CN208985692U - Voice control terminal - Google Patents
Voice control terminal Download PDFInfo
- Publication number
- CN208985692U CN208985692U CN201821604498.2U CN201821604498U CN208985692U CN 208985692 U CN208985692 U CN 208985692U CN 201821604498 U CN201821604498 U CN 201821604498U CN 208985692 U CN208985692 U CN 208985692U
- Authority
- CN
- China
- Prior art keywords
- voice control
- cloud
- control box
- voice
- semantic analysis
- 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)
- Machine Translation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The utility model discloses a kind of voice control terminal, including voice control box, cloud, throw screen, microphone, camera, collected audio data is sent to the speech recognition of the cloud in cloud/semantic analysis engine by AIUI service by voice control box, and the text of needs is converted speech by semantic understanding, the text is converted into corresponding control instruction by voice control box, is sent to control centre by transmission forms such as network, serial ports；Voice control box identifies the identity for issuing the people of control voice by recognition of face, finger print identifying and Application on Voiceprint Recognition, and decide whether to send phonetic order by identification, and loudspeaker is provided in voice control box, support full-duplex voice interactive and barge function, it is handled by local voice identification/semantic analysis engine that the cloud speech recognition/semantic analysis engine cooperation disposed on beyond the clouds is deployed on voice control box to carry out speech recognition and semantic analysis, hand labor is liberated significantly, improves working efficiency.
Description
Technical field
The utility model relates to intelligent sound control technology field more particularly to a kind of voice control terminals.
Background technique
With the development of science and technology, science and technology is more and more intelligent, wherein voice control terminal is more more and more universal, existing voice
Controlling terminal all has user identity identification function, but is mostly identified by vocal print, also has plenty of and passes through
Action gesture identifies that this results in function more single, and cloud deployment way is also more single, lead to voice control terminal
It is more low for the treatment effeciency of audio-frequency information, and phonetic order back track function is not had, therefore, solve this kind of ask
Topic is particularly important.
Utility model content
In view of the deficiencies of the prior art, the utility model provides a kind of voice control terminal, will be adopted by voice control box
The audio data collected is sent to the speech recognition of the cloud in cloud/semantic analysis engine by AIUI service, and passes through semantic reason
Solution converts speech into the text of needs, which is converted into corresponding control instruction by voice control box, passes through network, serial ports
Form is sent to control centre, is deployed in voice by the cloud speech recognition/semantic analysis engine cooperation disposed on beyond the clouds
Local voice identification/semantic analysis engine on control box is handled to carry out speech recognition and semantic analysis.
To solve the above-mentioned problems, the utility model provides a kind of voice control terminal, includes
Voice control box: collected audio data is sent to the speech recognition of the cloud in cloud/language by AIUI service
Adopted analysis engine, and the text of needs is converted speech by semantic understanding, which is converted into accordingly by voice control box
Control instruction, control centre is sent to by network, serial port form, be additionally provided in the voice control box local voice knowledge
Not/semantic analysis engine is used for speech recognition and semantic analysis；
Cloud: the audio data transmitted for receiving and identifying voice control box, the cloud include private clound
End and publicly-owned cloud, the public cloud end administration are deployed in open network, and the private clound end administration is deployed in local area network
It is interior, cloud speech recognition/semantic analysis engine, the cloud speech recognition/semantic analysis engine part are provided in the cloud
Administration is on privately owned cloud and publicly-owned cloud；
Throw screen: for showing treated audio data, content feed, guidance and configuration；
Microphone: for acquiring audio data, the microphone is connected to voice control box by bluetooth or network interface
On；
Camera: for acquiring user's human face data, the camera is connected to voice control by USB or network interface
On box.
Further improvement lies in that: the voice control box identifies hair by recognition of face, finger print identifying and Application on Voiceprint Recognition
The identity of the people of voice is controlled out, and decides whether to send phonetic order by identification.
Further improvement lies in that: it is provided with loudspeaker in the voice control box, loudspeaker can carry or external.
Further improvement lies in that: the microphone uses array algorithm noise reduction, supports near field and far field pickup.
Further improvement lies in that: it is provided with backtracking module in the voice control box, for using the instruction of sending
The retrospect of family identity.
Further improvement lies in that: the semantic understanding includes the understanding of the standard meaning of one's words and the understanding for extending the meaning of one's words.
The beneficial effects of the utility model are: the utility model acquires audio data by microphone, microphone passes through
Usb, bluetooth etc. are wired or are wirelessly connected with voice control terminal, and collected audio data is passed through AIUI by voice control box
Service is sent to cloud speech recognition/semantic analysis engine, and converts speech into needs by speech analysis, semantic understanding etc.
The text is converted into corresponding control instruction by text, voice control box, is sent to by transmission forms such as network, serial ports integrated
The control centre of manufacturer；Voice control box is identified by recognition of face, finger print identifying and Application on Voiceprint Recognition issues control voice
The identity of people, and decide whether to send phonetic order by identification, and there is back track function simultaneously, facilitate user to hair
Instruction out is tracked；And voice control box carries loudspeaker, supports full-duplex voice interactive and barge function；Mike
Elegance noise reduction of microphone array algorithm supports near field and far field pickup, passes through the cloud speech recognition/language disposed on beyond the clouds
Adopted analysis engine cooperates the local voice identification/semantic analysis engine being deployed on voice control box to carry out speech recognition and language
Adopted analysis processing, has liberated hand labor significantly, has improved work efficiency.
Detailed description of the invention
Fig. 1 is the system connection figure of the utility model.
Fig. 2 is the cloud deployment schematic diagram of the utility model.
Fig. 3 is the local speech recognition engine system framework figure of the utility model.
Specific embodiment
In order to deepen the understanding to the utility model, the utility model is further described below in conjunction with embodiment,
The present embodiment is only used for explaining the utility model, does not constitute the restriction to scope of protection of the utility model.
As shown in Figure 1, 2, 3, a kind of voice control terminal is present embodiments provided, includes
Voice control box: collected audio data is sent to the speech recognition engine in cloud by AIUI service, and is led to
The text that semantic understanding converts speech into needs is crossed, which is converted into corresponding control instruction, passed through by voice control box
Network, serial port form are sent to control centre, are provided with local speech recognition engine in the voice control box；
Cloud: the audio data transmitted for receiving and identifying voice control box, the cloud include private clound
End and publicly-owned cloud, the public cloud end administration are deployed in open network, and the private clound end administration is deployed in local area network
It is interior, cloud speech recognition/semantic analysis engine, the cloud speech recognition/semantic analysis engine part are provided in the cloud
Administration is on privately owned cloud and publicly-owned cloud；
Throw screen: for showing treated audio data；
Microphone: for acquiring audio data, the microphone is connected to voice control box by bluetooth or MIC interface
On；
Camera: for acquiring user's human face data, the camera is connected to voice control by USB or network interface
On box.
The voice control box identifies the people's for issuing control voice by recognition of face, finger print identifying and Application on Voiceprint Recognition
Identity, and decide whether to send phonetic order by identification.Loudspeaker is provided in the voice control box.The wheat
Gram elegance array algorithm noise reduction supports near field and far field pickup.Be provided with backtracking module in the voice control box, for pair
The instruction of sending carries out the retrospect of user identity.The local speech recognition engine is used for speech recognition and semantic analysis.It is described
Semantic understanding includes the understanding of the standard meaning of one's words and the understanding for extending the meaning of one's words.
The utility model acquires audio data by microphone, and microphone is wired or wirelessly and language by usb, bluetooth etc.
Sound controlling terminal is connected, and collected audio data is sent to cloud speech recognition/semanteme by AIUI service by voice control box
Analysis engine, and the text of needs is converted speech by speech analysis, semantic understanding etc., voice control box turns the text
It changes corresponding control instruction into, the control centre of integrated manufacturer is sent to by transmission forms such as network, serial ports；Voice control box
Identified by recognition of face, finger print identifying and Application on Voiceprint Recognition issue control voice people identity, and by identification come
Decide whether to send phonetic order, and there is back track function simultaneously, user is facilitated to be tracked the instruction of sending；And voice control
Box processed carries loudspeaker, supports full-duplex voice interactive and barge function；Microphone uses noise reduction of microphone array algorithm,
It supports near field and far field pickup, voice is deployed in by the cloud speech recognition/semantic analysis engine cooperation disposed on beyond the clouds
Local voice identification/semantic analysis engine on control box is handled to carry out speech recognition and semantic analysis, has liberated people significantly
Work labour, improves work efficiency.
Claims (6)
1. a kind of voice control terminal, which is characterized in that include
Voice control box: collected audio data is sent to the speech recognition of the cloud in cloud/semanteme point by AIUI service
Engine is analysed, and converts speech into the text of needs by semantic understanding, which is converted into controlling accordingly by voice control box
System instruction, control centre is sent to by network, serial port form, be additionally provided in the voice control box local voice identification/
Semantic analysis engine is used for speech recognition and semantic analysis；
Cloud: the audio data transmitted for receiving and identifying voice control box, the cloud include privately owned cloud and
Publicly-owned cloud, the public cloud end administration are deployed in open network, and the private clound end administration is deployed in local area network, institute
It states and is provided with cloud speech recognition/semantic analysis engine in cloud, the cloud speech recognition/semantic analysis engine distribution is in private
Have on cloud and publicly-owned cloud；
Throw screen: for showing treated audio data, content feed, guidance and configuration；
Microphone: for acquiring audio data, the microphone is connected on voice control box by bluetooth or network interface；
Camera: for acquiring user's human face data, the camera is connected to voice control box by USB or network interface
On.
2. voice control terminal according to claim 1, it is characterised in that: the voice control box by recognition of face,
Finger print identifying and Application on Voiceprint Recognition identify the identity for the people for issuing control voice, and decide whether to send language by identification
Sound instruction.
3. voice control terminal according to claim 1, it is characterised in that: be provided with loudspeaking in the voice control box
Device.
4. voice control terminal according to claim 1, it is characterised in that: the microphone uses array algorithm noise reduction,
Support near field and far field pickup.
5. voice control terminal according to claim 1, it is characterised in that: be provided with backtracking mould in the voice control box
Block carries out the retrospect of user identity for the instruction to sending.
6. voice control terminal according to claim 1, it is characterised in that: the semantic understanding includes the standard meaning of one's words
Understand and extend the understanding of the meaning of one's words.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821604498.2U CN208985692U (en) | 2018-09-29 | 2018-09-29 | Voice control terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821604498.2U CN208985692U (en) | 2018-09-29 | 2018-09-29 | Voice control terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208985692U true CN208985692U (en) | 2019-06-14 |
Family
ID=66786164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201821604498.2U Active CN208985692U (en) | 2018-09-29 | 2018-09-29 | Voice control terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208985692U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112269977A (en) * | 2020-11-18 | 2021-01-26 | 桂林电子科技大学 | Computer platform and storage device mutual binding authentication system and device thereof |
-
2018
- 2018-09-29 CN CN201821604498.2U patent/CN208985692U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112269977A (en) * | 2020-11-18 | 2021-01-26 | 桂林电子科技大学 | Computer platform and storage device mutual binding authentication system and device thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109036430A (en) | Voice control terminal | |
| CN109309804A (en) | A kind of intelligent meeting system | |
| CN105512113B (en) | AC system speech translation system and interpretation method | |
| CN202542604U (en) | Speech recognition man-machine interaction device for elevator | |
| CN105957514A (en) | Portable deaf-mute communication equipment | |
| WO2018113650A1 (en) | Virtual reality language interaction system and method | |
| CN108877805A (en) | Speech processes mould group and terminal with phonetic function | |
| CN105976814A (en) | Headset control method and device | |
| CN205901877U (en) | On -vehicle android mobile phone connecting device | |
| CN109545216A (en) | A kind of audio recognition method and speech recognition system | |
| CN107680594A (en) | A kind of distributed intelligence voice collecting identifying system and its collection and recognition method | |
| CN107277276A (en) | One kind possesses voice control function smart mobile phone | |
| CN208985692U (en) | Voice control terminal | |
| CN205619070U (en) | Intelligence pronunciation desk lamp | |
| CN107945799A (en) | A kind of multifunction speech interactive intelligence machine | |
| CN108766426B (en) | Intelligent voice interaction command system for naval vessel | |
| CN107071603A (en) | A kind of microphone and system for Real-time speech recognition | |
| CN205582480U (en) | Intelligence acoustic control system | |
| CN206672078U (en) | A kind of sound card for possessing voice control function | |
| CN109168110A (en) | External hanging type speech packet | |
| CN209571226U (en) | A kind of speech recognition equipment and system | |
| CN205376116U (en) | Automatic dolly remote control unit that guides of wireless directional speech control | |
| CN107635178A (en) | A kind of pull bar audio amplifier with identification phonetic function | |
| CN209625783U (en) | Intelligent sound box and smart home system | |
| CN208623896U (en) | Intelligent sound box |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |