoustic control.For example, wired home service or
Internet of Things is to be provided with voice control function.
However, the design of general individual's voice assistance system only considers the situation that user is located near device,
Therefore be also only through radio reception device and acoustical generator of the configuration on device and engaged in the dialogue with user.Once user
Not near device, the function of personal voice assistance system just cannot be used.Though prior art can be by indigo plant
Tooth device operates personal voice assistance system, but is limited to the transmission range of Bluetooth technology, can only still carry
Personal voice assistance system is operated for the user in near-end.
The content of the invention
The present invention provides a kind of sound control method and speech control system, its user that can make way for distal end
Voice assistant module can be operated using voice, and then control to be located at by voice assistant module
Other electronic installations in the same area network.
The present invention proposes a kind of sound control method, and it is applied to the Voice command dress for being linked to Local Area Network
Put.The sound control method comprises the following steps.Speech data is received by world-wide web, to voice
Data perform speech recognition action to obtain the control instruction in speech data, transmit anti-by world-wide web
In the speech response information of control instruction, and should be controlled at least with by Local Area Network according to control instruction
One electronic installation.
The present invention separately proposes a kind of speech control system, and it includes user's set, at least one electronic installation
And phonetic controller.User's set sends speech data by world-wide web.Electronic installation includes the
One communication unit, it is linked to Local Area Network.Phonetic controller includes that the second communication unit, storage are single
Unit and processing unit.Second communication unit is linked to Local Area Network.Unit records multiple module.
Processing unit couples the second communication unit and memory cell, is used to access and perform record in memory cell
The module.The module includes voice communications module and voice assistant module.Voice communications module
Speech data is received by world-wide web.Voice assistant module to speech data perform speech recognition action with
Obtain the control instruction in speech data.Wherein, voice communications module is transmitted by world-wide web and reacted on
The speech response information of control instruction, and voice assistant module foundation control instruction is with by Local Area Network control
Make the electronic installation.
Based on above-mentioned, the embodiment of the present invention will pass through the speech data that world-wide web received and bridge to voice
Assistant, user voice assistant module can be operated using voice in distal end, and then by voice
Assistant module come control be located at the same area network in other electronic installations.Further, since speech recognition
Action is performed by phonetic controller, therefore the element that user's set is configured can be simplified.
It is that features described above of the invention and advantage can be become apparent, special embodiment below, and coordinate
Accompanying drawing is described in detail below.
Brief description of the drawings
Fig. 1 is the block diagram of the speech control system shown by one embodiment of the invention;
Fig. 2 is the flow chart of the sound control method shown by one embodiment of the invention;
Fig. 3 is the block diagram of the speech control system shown by one embodiment of the invention;
Fig. 4 is the flow chart of the sound control method shown by one embodiment of the invention;
Fig. 5 is the block diagram of the speech control system shown by one embodiment of the invention;
Fig. 6 is the flow chart of the sound control method shown by one embodiment of the invention;
Fig. 7 is the flow chart of the sound control method shown by one embodiment of the invention;
Fig. 8 is the flow chart of the sound control method shown by one embodiment of the invention;
Fig. 9 is the flow chart of the sound control method shown by one embodiment of the invention.
Description of reference numerals:
10、30、50:Speech control system;
100、500:Phonetic controller;
110、210、510:Communication unit;
120、520:Memory cell;
122、522:Voice communications module;
124、524:Voice assistant module;
126:System voice input module;
128:System voice output module;
130、530:Processing unit;
200:Electronic installation;
300:User's set;
526:Authority setting module;
528:Control module;
S202~S208, S402~S410, S602~S612, S702~S718, S802~S806, S902~S908:
Method and step.
Specific embodiment
World-wide web voice agreement (Voice over Internet Protocol, abbreviation VoIP) technology can lead to
Cross network to transmit voice to far end device, but be only applied to the communication between user.Using voip technology
The characteristic that voice can be passed through into network transmission to distal end, the embodiment of the present invention further will be by Internet
The speech data that network is received bridges to voice assistant, to realize the distal end voice control function of voice assistant, allows
User can be operated in distal end by voice to voice assistant, and then control to link with voice assistant
To other electronic installations (such as intelligent appliance dresses for linking with same private network of the same area network
Put).On the other hand, the convenient safety problem stretched, this hair of spreading out of operation of intelligent appliance device is contemplated
Bright embodiment can also confirm whether user is validated user using sound-groove identification, and validated user is set
Different grades of access right, adaptively to determine Voice command according to access right and using situation
Device sets for the control of other electronic installations.
In the examples below, Fig. 1 to Fig. 4 is used to illustrate the part of distal end voice control function, Fig. 5 to figure
8 are used to illustrate the control setting that security is considered.
Fig. 1 is the block diagram of the speech control system shown by one embodiment of the invention.Refer to Fig. 1,
The speech control system 10 of the present embodiment includes phonetic controller 100, at least one electronic installation 200
And user's set 300.For convenience of description, only show out that an electronic installation 200 is made in Fig. 1
To illustrate.Wherein, phonetic controller 100 is, for example, the electronic installations such as desktop computer, notebook computer,
It has basic network connectivity and operational capability.In addition, electronic installation 200 is, for example, intelligent appliance dress
Put (such as intelligent television, intelligent bulbs, projecting apparatus etc.) or other electronic installations.As for user's set
300 are, for example, the electronic installations such as desktop computer, notebook computer, or can also be panel computer, intelligence
The running gears such as energy type mobile phone.Phonetic controller 100 can receive user's set 300 by world-wide web
The speech data for being sent, and can be linked with electronic installation 200 by Local Area Network, to allow user to fill
Putting 300 can receive the voice signal of user, and this voice signal is conveyed directly into voice by network
Control device 100, uses the voice control function that distal end performs phonetic controller 100.
It is noted that the phonetic controller 100 of the embodiment of the present invention is arranged at a private network (example
Such as home network Local Area Network) in, and for example as the server in this private network.Therefore, phase
For the server for being generally positioned at external network, the embodiment of the present invention can avoid external device (ED) from invading
Or the problem of improper operation.
Specifically, phonetic controller 100 includes communication unit 110, memory cell 120 and place
Reason unit 130.Communication unit 110 is, for example, wired network interface card or supports motor electronic engineer
Association (Institute of Electrical and Electronics Engineers, abbreviation IEEE) 802.11b/g/n
Deng the wireless network interface card of communication protocol, or the network communication module of other network conventions is supported, it can
It is used to transmit data by network or receives data.In the present embodiment, communication unit 110 may be used to
Link world-wide web, phonetic controller 100 can be filled with transferring data to user by world-wide web
300 are put, and data are received with from user's set 300 by world-wide web.Additionally, communication unit 110
And can connecting area network, control providing phonetic controller 100 to be located at by Local Area Network same
(for example, the intelligent appliance product in wired home, it is under the jurisdiction of electronic installation 200 in Local Area Network
Same home network).
Memory cell 120 is, for example, various non-volatile (non-volatile) memories or its combination, example
Such as read-only storage (Read-Only Memory, abbreviation ROM) and/or flash memory (flash
memory).In addition, memory cell 120 may also comprise hard disk, laser disc or external storage device (such as
Storage card, mobile hard disk etc.) etc. storage media or its combination, herein not to the body of memory cell 120
Existing mode is any limitation as.In the present embodiment, memory cell 120 is used to record voice communications module 122
And voice assistant module 124.These modules are, for example, storage program in the storage unit 120, its
Can be loaded into the processing unit 130 of phonetic controller 100, and by processing unit 130 perform phonetic incepting,
The function such as identification and control.It should be noted that, memory cell 120 described in the present embodiment be not limiting as be
Single memory component, above-mentioned module can also be stored separately in two or more identical or different types
In the memory component of state.
In addition, memory cell 120 may also include speech database (not shown), and optionally wrap
Include voice print database (not shown).Speech database is used to record multiple preset audio signals, and can example
Such as correspond to multiple glossarys or sound sequence.Voice print database is used to record multiple default vocal prints, and these are preset
Vocal print can correspond respectively to different users.In simple terms, the user corresponding to these default vocal prints is visual
To be allowed to access the validated user of phonetic controller 100.
The e.g. CPU of processing unit 130, or other programmable general services or special
The microprocessor (Microprocessor) of purposes, digital signal processor (Digital Signal Processor,
Abbreviation DSP), Programmable Logic Controller, application specific integrated circuit (Application Specific Integrated
Circuits, abbreviation ASIC), programmable logic device (Programmable Logic Device, referred to as
PLD) or other similar devices or these devices combination.Processing unit 130 couples communication unit 110
And memory cell 120, it is used to access and perform the module recorded in memory cell 120, and controls
The overall operation of phonetic controller 100, so as to realize the sound control method of the present embodiment.This implementation
Example described in processing unit 130 be not limiting as be single treatment element, or by two or two with
On treatment element perform jointly.
Electronic installation 200 includes communication unit 210.Communication unit 210 is, for example, wired network interface card
Or the support Institute of Electrical and Electronics Engineers (IEEE) (Institute of Electrical and Electronics Engineers,
Abbreviation IEEE) communication protocol such as 802.11b/g/n wireless network interface card, or support other network conventions
Network communication module, it may be used to be transmitted by network data or receives data.In the present embodiment,
Communication unit 210 can connecting area network received from phonetic controller 100 with providing electronic installation 200
Control instruction, and make electronic installation 200 that corresponding operation can be performed according to control instruction.
In addition, electronic installation 200 may also include memory cell (not shown) and processing unit (does not show
Go out).Wherein, the memory cell of electronic installation 200 is, for example, various non-volatile (non-volatile)
Memory or its combination, for example read-only storage (Read-Only Memory, abbreviation ROM) and/or
Flash memory (flash memory), or may also comprise hard disk, laser disc or external storage device (such as
Storage card, mobile hard disk etc.) etc. storage media or its combination, it may be used to store the control for receiving and refers to
Order.Processing unit as electronic installation 200 is, for example, then CPU, or other can program
The general service of change or microprocessor (Microprocessor), the digital signal processor of specific use
(Digital Signal Processor, abbreviation DSP), Programmable Logic Controller, application specific integrated circuit
(Application Specific Integrated Circuits, abbreviation ASIC), programmable logic device
The combination of (Programmable Logic Device, abbreviation PLD) or other similar devices or these devices,
Its overall operation for being used to control electronic installation 200.
Fig. 2 is the flow chart of the sound control method shown by one embodiment of the invention, and it is applied to Fig. 1
Speech control system 10.Hereinafter each element i.e. in collocation speech control system 10, illustrates this implementation
The detailed process of example method.
Fig. 1 and Fig. 2 is refer to, in step S202, voice communications module 122 is connect by world-wide web
Receive speech data.Above-mentioned speech data is, for example, the speech data based on VoIP, and is after being digitized into
Voice signal.
Voice communications module 122 is, for example, the language for receiving and being sent by world-wide web by user's set 300
Sound data.In one embodiment, voice communications module 122 is, for example, the VoIP such as Skype, Line applications
Program.Therefore, when phonetic controller 100 and user's set 300 are carried out VoIP application programs, and
User is conversed in far-end operation user's set 300 and by VoIP with being set up with phonetic controller 100
When, the voice signal that user sends just can be converted into by the VoIP application programs on user's set 300
Speech data based on VoIP, and it is transferred into voice communications module 122.From for another angle,
The phonetic controller 100 of the present embodiment can receive speech data by application program.
In step S204, voice assistant module 124 performs speech recognition action to speech data to obtain
Control instruction in speech data.In detail, voice assistant module 124 for example includes speech recognition device,
It can have speech recognition and analytic function.In the present embodiment, voice assistant module 124 can compare language
Whether sound data meet at least one of the preset audio signal in speech database.When above-mentioned comparison
Result is for when being, just can be considered as the preset audio signal met with speech data by voice assistant module 124
Control instruction.Furthermore, it is understood that above-mentioned preset audio signal can correspond to acoustic model and/or language
Model, wherein, acoustic model is, for example, one or more enunciative least units (for example, KK phonetic symbols
Or phonetic symbol (Phonetic Symbol) etc.) combination.It is, for example, then specific language as language model
The common syntax rule of speech (such as English or Chinese etc.).Therefore, voice assistant module 124 can be from language
Obtain acoustic feature in sound data, and by the acoustic model and language included by acoustic feature and speech database
Speech model is compared, and glossary corresponding with speech data or syllable is judged according to this, and obtain voice number
Control instruction in.
In the present embodiment, voice assistant module 124 is, for example, to language using single speech database
Sound data are recognized.In another embodiment, voice assistant module 124 can be then distinguished different user
The speech database of foundation, with using the speech database corresponding with user come the voice number to this user
According to being recognized.Under this framework, voice assistant module 124 can also be by study mechanism with to specific use
The speech recognition at family is optimized.The details of this part is by row is described again in the embodiment after.
Additionally, in other embodiments, voice assistant module 124 also can be by network connection a to high in the clouds
Server, and voice assistant module 124 can communicate with cloud server, with speech data is judged
When control instruction must could be processed by connecting network, assist process this control is come by cloud server and is referred to
Order.
Afterwards, in step S206, voice communications module 122 is transmitted by world-wide web and reacts on control
The speech response information of instruction, and, in step S208, voice assistant module 124 refers to according to control
Order controls electronic installation 200 with by Local Area Network.Above-mentioned speech response information is, for example, to be helped by voice
Reason module 124 according to produced by control instruction, and after by voice communications module 122 by speech response
Information back is to user's set 300.In other words, the data form of speech response information can be with speech data
It is identical.In the present embodiment, speech response information is also, for example, the data form based on VoIP.
Thus, user's set 300 can be after speech response information be received, such as by voice output
Unit (such as loudspeaker) and the speech response information based on VoIP is directly converted into the language of analog form
Message number is simultaneously exported, with to remote subscriber present voice recognition result on this control instruction or on
The control information of electronic installation 200.Or, user's set 300 can also be used display unit and (for example shield
Curtain) and the control information of voice recognition result or correlation is presented in the way of word.It is above-mentioned to be filled in user
The mode for putting 300 ends presentation speech response information can be depending on the demand in practice, and the present invention is not limited this
System.
Consequently, it is possible to the present embodiment passes through voip technology in user's set 300 and phonetic controller 100
Between transmit speech data and speech response information, can allow user pass through user's set 300 with distal end grasp
Make the voice assistant module 124 of phonetic controller 100, so as to realize phonetic controller 100 with it is remote
Hold the voice interface between the user's set 300 of operation.
On the other hand, because phonetic controller 100 and electronic installation 200 can respectively pass through communication unit
110 with communication unit 210 and be linked to the same area network, therefore, obtained in voice assistant module 124
Obtain after the control instruction in speech data, can also control electronic installation 200 by Local Area Network according to this,
So that electronic installation 200 performs act corresponding with control instruction.Thus, user just can distal end with
The mode of acoustic control is controlled to the household electrical appliances in wired home service.
Fig. 3 is the block diagram of the speech control system shown by one embodiment of the invention, and it shows out voice
The detailed architecture of control device 100.Fig. 3 is refer to, speech control system 30 includes phonetic controller
100th, at least one electronic installation 200 (only showing out an electronic installation 200 in order to illustrate in Fig. 3)
And user's set 300.Speech control system 30 is similar with the speech control system 10 of Fig. 1, therefore phase
Same or similarity is repeated no more.
In the present embodiment, the memory cell 120 of phonetic controller 100 is also used to record system voice
Input module 126 and system voice output module 128, it is, for example, to store in the storage unit 120
Program, the processing unit 130 of phonetic controller 100 can be loaded into, and performed by processing unit 130,
To bridge the voice data transmission between voice communications module 122 and voice assistant module 124 respectively.
Specifically, voice communications module 122 can receive speech data by world-wide web, and by voice
Data are provided to system voice input module 126.System voice input module 126 can enter to speech data
Row format is changed, and the speech data after form is changed is provided to voice assistant module 124.If
By the reception of voice communications module 122 is that then system voice is input into mould as a example by being based on the speech data of VoIP
Block 126 is, for example, that the speech data based on VoIP is converted into the voice number with system voice input specification
According to be supplied to voice assistant module 124 to be recognized.
After the speech recognition action that voice assistant module 124 is carried out to speech data is completed, voice is helped
Reason module 124 can obtain control instruction, and produce speech response information according to control instruction, and by language
Sound echo message is provided to system voice output module 128.System voice output module 128 can be to voice
Echo message enters row format conversion, and the speech response information after form is changed is provided to voice leads to
Letter module 122.Above-mentioned speech response information is for example with system voice output specification, therefore system voice
Speech response information with system voice output specification for example can be converted into being based on by output module 128
The speech response information of VoIP, speech response information is provided to voice communications module 122, and by language
Sound communication module 122 is by world-wide web with by speech response information transmission to user's set 300.
It is noted that the embodiment of the present invention is only carried out by phonetic controller 100 to speech data
Speech recognition, user's set 300 need not perform speech recognition action, therefore also without in user's set 300
The language of the upper a large amount of default voice audio signals of specifically configured processor and record with powerful operational capability
Sound database, therefore, it is possible to simplify the design of user's set 300.Additionally, being transmitted by voip technology
Voice, can also avoid fire wall and network settings on network from stopping the problem of network connectivity.
In addition, the safety issue of distal end voice control function and the degree of accuracy of speech recognition are considered, at some
In embodiment, voice assistant module 124 can also be by sound-groove identification to confirm user's status, and for use
Family provides an other speech database to be controlled the comparison of instruction, thus avoid because user accent or
The degree of accuracy that custom of speaking is different and influences control instruction to recognize.
Illustrated in the embodiment of this measure one.Fig. 4 is the Voice command side shown by one embodiment of the invention
The flow chart of method, it shows out that voice assistant module 124 performs the detailed of speech recognition action to speech data
Thin step.The present embodiment be applied to Fig. 1 speech control system 10, and it is different from previous embodiment it
Place is that the phonetic controller 100 of the present embodiment also includes voice print database and multiple speech datas
Storehouse, it can be recorded in memory cell 120 respectively.Wherein, the recordable multiple default sound of voice print database
Line, these default vocal prints correspond to the speech database respectively, and each speech database is recordable multiple pre-
If audio signal.
Fig. 4 is refer to, in step S402, voice assistant module 124 joins according to the feature of speech data
Count to obtain the voiceprint in speech data.For example, voice assistant module 124 can be by linear
Predictive coefficient (Linear Prediction Coefficient, abbreviation LPC), Mel-frequency Cepstral Coefficients
Computings such as (Mel-Frequency Cepstral Coefficient, abbreviation MFCC), to extract speech data
Characteristic parameter and as voiceprint.
In step s 404, voice assistant module 124 is compared during whether voiceprint meet voice print database
One of default vocal print of multiple.If so, then voice assistant module 124 judges this voiceprint pair
What is answered is validated user, and in step S406, voice assistant module 124 obtains and meets with voiceprint
Default vocal print corresponding to speech database, and this speech database is considered as the corresponding spy of speech data
Determine speech database.If it is not, then voice assistant module 124 can determine that this voiceprint does not have voice control
The access right of device processed 100, therefore subsequent treatment is no longer carried out to this speech data, and return to step S402
To receive speech data again.
Then, in step S408, voice assistant module 124 compares whether speech data meets specific language
At least one of multiple preset audio signals in sound database.If so, then in step S410,
The preset audio signal met with speech data is considered as control instruction by voice assistant module 124.If it is not,
Then voice assistant module 124 can determine that the control of control instruction in this speech data not in authority refers to
Order, therefore this control instruction is not performed, and return to step S402.
It is noted that in one embodiment, phonetic controller 100 may also provide machine learning machine
System, is updated with the input operation according to user to above-mentioned particular phonetic database.For example,
When user's set 300 receives the speech response information that phonetic controller 100 is returned, user's set
300 can also for example provide an input interface, and the mode that user can be input into for example, by word carrys out feedback
For revising one's view for voice recognition result.Thus, phonetic controller 100 can by data training come
The acoustic model and/or language model in this particular phonetic database are adjusted, so as to optimize the language to this user
The degree of accuracy of sound identification.
How following then explanation phonetic controller is using voiceprint, prompt command and environmental information
Set with realizing the control considered based on security etc. parameter.Wherein, the embodiment of the present invention is except available
Foregoing sound-groove identification outside confirming whether user is validated user, different to user's setting can also make
With authority, and by the prompt command in speech data obtain User Status (such as user be in or
The positional information such as outgoing), use using User Status and/or environmental information in time adjust access right with
And judge current use situation.Thus, the embodiment of the present invention is except can determine whether user for Voice command
Authority outside, additionally it is possible to it is specific using situation under further limitation phonetic controller to user institute
The voice control function of offer, or phonetic controller is performed specific operator scheme automatically.Therefore, may be used
Effectively to take into account the operation ease and security of wired home service.
Fig. 5 is the block diagram of the speech control system shown by one embodiment of the invention.Refer to Fig. 5,
Speech control system 50 includes the electronic installation 200 of phonetic controller 500 and at least one (in Fig. 5
Only show out an electronic installation 200 in order to illustrate).Phonetic controller 500 includes communication unit
510th, memory cell 520 and processing unit 530.Wherein, memory cell 520 is used to record voice and leads to
Letter module 522, voice assistant module 524, authority setting module 526 and control module 528, its example
The program in memory cell 520 is such as stored in, and the processing unit of phonetic controller 500 can be loaded into
530, and the functions such as speech recognition, authority setting and control are performed by processing unit 530.In addition, electronics
Device 200 then includes communication unit 210, memory cell (not shown) and processing unit (not shown).
Each element of the present embodiment is similar with previous embodiment respectively, therefore same or similar part is repeated no more.
Specifically, voice communications module 522 may be used to receive speech data.In the present embodiment, language
Sound communication module 522 can for example be directly received by audio signal reception device (such as microphone or other radio reception devices)
The voice signal that user is sent, and treatment is digitized to voice signal by voice communications module 522
To obtain speech data.In other words, the user of the present embodiment and phonetic controller 500 are in same room
Between, among the space such as meeting room.In other embodiments, voice communications module 522 also can be by internet
Network receives the speech data from user's set (such as the user's set 300 in Fig. 1 embodiments),
And this speech data is, for example, the speech data based on VoIP.The implementation detail and previous embodiment of this part
It is similar, therefore explanation is not repeated.
Voice assistant module 524 can perform speech recognition action to obtain speech data correspondence to speech data
Voiceprint and prompt command.Voice assistant module 524 be, for example, by obtaining speech data in
To obtain voiceprint, it may be used to confirm user's status characteristic parameter.In addition, voice assistant module 524
E.g. by comparing speech data and speech database to obtain prompt command.In the present embodiment,
The prompt command for example includes the positional information of the specific words and expressions such as " in outgoing ", " at home ", and it can use
To be recorded as User Status.Above-mentioned voice assistant module 524 performs speech recognition action to obtain voice number
Can be similar with the embodiment of Fig. 4 according to the detailed process of corresponding voiceprint and prompt command, therefore its is thin
Section refer to foregoing.
Authority setting module 526 can be according to voiceprint and prompt command, to determine voiceprint correspondence
Authority information.Specifically, authority setting module 526 (can correspond respectively to different vocal prints to user
Information) set different Permission Levels.These Permission Levels may be used to decision, and to be controlled by this voiceprint (right
Using family) the device quantity of electronic installation 200, function quantity or its combination, and can for example searching
The mode of table is stored in memory cell 520.
As for control module 528 then can according to authority information, prompt command and environmental information at least its
One of, control electronic installation 200 with by Local Area Network.In other words, the present embodiment can be by power
The combination of limit information and environmental information sets various use situations so that control module 528 according to
Different is controlled using situation to electronic installation 200.
For example, when speech control system 50 includes an electronic installation 200, the height of Permission Levels can
Determine the controllable electronic installation 200 of this voiceprint function quantity number.For another example speech control system
50 situations for including multiple electronic installations 200, the height of Permission Levels is except that can determine this voiceprint
Outside the function quantity of controllable each electronic installation 200, additionally it is possible to determine this voiceprint in language
The device quantity of controllable electronic installation 200 in sound control system 50.From for another angle, hold power
When limiting higher ranked, corresponding to voiceprint speech data can control speech control system 50 ability compared with
By force, and when Permission Levels are relatively low, the speech data corresponding to voiceprint can control speech control system
50 ability is then restricted.
Therefore, in the present embodiment, when voice assistant module 524 obtains voiceprint, authority setting
Module 526 just can be according to voiceprint searching data storehouse, with one of selection from multiple Permission Levels
As the authority information corresponding to this voiceprint.Additionally, authority setting module 526 can also be according to carrying
Show in order whether the positional information comprising user, with the authority for adaptively improving or reducing authority information
Grade.
Illustrated to determining the detailed step of authority information with the embodiment of Fig. 6 herein.Fig. 6 is this hair
The flow chart of the sound control method shown by a bright embodiment, its speech control system for being applied to Fig. 5
50。
Fig. 6 is refer to, in step S602, authority setting module 526 is selected many according to voiceprint
One of individual Permission Levels are being set as authority information.In other words, authority setting module 526 can be first
Default access grade in searching data storehouse corresponding to this voiceprint, and it is set as current authority information.
In step s 604, authority setting module 526 provides voiceprint corresponding User Status.It is described
User Status is, for example, to be recorded in memory cell 520, or be can record in other registers.
Then, in step S606, authority setting module 526 will be prompted to the positional information note that order includes
Record to User Status.In detail, whether authority setting module 526 can determine whether prompt command including position letter
Breath, and when prompt command include positional information when, authority setting module 526 can by positional information record to
User Status.The positional information can be for example the specific words and expressions such as foregoing " in outgoing ", " at home ".
Afterwards, in step S608, whether authority setting module 526 judges User Status according to position letter
Cease and change, and when User Status is changed according to positional information, in step S610, authority setting
The Permission Levels of the renewal authority information of module 526.Wherein, the above-mentioned update action example for authority information
In this way described authority etc. is adjusted to by authority setting module 526 with by the first authority information according to User Status
Level it is wherein another.
On the other hand, if User Status is not changed, into step S612, authority setting module 526
The update action of authority information is not performed.
For example, when voice communications module 522 is direct by the radio unit of phonetic controller 500
When receiving the speech data of a validated user, authority setting module 526 can be believed according to the vocal print of this user
Cease and correspond to and find out authority information.In addition, authority setting module 526 and can by this voiceprint correspondence
User Status be preset to " at home ".Include " in outgoing " when authority setting module 526 judges prompt command
Or during other different from " at home " positional informations, authority setting module 526 can believe above-mentioned position
Breath (such as " in outgoing ") is recorded to User Status.Now, because User Status is sent out because of positional information
Change more, therefore authority setting module 526 can adjust the Permission Levels of authority information.In this embodiment,
When User Status is switched to " in outgoing " from " at home ", authority setting module 526 is, for example, to drop
The Permission Levels of low rights information.On the other hand, when prompt command does not include positional information or prompting
When order only includes the positional information of " at home ", authority setting module 526 does not change User Status then,
Also therefore not authority information is updated/is adjusted, and current Permission Levels are directly set as this vocal print
The corresponding authority information of information.
Thus, the present embodiment can provide user by way of acoustic control so that (such as user is by User Status
No is outgoing) phonetic controller 500 is informed, then decided whether according to use by phonetic controller 500
Family state adjusts the Permission Levels of authority information.From for another angle, the present embodiment is weighed by adjusting
Limit information is limiting access right of the user in staying out for control voice control device 500 and behaviour
Operation mode.
In another embodiment, when phonetic controller 500 receives the speech data of multiple users,
If judging, the user with access right high is in, and authority setting module 526 can be improved accordingly to be had
The Permission Levels of the authority information corresponding to the user of low access right.
First speech data and second user of first user are respectively received with phonetic controller 100
Second speech data in case of, if first user and second user are all validated user, and relatively
For second user, the Permission Levels of the corresponding authority information of first user are higher, then work as authority setting
When module 526 judges that the first prompt command includes words and expressions " at home ", authority setting module 526 can be by
" at home " record to the User Status of first user, and improve the power of the corresponding authority information of second user
Limit grade, for example, allow the function quantity of electronic installation 200 that second user can be operated by Voice command
Increase.
Above-mentioned situation can be represented with the flow chart of Fig. 7.Fig. 7 is the language shown by one embodiment of the invention
The flow chart of sound controlling method, its speech control system 50 for being applied to Fig. 5.
Fig. 7 is refer to, in step S702, voice communications module 522 receives the first speech data.
In step S704,524 pairs of the first speech datas of voice assistant module perform speech recognitions action to obtain the
Corresponding first voiceprint of one speech data and the first prompt command.In step S706, authority sets
Cover half block 526 according to the first voiceprint and the first prompt command, to determine the first voiceprint correspondence
The first authority information.Additionally, in step S708, voice communications module 522 receives the second voice number
According to.In step S710, voice assistant module 524 to second speech data perform speech recognition action with
Obtain corresponding second voiceprint of second speech data and the second prompt command.Wherein the second vocal print is believed
Breath is different from the first voiceprint.In step S712, authority setting module 526 is believed according to the second vocal print
Breath and the second prompt command, to determine corresponding second authority information of the second voiceprint.
Above-mentioned (i.e. step S702, S704, S706) the step of determine the first authority information and determine
The implementation detail of the step of two authority informations (i.e. step S708, S710, S712) is in previous embodiment
In be described in detail, therefore refer to foregoing.In addition it is noted that above-mentioned determine the first authority information
The step of and execution sequence the step of determine the second authority information can depending on the demand in practice, for example,
Step S708, S710, S712 can simultaneously or before be carried out with step S702, S704, S706, this hair
It is bright that this is not limited.
Then, in step S714, authority setting module 526 judges the corresponding user of the first voiceprint
Whether state records specific location information and whether the first authority information is higher than the second authority information.When first
The corresponding User Status of voiceprint records specific location information and the first authority information is believed higher than the second authority
During breath, in step S716, authority setting module 526 is according to the first authority information improving the second authority
The Permission Levels of information.And if the judged result of step S714 is no, in step S718, authority
Permission Levels of the setting module 526 not to the second authority information are adjusted.
In another embodiment, phonetic controller 500 can also control specific electronic devices in user view
(such as specific household electrical appliances), namely pick out prompt command and include the situation of a specific electronic devices 200
Under, remind the user of highest Permission Levels.Specifically, during control module 528 can determine whether prompt command
Whether the device information (such as title of electronic installation 200) of electronic installation 200 is included, if so, then
Control module 528 corresponds to the specific vocal print of highest Permission Levels in can searching the default vocal print, and incites somebody to action
Prompt message transmission user so far corresponding to specific vocal print.Above-mentioned prompt message can for example pass through user
User's set receive.Or, when control module 528 judges this user and phonetic controller 500
Itself is located at when in the middle of the same space, and control module 528 also can directly control the output list by device in itself
First (such as loudspeaker, screen, LED) points out this user.The present invention is not intended to limit prompt message
Presentation mode.
Additionally, in other embodiments, phonetic controller 500 can also be according to environmental information determining language
Control model of the sound control device 500 for electronic installation 200.Above-mentioned environmental information may include the time
Information, it is, for example, a time interval or a particular point in time.
For example, a kind of automatic operation mode of phonetic controller 500 is when phonetic controller 500
The validated user of access is allowed when all staying out, phonetic controller 500 can in the afternoon 6 when hold automatically
Open the light of entry.The sustainable detection time of control module 528, and when 6 in the afternoon, judge language
Sound control device 500 allows whether the User Status corresponding to the validated user of access is not recorded into
" at home " positional information.If being neither, control module 528 judges that these users stay out, and
Perform being automatically brought into operation for above-mentioned unlatching entry light.
Above-mentioned situation can be represented with the flow chart of Fig. 8.Fig. 8 is the language shown by one embodiment of the invention
The flow chart of sound controlling method, and suitable for the speech control system 50 of Fig. 5.
Fig. 8 is refer to, in step S802, when environmental information is detected for a particular point in time, control
Molding block 528 obtains default vocal print and distinguishes corresponding multiple User Status.In step S804, mould is controlled
Block 528 judges whether each User Status is set to specific location information.When the User Status all not by
When being set as specific location information, in step S806, control module 528 performs this particular point in time pair
The operator scheme answered is controlling electronic installation 200.
In another example, phonetic controller 500 may be placed at meeting room.Wherein, Voice command
The projecting apparatus and audio output that device 500 can provide voice control function to provide in user's control meeting room set
It is standby, and can be limited during lunch break user use above-mentioned voice control function.For example, general audio output sets
Standby output volume can allow user to be adjusted in an intensity interval, but during lunch break, user's then example
Such as limited and be only capable of by output volume control above-mentioned intensity interval maximum intensity half or following.
On the other hand, for the user with different rights information, during lunch break, phonetic controller
500 also optionally forbid the user with relatively low Permission Levels operated during lunch break projecting apparatus and
The institute of audio output apparatus is functional.
In other words, the control module 528 in above-mentioned example can detect environmental information whether meet one it is specific when
Between interval (during lunch break as escribed above), and when environmental information meet this special time it is interval when, control
Molding block 528 can be moved with limiting execution speech data according to authority information for the control of electronic installation 200
Make.
Based on the above embodiments, the embodiment of the present invention separately proposes a kind of sound control method.Refer to figure
9, Fig. 9 is the flow chart of the sound control method shown by one embodiment of the invention, and it is applied to Fig. 5's
Speech control system 50.In step S902, voice communications module 522 receives speech data.In step
In rapid S904, voice assistant module 524 performs speech recognition action to speech data to obtain speech data
Corresponding voiceprint and prompt command.In step S906, authority setting module 526 is according to vocal print
Information and prompt command, to determine the corresponding authority information of voiceprint.In step S908, control
Module 528 according to authority information, prompt command and environmental information at least one, with by area
Domain network control electronic installation 200.
In sum, voice can be arrived distal end by the embodiment of the present invention using voip technology by network transmission
Characteristic, will pass through the speech data that is received of world-wide web and bridge to voice assistant, allow the user can be in distal end
Operated come the voice assistant module to phonetic controller using voice, and then by voice assistant's mould
Block come control be located at the same area network in other electronic installations, so as to realize the distal end sound of voice assistant
Control function.Because speech recognition action is performed by phonetic controller, therefore what user's set was configured
Element can be simplified.On the other hand, the embodiment of the present invention can also confirm that user is using sound-groove identification
No is validated user, and sets different grades of access right to validated user.Additionally, passing through user's shape
State and/or environmental information are in time to adjust access right and judge current use situation, and the present invention is real
Applying example can further limit voice control function or the specific operation of automatic execution that phonetic controller is provided
Pattern.Thus, can make wired home can also take into account the behaviour under different situations while convenience is lifted
Make security.
Finally it should be noted that:Various embodiments above is merely illustrative of the technical solution of the present invention, rather than right
Its limitation;Although being described in detail to the present invention with reference to foregoing embodiments, this area it is common
Technical staff should be understood:It can still modify to the technical scheme described in foregoing embodiments,
Or equivalent is carried out to which part or all technical characteristic;And these modifications or replacement, and
The scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution is not made.
Claims (10)
1. a kind of sound control method, it is adaptable to be linked to the phonetic controller of Local Area Network, its feature
It is that the sound control method includes:
Speech data is received by world-wide web;
Speech recognition action is performed to the speech data to obtain the control instruction in the speech data;
The speech response information for reacting on the control instruction is transmitted by the world-wide web;And
According to the control instruction, an at least electronic installation is controlled by the Local Area Network.
2. sound control method according to claim 1, it is characterised in that by the Internet
The step of network receives the speech data includes:
Receive the speech data sent by the world-wide web by user's set.
3. sound control method according to claim 2, it is characterised in that by the Internet
The step of network transmission reacts on the speech response information of the control instruction includes:
The speech response information to the user's set is transmitted by the world-wide web.
4. sound control method according to claim 1, it is characterised in that the Voice command dress
Put including speech database, the multiple preset audio signals of speech database record, and to the voice
The step of data perform the speech recognition action to obtain the control instruction in the speech data is wrapped
Include:
Compare the preset audio signal that whether speech data meet in the speech database extremely
It is one of few;And
If so, the preset audio signal met with the speech data is considered as into the control instruction.
5. sound control method according to claim 1, it is characterised in that the Voice command dress
Put including voice print database and multiple speech databases, the voice print database record is multiple to preset vocal prints,
The default vocal print corresponds to the speech database, each multiple default sounds of speech database record respectively
Frequency signal, and speech recognition action is performed to the speech data with obtaining the speech data
The step of control instruction, includes:
According to the characteristic parameter of the speech data obtaining the voiceprint in the speech data;
Compare the voiceprint whether meet described default vocal print in the voice print database wherein it
One;
If so, the speech database corresponding to the default vocal print met with the voiceprint is obtained, and will
The speech database is considered as the corresponding particular phonetic database of the speech data;
Compare the preset audio signal during whether the speech data meets the particular phonetic database
At least one;And
If so, the preset audio signal met with the speech data is considered as into the control instruction.
6. sound control method according to claim 5, it is characterised in that also include:
It is updated with to the particular phonetic database according to input operation.
7. sound control method according to claim 1, it is characterised in that by the Internet
The step of network receives the speech data includes:
The speech data is received by application program.
8. sound control method according to claim 1, it is characterised in that the speech data is
Speech data based on the agreement of world-wide web voice.
9. sound control method according to claim 1, it is characterised in that the Voice command dress
Put including the output of voice communications module, system voice input module, voice assistant module and system voice
Module, wherein,
The voice communications module receives the speech data by the world-wide web, and by the voice
Data are provided to the system voice input module,
The system voice input module enters row format conversion to the speech data, and will turn by form
The speech data after changing is provided to the voice assistant module,
The voice assistant module produces the speech response information according to the control instruction, and will be described
Speech response information is provided to the system voice output module,
The system voice output module enters row format conversion to the speech response information, and will be by lattice
The speech response information after formula conversion is provided to the voice communications module, and
The voice communications module transmits the speech response information by the world-wide web.
10. a kind of speech control system, it is characterised in that including:
User's set, speech data is sent by world-wide web;
An at least electronic installation, including:
First communication unit, is linked to Local Area Network;And
Phonetic controller, including:
Second communication unit, is linked to the Local Area Network;
Memory cell, the multiple modules of record;And
Processing unit, couples second communication unit and the memory cell, is used to access simultaneously
The module recorded in the memory cell is performed, the module includes:
Voice communications module, the speech data is received by the world-wide web;And
Voice assistant module, speech recognition action is performed to the speech data to obtain
The control instruction in speech data is stated,
Wherein, the voice communications module is transmitted by the world-wide web and reacts on the control instruction
Speech response information, and the voice assistant module according to the control instruction with by the Local Area Network
An at least electronic installation described in control.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510815428.6A CN106782522A (en) | 2015-11-23 | 2015-11-23 | Sound control method and speech control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510815428.6A CN106782522A (en) | 2015-11-23 | 2015-11-23 | Sound control method and speech control system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106782522A true CN106782522A (en) | 2017-05-31 |
Family
ID=58886247
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510815428.6A Withdrawn CN106782522A (en) | 2015-11-23 | 2015-11-23 | Sound control method and speech control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106782522A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107825433A (en) * | 2017-10-27 | 2018-03-23 | 安徽硕威智能科技有限公司 | A kind of card machine people of children speech instruction identification |
CN110867182A (en) * | 2018-08-28 | 2020-03-06 | 仁宝电脑工业股份有限公司 | Control method of multi-voice assistant |
CN111081248A (en) * | 2019-12-27 | 2020-04-28 | 安徽仁昊智能科技有限公司 | Artificial intelligence speech recognition device |
CN111081257A (en) * | 2018-10-19 | 2020-04-28 | 珠海格力电器股份有限公司 | Voice acquisition method, device, equipment and storage medium |
CN111508485A (en) * | 2019-01-11 | 2020-08-07 | 纬创资通股份有限公司 | Electronic device and voice instruction recognition method thereof |
US11087754B2 (en) | 2018-09-27 | 2021-08-10 | Coretronic Corporation | Intelligent voice system and method for controlling projector by using the intelligent voice system |
US11100926B2 (en) | 2018-09-27 | 2021-08-24 | Coretronic Corporation | Intelligent voice system and method for controlling projector by using the intelligent voice system |
CN113421567A (en) * | 2021-08-25 | 2021-09-21 | 江西影创信息产业有限公司 | Terminal equipment control method and system based on intelligent glasses and intelligent glasses |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1324175A (en) * | 2000-05-11 | 2001-11-28 | 松下电工株式会社 | Speech control system for operating house keeping electric appliance |
CN103634194A (en) * | 2012-08-21 | 2014-03-12 | 无锡爱睿芯电子有限公司 | Long-distance voice remote control system and method thereof |
CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
CN104036778A (en) * | 2014-05-20 | 2014-09-10 | 安徽科大讯飞信息科技股份有限公司 | Equipment control method, device and system |
CN104885406A (en) * | 2012-12-18 | 2015-09-02 | 三星电子株式会社 | Method and device for controlling home device remotely in home network system |
-
2015
- 2015-11-23 CN CN201510815428.6A patent/CN106782522A/en not_active Withdrawn
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1324175A (en) * | 2000-05-11 | 2001-11-28 | 松下电工株式会社 | Speech control system for operating house keeping electric appliance |
CN103634194A (en) * | 2012-08-21 | 2014-03-12 | 无锡爱睿芯电子有限公司 | Long-distance voice remote control system and method thereof |
CN104885406A (en) * | 2012-12-18 | 2015-09-02 | 三星电子株式会社 | Method and device for controlling home device remotely in home network system |
CN103730120A (en) * | 2013-12-27 | 2014-04-16 | 深圳市亚略特生物识别科技有限公司 | Voice control method and system for electronic device |
CN104036778A (en) * | 2014-05-20 | 2014-09-10 | 安徽科大讯飞信息科技股份有限公司 | Equipment control method, device and system |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107825433A (en) * | 2017-10-27 | 2018-03-23 | 安徽硕威智能科技有限公司 | A kind of card machine people of children speech instruction identification |
CN110867182A (en) * | 2018-08-28 | 2020-03-06 | 仁宝电脑工业股份有限公司 | Control method of multi-voice assistant |
CN110867182B (en) * | 2018-08-28 | 2022-04-12 | 仁宝电脑工业股份有限公司 | Control method of multi-voice assistant |
US11087754B2 (en) | 2018-09-27 | 2021-08-10 | Coretronic Corporation | Intelligent voice system and method for controlling projector by using the intelligent voice system |
US11100926B2 (en) | 2018-09-27 | 2021-08-24 | Coretronic Corporation | Intelligent voice system and method for controlling projector by using the intelligent voice system |
CN111081257A (en) * | 2018-10-19 | 2020-04-28 | 珠海格力电器股份有限公司 | Voice acquisition method, device, equipment and storage medium |
CN111508485A (en) * | 2019-01-11 | 2020-08-07 | 纬创资通股份有限公司 | Electronic device and voice instruction recognition method thereof |
CN111508485B (en) * | 2019-01-11 | 2023-11-07 | 纬创资通股份有限公司 | Electronic device and voice instruction recognition method thereof |
CN111081248A (en) * | 2019-12-27 | 2020-04-28 | 安徽仁昊智能科技有限公司 | Artificial intelligence speech recognition device |
CN113421567A (en) * | 2021-08-25 | 2021-09-21 | 江西影创信息产业有限公司 | Terminal equipment control method and system based on intelligent glasses and intelligent glasses |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106773742B (en) | Sound control method and speech control system | |
CN106782522A (en) | Sound control method and speech control system | |
TWI557599B (en) | Voice control method and voice control system | |
USRE48569E1 (en) | Control method for household electrical appliance, household electrical appliance control system, and gateway | |
TW201717655A (en) | Voice control method and voice control system | |
CN105493180B (en) | Electronic device and method for speech recognition | |
KR102489914B1 (en) | Electronic Device and method for controlling the electronic device | |
US7464035B2 (en) | Voice control of home automation systems via telephone | |
CN108172223A (en) | Voice instruction recognition method, device and server and computer readable storage medium | |
KR102421824B1 (en) | Electronic device for providing voice based service using external device and operating method thereof, the external device and operating method thereof | |
CN112331196A (en) | Electronic device for managing a plurality of intelligent agents and method of operating the same | |
KR102326272B1 (en) | Electronic device for network setup of external device and operating method thereof | |
CN109474658A (en) | Electronic equipment, server and the recording medium of task run are supported with external equipment | |
US20200135202A1 (en) | Electronic device and control method thereof | |
US10236016B1 (en) | Peripheral-based selection of audio sources | |
CN107688329A (en) | Intelligent home furnishing control method and intelligent home control system | |
EP3422344B1 (en) | Electronic device for performing operation corresponding to voice input | |
JP2004214895A (en) | Auxiliary communication apparatus | |
CN112567718A (en) | Electronic device for performing tasks including calls in response to user speech and method of operation | |
KR20190059509A (en) | Electronic apparatus and the control method thereof | |
Arya et al. | Implementation of Google Assistant & Amazon Alexa on Raspberry Pi | |
CN106453922A (en) | Scene mode setting method and device, and terminal | |
KR20210061091A (en) | Electronic device for providing intelligent assistance service and operating method thereof | |
CN109819297A (en) | A kind of method of controlling operation thereof and set-top box | |
KR20220118698A (en) | Electronic device for supporting artificial intelligence agent services to talk to users |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170531 |
|
WW01 | Invention patent application withdrawn after publication |