CN208737877U - Internet of Things speech control system - Google Patents
Internet of Things speech control system Download PDFInfo
- Publication number
- CN208737877U CN208737877U CN201820509635.8U CN201820509635U CN208737877U CN 208737877 U CN208737877 U CN 208737877U CN 201820509635 U CN201820509635 U CN 201820509635U CN 208737877 U CN208737877 U CN 208737877U
- Authority
- CN
- China
- Prior art keywords
- speech recognition
- recognition equipment
- acoustics
- voice
- internet
- 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.)
- Active
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The utility model relates to a kind of Internet of Things speech control systems, and including at least one device in the first speech recognition equipment and the second speech recognition equipment, first speech recognition equipment includes acoustics interpolater, acoustics fraction transformation device and decoder；Second speech recognition equipment includes acoustics interpolater, acoustics fraction transformation device and decoder；When the first voice that first speech recognition equipment obtains includes predetermined command, the second voice for additionally identifying it is identified by external electronic, when the first voice that second speech recognition equipment obtains includes predetermined command, the second voice for additionally identifying it is identified, and second speech recognition equipment is for executing the corresponding operation of second voice.Thus multiple speech recognition equipments can identify the phonetic control command of user respectively, and user only passes through transmission voice and can control the first speech recognition equipment.
Description
Technical field
The utility model relates to Internet of Things controls, more particularly to a kind of Internet of Things speech control system easy to operate.
Background technique
With the continuous development of science and technology, the type of household electrical appliance is more and more many and diverse, and the control of Internet of Things is also more complicated.Object
Networking is the important component of generation information technology, and the important development stage in " informationization " epoch.User terminal extends
And extend between any article and article, information exchange and communication are carried out, that is, object object mutually ceases.Internet of Things passes through intelligence
Perception, identification technology and general fit calculation etc. communicate cognition technology, are widely used in the fusion of network.Internet of Things is internet
Application extension, rather than Internet of Things is network, Internet of Things is business and application.Therefore, all household electrical appliance are accessed
After Internet of Things, user is increasingly complex to the operation control of household electrical appliance.
Utility model content
Based on this, it is necessary to provide a kind of Internet of Things speech control system easy to operate.
A kind of Internet of Things speech control system, including in the first speech recognition equipment and the second speech recognition equipment at least
One device, first speech recognition equipment include acoustics interpolater, acoustics fraction transformation device and decoder；Described
Two speech recognition equipments include acoustics interpolater, acoustics fraction transformation device and decoder；
The acoustics interpolater is used to calculate the acoustics score of voice input according to acoustic model；The acoustics point
A/D converter is used for according to running parameter, is acoustics score corresponding with standard pronunciation by the acoustics fraction transformation；The solution
Code device is used to export the recognition result of voice input according to the acoustics score of transformation；
Wherein, when the first voice that first speech recognition equipment obtains includes predetermined command, additionally identify second
Voice is identified by external electronic, when the first voice that second speech recognition equipment obtains includes predetermined command,
The second voice additionally identified is identified, and second speech recognition equipment is for executing the corresponding behaviour of second voice
Make.
In one of the embodiments, in first speech recognition equipment and second speech recognition equipment at least
One device executes corresponding operation based on the second voice identified by external electronic.
It in one of the embodiments, further include language score calculator, the language score calculator is used for according to language
Model is sayed to export the language score of voice input, the decoder is used for the acoustics score according to the language score and transformation
It is decoded, and exports recognition result.
In one of the embodiments, further include feedback collection device, the feedback collection device be used for according to user feedback come
Acquire the verify data about recognition result.
It in one of the embodiments, further include training aids, the training aids is by according to based on by acoustics interpolater
The acoustics score of calculation and the verify data of acquisition carry out sudden peal of thunder running parameter again, and transformation ginseng is updated based on the re -training
Number.
In one of the embodiments, the training aids for will the acoustics score that is calculated and acquisition verify data transmission
Transformation parameter is updated to training equipment and by receiving the transformation parameter of re -training from training equipment.
In one of the embodiments, further include: nodal terminal device and display device；
The nodal terminal device is used to connect first speech recognition equipment and second speech recognition equipment, and
Acquire the sensing data of first speech recognition equipment and second speech recognition equipment；
The display device is used to receive sensing data from the nodal terminal device, and is determined according to the sensing data
The mode of operation of first speech recognition equipment and second speech recognition equipment, and it is shown in user interface.
In one of the embodiments, the display device executed according to the pairing request of the nodal terminal device with
The pairing of the nodal terminal device, and the sensing data in response to receiving peripheral equipment from the nodal terminal device of distribution,
External server is sent by the sensing data simultaneously, the facility information of peripheral equipment is received from the external server.
First speech recognition equipment, second speech recognition equipment are in one of the embodiments, with channel radio
The mode and peripheral equipment of news carry out data interaction.
First speech recognition equipment includes the household electrical appliance with speech recognition in one of the embodiments,；
Second speech recognition equipment includes the household electrical appliance with speech recognition.
Above-mentioned Internet of Things speech control system, including in the first speech recognition equipment and the second speech recognition equipment at least
One device, first speech recognition equipment include acoustics interpolater, acoustics fraction transformation device and decoder；Described
Two speech recognition equipments include acoustics interpolater, acoustics fraction transformation device and decoder；First speech recognition equipment
The first voice obtained when including predetermined command, the second voice additionally identified are identified by external electronic, and described the
The first voice that two speech recognition equipments obtain when including predetermined command, the second voice additionally identified are identified, and described the
Two speech recognition equipments are for executing the corresponding operation of second voice.Thus multiple speech recognition equipments can identify respectively
The phonetic control command of user, and user only passes through transmission voice and can control the first speech recognition equipment.
Detailed description of the invention
Fig. 1 is the module map of Internet of Things speech control system.
Specific embodiment
The utility model is more fully retouched below with reference to relevant drawings for the ease of understanding the utility model,
It states.The preferred embodiment of the utility model is given in attached drawing.But the utility model can come in many different forms in fact
It is existing, however it is not limited to embodiment described herein.On the contrary, purpose of providing these embodiments is makes public affairs to the utility model
The understanding for opening content is more thorough and comprehensive.
Unless otherwise defined, all technical and scientific terms used herein are led with the technology for belonging to the utility model
The normally understood meaning of the technical staff in domain is identical.Terminology used in the description of the utility model herein only be
The purpose of description specific embodiment, it is not intended that limitation the utility model.Term as used herein "and/or" includes one
Any and all combinations of a or multiple relevant listed items.
As shown in Figure 1, being the module map of Internet of Things speech control system.
A kind of Internet of Things speech control system, including in the first speech recognition equipment 10 and the second speech recognition equipment 20
At least one device, first speech recognition equipment 10 include acoustics interpolater 301, acoustics fraction transformation device 302 and
Decoder 303；Second speech recognition equipment includes acoustics interpolater 301, acoustics fraction transformation device 302 and decoder
303；
The acoustics interpolater 301 is used to calculate the acoustics score of voice input according to acoustic model；The sound
Credit A/D converter 302 is used for according to running parameter, is acoustics score corresponding with standard pronunciation by the acoustics fraction transformation；
The decoder 303 is used to export the recognition result of voice input according to the acoustics score of transformation；
Wherein, when the first voice that first speech recognition equipment 10 obtains includes predetermined command, additionally identify the
Two voices are identified by external electronic, and the first voice that second speech recognition equipment 20 obtains includes predetermined command
When, the second voice for additionally identifying it is identified, and second speech recognition equipment 20 is corresponding for executing second voice
Operation.
In the present embodiment, the first speech recognition equipment 10 and the second speech recognition equipment 20 are the family with speech recognition
Electrical appliance, therefore, when identifying multiple voices at the same time, 10/ second speech recognition equipment 20 of the first speech recognition equipment is identified
After first voice, the second voice can be identified by mobile terminal, i.e. 10/ second speech recognition equipment of the first speech recognition equipment
20 execute the corresponding operation of the first voice, and mobile terminal then executes or postpone the corresponding operation of the second voice.
For example, after 10/ second speech recognition equipment 20 of the first speech recognition equipment obtains the instruction turned on light and be switched on, the
One speech recognition equipment, 10/ second speech recognition equipment 20 executes instruction of turning on light, and power-on instruction is being sent to mobile terminal, by
Mobile terminal controls the household electrical appliance needed in the Internet of Things that is switched on.
At least one device in first speech recognition equipment 10 and second speech recognition equipment 20 be based on by
Second voice of external electronic identification executes corresponding operation.
Internet of Things speech control system further includes language score calculator, and the language score calculator is used for according to language
Model exports the language score of voice input, and the decoder 303 is used for according to the language score and the acoustics of transformation point
Number is decoded, and exports recognition result.
Internet of Things speech control system further includes feedback collection device, and the feedback collection device according to user feedback for adopting
Collect the verify data about recognition result.
Internet of Things speech control system further includes training aids, and the training aids is used for according to by acoustics interpolater 301
The acoustics score of calculating and the verify data of acquisition carry out sudden peal of thunder running parameter again, and transformation is updated based on the re -training
Parameter.
Training aids is used to send the verify data of the acoustics score of calculating and acquisition to trained equipment and by from training
Equipment receives the transformation parameter of re -training to update transformation parameter.
Internet of Things speech control system further include: nodal terminal device and display device；
The nodal terminal device is for connecting first speech recognition equipment 10 and second speech recognition equipment
20, and acquire the sensing data of first speech recognition equipment 10 and second speech recognition equipment 20；
The display device is used to receive sensing data from the nodal terminal device, and is determined according to the sensing data
The mode of operation of first speech recognition equipment 10 and second speech recognition equipment 20, and it is shown in user interface.
Display device executes the pairing with the nodal terminal device according to the pairing request of the nodal terminal device,
And the sensing data in response to receiving peripheral equipment from the nodal terminal device of distribution, while sending the sensing data to outside
Portion's server receives the facility information of peripheral equipment from the external server.
First speech recognition equipment 10, second speech recognition equipment 20 in a manner of wireless telecommunications and peripheral equipment into
Row data interaction.
First speech recognition equipment 10 includes the household electrical appliance with speech recognition；
Second speech recognition equipment 20 includes the household electrical appliance with speech recognition.
Specifically, the phonetic order that 10/ second speech recognition equipment 20 of the first speech recognition equipment can be issued by user
It directly controls, can also be controlled by mobile terminal by Internet of Things.
For example, voice sound equipment, which directly can issue voice by user, carries out control start and close, selection specific music, tune
Save the operation such as volume.Can also be controlled by mobile terminal networking, by mobile terminal boot up shutdown, selection specific music,
Adjust the operation such as volume
Above-mentioned Internet of Things speech control system, including in the first speech recognition equipment 10 and the second speech recognition equipment 20
At least one device, first speech recognition equipment 10 include acoustics interpolater 301, acoustics fraction transformation device 302 and
Decoder 303；Second speech recognition equipment 20 includes acoustics interpolater 301, acoustics fraction transformation device 302 and decoding
Device 303；When the first voice that first speech recognition equipment 10 obtains includes predetermined command, the second voice for additionally identifying it is logical
It crosses external electronic to be identified, when the first voice that second speech recognition equipment 20 obtains includes predetermined command, additionally
Second voice of identification is identified, and second speech recognition equipment 20 is for executing the corresponding operation of second voice.
Thus multiple speech recognition equipments can identify the phonetic control command of user respectively, and user only pass through send voice can
First speech recognition equipment 10 is controlled.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
Above-described embodiments merely represent several embodiments of the utility model, the description thereof is more specific and detailed,
But it cannot be understood as the limitations to utility model patent range.It should be pointed out that for the common skill of this field
For art personnel, without departing from the concept of the premise utility, various modifications and improvements can be made, these are belonged to
The protection scope of the utility model.Therefore, the scope of protection shall be subject to the appended claims for the utility model patent.
Claims (9)
1. a kind of Internet of Things speech control system, including at least one in the first speech recognition equipment and the second speech recognition equipment
A device, which is characterized in that first speech recognition equipment includes acoustics interpolater, acoustics fraction transformation device and decoding
Device；Second speech recognition equipment includes acoustics interpolater, acoustics fraction transformation device and decoder；
The acoustics interpolater is used to calculate the acoustics score of voice input according to acoustic model；The acoustics score becomes
Parallel operation is used for according to running parameter, is acoustics score corresponding with standard pronunciation by the acoustics fraction transformation；The decoder
For exporting the recognition result of voice input according to the acoustics score of transformation；
Wherein, when the first voice that first speech recognition equipment obtains includes predetermined command, the second voice for additionally identifying
It is identified by external electronic, when the first voice that second speech recognition equipment obtains includes predetermined command, additionally
Second voice of identification is identified by external electronic；
At least one device in first speech recognition equipment and second speech recognition equipment is based on by external electrical
Second voice of device identification executes corresponding operation.
2. Internet of Things speech control system according to claim 1, which is characterized in that it further include language score calculator,
The language score calculator is used to export the language score of voice input according to language model, and the decoder is used for basis
The language score and the acoustics score of transformation are decoded, and export recognition result.
3. Internet of Things speech control system according to claim 1, which is characterized in that it further include feedback collection device, it is described
Feedback collection device is used to acquire the verify data about recognition result according to user feedback.
4. Internet of Things speech control system according to claim 3, which is characterized in that it further include training aids, the training
Device is used for according to the acoustics score calculated by acoustics interpolater and the verify data of acquisition come re -training transformation parameter, and
Transformation parameter is updated based on the re -training.
5. Internet of Things speech control system according to claim 4, which is characterized in that the training aids was used to calculate
Acoustics score and the verify data of acquisition are sent to trained equipment and the transformation parameter by receiving re -training from training equipment
To update transformation parameter.
6. Internet of Things speech control system according to claim 1, which is characterized in that further include: nodal terminal device and
Display device；
The nodal terminal device is acquired for connecting first speech recognition equipment and second speech recognition equipment
The sensing data of first speech recognition equipment and second speech recognition equipment；
The display device is used to receive sensing data from the nodal terminal device, and according to sensing data determination
The mode of operation of first speech recognition equipment and second speech recognition equipment, and it is shown in user interface.
7. Internet of Things speech control system according to claim 6, which is characterized in that the display device is according to the section
The pairing request of terminal installation is put to execute the pairing with the nodal terminal device, and in response to filling from the nodal terminal of distribution
The sensing data for receiving peripheral equipment are set, while sending external server for the sensing data, from the external server
Receive the facility information of peripheral equipment.
8. Internet of Things speech control system according to claim 1, which is characterized in that first speech recognition equipment,
Second speech recognition equipment carries out data interaction with peripheral equipment in a manner of wireless telecommunications.
9. Internet of Things speech control system according to claim 1, which is characterized in that the first speech recognition equipment packet
Include the household electrical appliance with speech recognition；
Second speech recognition equipment includes the household electrical appliance with speech recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820509635.8U CN208737877U (en) | 2018-04-11 | 2018-04-11 | Internet of Things speech control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820509635.8U CN208737877U (en) | 2018-04-11 | 2018-04-11 | Internet of Things speech control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208737877U true CN208737877U (en) | 2019-04-12 |
Family
ID=66021854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201820509635.8U Active CN208737877U (en) | 2018-04-11 | 2018-04-11 | Internet of Things speech control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208737877U (en) |
-
2018
- 2018-04-11 CN CN201820509635.8U patent/CN208737877U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109634132A (en) | Smart home management method, device, medium and electronic equipment | |
| CN106773742B (en) | Sound control method and speech control system | |
| CN108335696A (en) | Voice awakening method and device | |
| CN108899023A (en) | control method and device | |
| CN105847099B (en) | Internet of things implementation system and method based on artificial intelligence | |
| CN110134022A (en) | Audio control method, device and the electronic device of smart home device | |
| CN109818839A (en) | Personalized behavior prediction methods, devices and systems applied to smart home | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN204613722U (en) | One can voice-operated intelligent cloud life staying idle at home system | |
| CN107748500A (en) | Method and apparatus for controlling smart machine | |
| CN105723360A (en) | Improving natural language interactions using emotional modulation | |
| CN108028044A (en) | The speech recognition system of delay is reduced using multiple identifiers | |
| CN102736536A (en) | Method and device for voice control of electrical equipment | |
| KR20120066523A (en) | Method of recognizing voice and system for the same | |
| CN107733762B (en) | Voice control method, device and system for smart home | |
| CN109737521A (en) | Air purifier with voice control function | |
| CN103546790A (en) | Language interaction method and language interaction system on basis of mobile terminal and interactive television | |
| CN103208285A (en) | Household electrical appliance control method and system based on voice interaction of mobile communication terminals | |
| Jimenez et al. | Alexa-based voice assistant for smart home applications | |
| CN108922528A (en) | Method and apparatus for handling voice | |
| CN109712644A (en) | Method based on speech recognition emotional change control LED display effect, the apparatus and system for controlling LED display effect | |
| CN110288995A (en) | Exchange method, device, storage medium and electronic equipment based on speech recognition | |
| CN102748833A (en) | Method, device and server for performing voice control on electric appliances | |
| CN106326087B (en) | Web page experience method and system based on robot operating system | |
| Devi et al. | Smart home system using voice command with integration of esp8266 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |