CN109617772A - A kind of smart home system based on speech recognition - Google Patents
A kind of smart home system based on speech recognition Download PDFInfo
- Publication number
- CN109617772A CN109617772A CN201811508847.5A CN201811508847A CN109617772A CN 109617772 A CN109617772 A CN 109617772A CN 201811508847 A CN201811508847 A CN 201811508847A CN 109617772 A CN109617772 A CN 109617772A
- Authority
- CN
- China
- Prior art keywords
- vocal print
- print feature
- semantic
- sample
- smart home
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000001755 vocal effect Effects 0.000 claims abstract description 67
- 238000000605 extraction Methods 0.000 claims description 19
- 238000013507 mapping Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G10L15/26—Speech to text systems
-
- 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
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a kind of smart home systems based on speech recognition, including voice collecting terminal, smart home device, intelligent gateway and voice remote controller.The present invention uses the speech recognition of vocal print feature matching way, it eliminates in actual life since the local dialect, accent, word speed do not manipulate erroneous judgement problem due to cognation etc. even caused by smart home device, the universality of user speech instruction is improved, also realizes the off-line operation of simple challenge;Simultaneously by customized semantic matching function, also efficiently solve the problems, such as instruction go beyond one's commission, it is semantic be directed toward it is unknown caused by cross-over control mistake.
Description
Technical field
The present invention relates to Intelligent housing fields, and in particular to a kind of smart home system based on speech recognition.
Background technique
With the continuous development of intelligent Computation Technology, human society is increasingly intended to intelligence, and intelligentized household is set
Standby more and more to come into daily life, smart home can allow resident to have more convenient means to manage
Housed device, therefore liked deeply by users.
Traditional smart home system control mode mostly uses greatly integrated chip control, but with cloud computing and speech recognition
Control instruction is extended to complicated language from single password by the development of technology, the intelligent sound identification technology based on cloud system
Justice, and then more control functions and rich experience are assigned for smart home.It is existing on the market to be based on but for user
There is also numerous deficiencies for the smart home system of speech recognition, such as exist and go out because phonetic order is directed toward the unknown home equipment that will cause
Show cross-over control mistake and because the problems such as control system can not be identified correctly caused by being mingled with the local dialect in user speech instruction.
Summary of the invention
The invention solves in the prior art because semanteme be directed toward it is unknown due to caused by cross-over control mistake and because of not Tongfang
Speech, the different tone, the not big problem of speech recognition universality difference and error caused by the reasons such as cognation, to provide a kind of base
In the smart home system of speech recognition.
In order to solve the above technical problems, the technical solution adopted in the present invention is as follows:
A kind of smart home system based on speech recognition, including voice collecting terminal, smart home device, intelligent gateway and
Voice remote controller.
The voice collecting terminal, the sample voice for acquiring user are instructed and are transferred in intelligent gateway.
Voice remote controller, typing user's order phonetic order, and be transmitted in intelligent gateway.
The intelligent gateway, including vocal print feature extraction module, sample vocal print feature library, semantic mapping module, control language
Adopted literal pool, Pattern Matching Module, instruction control module, authority management module.
Authority management module distributes the permission of each smart home device to user.
Vocal print feature extraction module instructs sample voice and carries out feature extraction, obtains sample vocal print feature, and be stored in
In sample vocal print feature library;Feature extraction is carried out to order phonetic order, obtains order vocal print feature.
Pattern Matching Module matches order vocal print feature and sample vocal print feature.
Sample vocal print feature and the control semanteme text controlled in semantic literal pool match pair by semantic mapping module
It answers.
Semantic literal pool is controlled, the control semanteme text of setting is stored.
Control semantic conversion is specifically to control signal and be transferred to corresponding smart home to set by instruction control module
It is standby.
Specifically, the sample voice instruction latter aspect that intelligent gateway receives acquisition is obtained by vocal print feature extraction module
Sample vocal print feature is simultaneously stored in sample vocal print feature library.
On the other hand semantic text will be controlled in sample vocal print feature and the semantic literal pool of control by semantic mapping module
Between carry out semantic pairing.
Intelligent gateway passes through the progress feature extraction of vocal print feature extraction module after receiving order phonetic order, obtains order
Vocal print feature.
Order vocal print feature is matched with sample vocal print feature by Pattern Matching Module, is passed through if successful match
Authority management module judges whether currently used person has permission.
If so, then obtaining order vocal print feature, sample vocal print feature and controlling the ternary mapping relations between semantic text.
And will control semantic text conversion by instruction control module is control signal, is sent control signals to corresponding
Smart home device.
In the present invention, the voice remote controller is at least one, and the different zones of family place different voice remote controls
Device, each voice remote controller can control the smart home device in each region.
The present invention identifies the phonetic order that user is issued by the way of semantic pairing and pattern match, effectively solution because
Semanteme be directed toward it is unknown and caused by cross-over control mistake and because of different dialects, the different tone, not language caused by the reasons such as cognation
Sound identifies universality difference and the big problem of error, and can identify simple semanteme in disconnection mode, and realization sets smart home
It is standby to carry out local off-line operation.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is present system structure chart.
Fig. 2 is speech recognition schematic diagram of the present invention.
Fig. 3 is multizone voice control schematic diagram of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under that premise of not paying creative labor
Embodiment shall fall within the protection scope of the present invention.
A kind of smart home system based on speech recognition, as shown in Figs. 1-2, including voice collecting terminal, smart home
Equipment, intelligent gateway and voice remote controller.
The voice collecting terminal, the sample voice for acquiring user are instructed and are transferred in intelligent gateway.
Voice remote controller, typing user's order phonetic order, and be transmitted in intelligent gateway.
The intelligent gateway, including vocal print feature extraction module, sample vocal print feature library, semantic mapping module, control language
Adopted literal pool, Pattern Matching Module, instruction control module, authority management module.
Authority management module distributes the permission of each smart home device to user.
Vocal print feature extraction module instructs sample voice and carries out feature extraction, obtains sample vocal print feature, and be stored in
In sample vocal print feature library;Feature extraction is carried out to order phonetic order, obtains order vocal print feature.
Pattern Matching Module matches order vocal print feature and sample vocal print feature.
Sample vocal print feature and the control semanteme text controlled in semantic literal pool match pair by semantic mapping module
It answers.
Semantic literal pool is controlled, the control semanteme text of setting is stored.
Control semantic conversion is specifically to control signal and be transferred to corresponding smart home to set by instruction control module
It is standby.
Application method of the invention are as follows:
Voice collecting terminal can be the mobile phone or plate for having the support interactive operation of screen, acquire the sample voice of user
It instructs and is transferred in intelligent gateway, the sample voice instruction latter aspect that intelligent gateway receives acquisition is extracted by vocal print feature
Module obtains sample vocal print feature and is stored in sample vocal print feature library.
On the other hand semantic text will be controlled in sample vocal print feature and the semantic literal pool of control by semantic mapping module
Between carry out semantic pairing.
Sample vocal print feature library, the vocal print feature including place and function.For example, it " turns off the light in bedroom ", in acquisition sample
When this vocal print feature, for " bedroom " this place, individually storage has its sample vocal print feature, for " turning off the light " this function
Can, same individually storage has its a sample vocal print feature, and the sample vocal print of place and function still match one by one it is corresponding.
Voice remote controller, typing user's order phonetic order, and be transmitted in intelligent gateway, intelligent gateway passes through vocal print
Characteristic extracting module carries out feature extraction to order phonetic order, obtains order vocal print feature.
Order vocal print feature is matched with sample vocal print feature by Pattern Matching Module, is passed through if successful match
Authority management module judges whether currently used person has permission;If so, then obtain order vocal print feature, sample vocal print feature and
Control the ternary mapping relations between semantic text.
It is control signal that semantic text conversion, which will be controlled, by instruction control module, and is sent control signals to corresponding
Smart home device.
Because intelligent gateway device is integrated with all kinds of communication modules, the smart home device of different access ways can be carried out
It is uniformly accessed into management.
The present invention by authority management module can it is customized to user distribution smart home device control authority, avoid house
Certain home equipment bring security risks are used alone in the case where nobody accompanies by middle child or old man.
In the present invention, the voice remote controller includes multiple voice remote controllers, and the different zones of family are placed different
Voice remote controller, individual voice remote controler is not bound one by one with equipment, and can all control the home equipment in each region,
As shown in Figure 3.
Intelligent gateway of the present invention has voice semantic processes and signal relay function.
When user is when parlor issues " turning off the light in bedroom ", intelligent gateway is in addition to doing the voice of " turning off the light ", semanteme is arrived and controlled
Other than the conversion for making instruction, also by the Application on Voiceprint Recognition to " bedroom " this object, and bedroom is matched one by one with control semanteme,
Then intelligent gateway uses point-to-point communication mechanism, sends " turning off the light " signal and gives bedroom lamp object, realizes that bedroom is turned off the light.
The present invention is by acquiring vocal print feature in advance and saving, and after phonetic order is sent, intelligent gateway only need to be by voice
The vocal print feature of instruction is compared with the vocal print feature prestored, sends control instruction if consistent, for some simple
Instruction, the present invention can also be handled offline.
Embodiment of above is only used for the description of this invention, rather than limitation of the present invention.To those skilled in the art
It carrying out variation or modification appropriate is without departing from the scope of the invention it will be apparent that therefore all equivalent skills for member
Art scheme also belongs to scope of the invention, and scope of patent protection of the invention is defined by the following claims.
Claims (4)
1. a kind of smart home system based on speech recognition, it is characterised in that: set including voice collecting terminal, smart home
Standby, intelligent gateway and voice remote controller;The voice collecting terminal, the sample voice for acquiring user instruct and are transferred to intelligence
In gateway;Voice remote controller, typing user's order phonetic order, and be transmitted in intelligent gateway;
The intelligent gateway, including vocal print feature extraction module, sample vocal print feature library, semantic mapping module, the semantic text of control
Character library, Pattern Matching Module, instruction control module, authority management module;
Authority management module distributes the permission of each smart home device to user;
Vocal print feature extraction module instructs sample voice and carries out feature extraction, obtains sample vocal print feature, and be stored in sample
In vocal print feature library;Feature extraction is carried out to order phonetic order, obtains order vocal print feature;
Pattern Matching Module matches order vocal print feature and sample vocal print feature;
It is corresponding with the control semanteme text controlled in semantic literal pool to be carried out matching by semantic mapping module for sample vocal print feature;
Semantic literal pool is controlled, the control semanteme text of setting is stored;
Control semantic conversion is specific control signal and is transferred to corresponding smart home device by instruction control module.
2. the smart home system according to claim 1 based on speech recognition, it is characterised in that: intelligent gateway reception is adopted
The sample voice instruction latter aspect of collection obtains sample vocal print feature by vocal print feature extraction module and is stored in sample vocal print
In feature database;
On the other hand it by sample vocal print feature and is controlled in semantic literal pool between the semantic text of control by semantic mapping module
Carry out semantic pairing.
3. the smart home system according to claim 2 based on speech recognition, it is characterised in that: intelligent gateway receives
Feature extraction is carried out by vocal print feature extraction module after order phonetic order, obtains order vocal print feature;
Order vocal print feature is matched with sample vocal print feature by Pattern Matching Module, passes through permission if successful match
Management module judges whether currently used person has permission;
If so, then obtaining order vocal print feature, sample vocal print feature and controlling the ternary mapping relations between semantic text;
And will control semantic text conversion by instruction control module is control signal, sends control signals to corresponding intelligence
Home equipment.
4. the smart home system according to claim 1 to 3 based on speech recognition, it is characterised in that: institute's predicate
Voice remote control device is at least one, and the different zones of family place different voice remote controllers, and each voice remote controller can control
The smart home device in each region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811508847.5A CN109617772A (en) | 2018-12-11 | 2018-12-11 | A kind of smart home system based on speech recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811508847.5A CN109617772A (en) | 2018-12-11 | 2018-12-11 | A kind of smart home system based on speech recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109617772A true CN109617772A (en) | 2019-04-12 |
Family
ID=66007699
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811508847.5A Pending CN109617772A (en) | 2018-12-11 | 2018-12-11 | A kind of smart home system based on speech recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109617772A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134022A (en) * | 2019-05-10 | 2019-08-16 | 平安科技(深圳)有限公司 | Audio control method, device and the electronic device of smart home device |
CN110719662A (en) * | 2019-10-29 | 2020-01-21 | 横店集团得邦照明股份有限公司 | Sound control LED lighting system with deep learning capability |
CN110956965A (en) * | 2019-12-12 | 2020-04-03 | 电子科技大学 | Personalized intelligent home safety control system and method based on voiceprint recognition |
CN111048072A (en) * | 2019-11-21 | 2020-04-21 | 中国南方电网有限责任公司 | Voiceprint recognition method applied to power enterprises |
CN111933149A (en) * | 2020-08-11 | 2020-11-13 | 北京声智科技有限公司 | Voice interaction method, wearable device, terminal and voice interaction system |
CN112180746A (en) * | 2020-09-02 | 2021-01-05 | 珠海格力电器股份有限公司 | Home equipment control method and device based on gateway, storage medium and gateway |
CN112218412A (en) * | 2019-07-10 | 2021-01-12 | 上汽通用汽车有限公司 | In-vehicle atmosphere lamp control system and control method based on voice recognition |
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 (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778946A (en) * | 2014-01-10 | 2015-07-15 | 中国电信股份有限公司 | Voice control method and system |
CN106847281A (en) * | 2017-02-26 | 2017-06-13 | 上海新柏石智能科技股份有限公司 | Intelligent household voice control system and method based on voice fuzzy identification technology |
CN108305623A (en) * | 2018-01-15 | 2018-07-20 | 珠海格力电器股份有限公司 | Electric control method and device |
CN108766424A (en) * | 2018-05-28 | 2018-11-06 | 深圳市天乔科技有限公司 | Smart home intelligent sound learning control method |
-
2018
- 2018-12-11 CN CN201811508847.5A patent/CN109617772A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778946A (en) * | 2014-01-10 | 2015-07-15 | 中国电信股份有限公司 | Voice control method and system |
CN106847281A (en) * | 2017-02-26 | 2017-06-13 | 上海新柏石智能科技股份有限公司 | Intelligent household voice control system and method based on voice fuzzy identification technology |
CN108305623A (en) * | 2018-01-15 | 2018-07-20 | 珠海格力电器股份有限公司 | Electric control method and device |
CN108766424A (en) * | 2018-05-28 | 2018-11-06 | 深圳市天乔科技有限公司 | Smart home intelligent sound learning control method |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110134022A (en) * | 2019-05-10 | 2019-08-16 | 平安科技(深圳)有限公司 | Audio control method, device and the electronic device of smart home device |
CN112218412A (en) * | 2019-07-10 | 2021-01-12 | 上汽通用汽车有限公司 | In-vehicle atmosphere lamp control system and control method based on voice recognition |
CN110719662A (en) * | 2019-10-29 | 2020-01-21 | 横店集团得邦照明股份有限公司 | Sound control LED lighting system with deep learning capability |
CN111048072A (en) * | 2019-11-21 | 2020-04-21 | 中国南方电网有限责任公司 | Voiceprint recognition method applied to power enterprises |
CN110956965A (en) * | 2019-12-12 | 2020-04-03 | 电子科技大学 | Personalized intelligent home safety control system and method based on voiceprint recognition |
CN111933149A (en) * | 2020-08-11 | 2020-11-13 | 北京声智科技有限公司 | Voice interaction method, wearable device, terminal and voice interaction system |
CN112180746A (en) * | 2020-09-02 | 2021-01-05 | 珠海格力电器股份有限公司 | Home equipment control method and device based on gateway, storage medium and gateway |
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 |
---|---|---|
CN109617772A (en) | A kind of smart home system based on speech recognition | |
CN105446159B (en) | Intelligent domestic system and its data processing method | |
CN103093755B (en) | Based on terminal and mutual network household electric appliance control method and the system of internet voice | |
CN204613722U (en) | One can voice-operated intelligent cloud life staying idle at home system | |
CN103188538A (en) | Household appliance control method and system based on smart television equipment and Internet | |
CN106249614A (en) | Intelligent terminal, intelligent domestic system, audio recognition method and ordering method | |
CN203232565U (en) | Multifunctional remote network remote controller | |
CN106023995A (en) | Voice recognition method and wearable voice control device using the method | |
CN101794126A (en) | Wireless intelligent home appliance voice control system | |
CN110095992A (en) | Smart home system based on wechat small routine | |
CN108833229B (en) | A kind of intelligent home control system of speech identifying function | |
CN208561316U (en) | A kind of voice interactive system and the elevator using voice interactive system | |
CN108204656A (en) | A kind of air conditioning control method based on cloud lock, system | |
CN110120222A (en) | A kind of voice broadcast method of the smart mirror cabinet with voice broadcast function | |
CN101917530A (en) | Telephone remote key-press and voice double mode controller | |
CN102847325A (en) | Toy control method and system based on voice interaction of mobile communication terminal | |
CN205620724U (en) | Intelligence pronunciation remote control system | |
CN107818782A (en) | A kind of method and system for realizing household electrical appliance intelligent control | |
CN107347026A (en) | A kind of wisdom steward system based on wechat public platform | |
CN204791241U (en) | Voice interaction formula access control system | |
CN102868740A (en) | Method and system for controlling toy based on mobile communication terminal and internet voice interaction | |
CN106354112A (en) | Speed recognition and control system used for smart home devices | |
CN109308898A (en) | A kind of dialect phonetic recognition methods, device, terminal and its storage medium | |
CN205376116U (en) | Automatic dolly remote control unit that guides of wireless directional speech control | |
CN205193468U (en) | Sound -controlled apparatus of intelligence house |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |