CN108364640A - A kind of robot remote speech control system based on TensorFlow frames - Google Patents
A kind of robot remote speech control system based on TensorFlow frames Download PDFInfo
- Publication number
- CN108364640A CN108364640A CN201810363531.5A CN201810363531A CN108364640A CN 108364640 A CN108364640 A CN 108364640A CN 201810363531 A CN201810363531 A CN 201810363531A CN 108364640 A CN108364640 A CN 108364640A
- Authority
- CN
- China
- Prior art keywords
- robot
- module
- tensorflow
- control system
- system based
- 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
- 238000004891 communication Methods 0.000 claims abstract description 19
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims abstract description 7
- 238000011161 development Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000002864 sequence alignment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
- H04L69/161—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
- H04L69/162—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields involving adaptations of sockets based mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/72409—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality by interfacing with external accessories
- H04M1/72415—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality by interfacing with external accessories for remote control of appliances
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Computation (AREA)
- Manipulator (AREA)
- Toys (AREA)
Abstract
The present invention provides a kind of robot remote speech control system based on TensorFlow frames, including：Mobile phone terminal, robot, communication module；The mobile phone terminal includes：Voice acquisition module acquires phonetic order；Sound identification module acquires voice by cell phone application, uses TensorFlow convolutional neural networks Model Identification voices；The robot includes：Robot controls chip, using Raspberry Pi 3 generation b types development board；Wireless driver module, the signal for receiving app transmissions, and pass it to motor drive module；Motor drive module, using the control motor rotation of L298N motor driving plates；The communication module realizes that app and robot control the communication of chip with the libraries socket；The present invention simultaneously can realize remote control, can effectively identify different accents and the clear situation of aphthenxia.
Description
Technical field
The invention belongs to automation control area, more particularly to a kind of robot remote language based on TensorFlow frames
Sound control system.
Background technology
Steady with artificial intelligence is popularized, and the mankind are higher and higher to the acceptance level of intelligent robot；And with intelligence
Can robot diversification, precision service etc., substantially liberated the labour of the mankind, with the research and development of intelligent robot,
Its cost is also constantly declining, the mankind to intelligence machine Man's Demands also to a unprecedented height, and demand
It increases year by year.Intelligent robot includes multiple technologies, and multiple product, voice control robot is as one kind therein, liberation
The both hands mode of operation of the mankind, accurately says demand, is identified by speech recognition technology and controls robot and is operated.
Its sound identification module part of existing robot voice control system is based on sequence alignment algorithms, when such as dynamic
Between bending algorithm etc., such algorithm can not effectively identify situations such as different accents and clear aphthenxia；Another part is based on
Neural network algorithm is such as based on Baidu's speech recognition interface, and such methods need connection internet in real time, and are supplied by interface
The limitation of quotient's technical merit and technical stability.Its sound identification module of existing voice control robot is integrated in robot control
In chip, limited by voice collecting range, it can not remote control.
Invention content
For disadvantages described above, the present invention provides a kind of speech recognition control system, can realize remote speech control.
The technical scheme is that：A kind of robot remote speech control system based on TensorFlow frames, packet
It includes：Mobile phone terminal, robot, communication module；The mobile phone terminal includes：Voice acquisition module acquires phonetic order；Voice is known
Other module acquires voice by cell phone application, uses TensorFlow convolutional neural networks Model Identification voices；The robot
Including：Robot controls chip, using Raspberry Pi 3 generation b types development board；Wireless driver module, the letter for receiving app transmissions
Number, and pass it to motor drive module；Motor drive module, using the control motor rotation of L298N motor driving plates；It is described
Communication module, the communication for controlling chip with robot with the libraries socket realization app include：Instruction issue unit is located at mobile phone
In terminal, chip is controlled for sending an instruction to robot；Instruction accepting unit：In robot, for receiving mobile phone
The instruction that terminal sends over.
Further, a kind of robot remote speech control system based on TensorFlow frames, the communication module
It is communicated using wifi, bluetooth, ZigBee transmission modes.
Further, a kind of robot remote speech control system based on TensorFlow frames, the robot control
Coremaking piece is integrated with wireless driver module.
Further, a kind of robot remote speech control system based on TensorFlow frames, the speech recognition
Module acquires voice signal using APP modes by mobile microphone, extracts characteristic value by MFCC methods, inputs and use in advance
The trained models of TensorFlow, identify voice messaging；Then robot is sent information to by the libraries socket and controls mould
Block.
Further, a kind of robot remote speech control system based on TensorFlow frames, the instruction of the model
White silk is by building TensorFlow flow charts, training set voice data being initialized, and input CNN models are trained, and are obtained
Model parameter.
Beneficial effects of the present invention are：Speech recognition is completed by cell phone application, recognition result is being sent to robot control
In coremaking piece, such communication can be based on LAN, and can realize remote control；The sound identification module of the present invention uses
TensorFlow frames, the frame are based on convolutional neural networks model（CNN）, can effectively identify different accents and aphthenxia
Clear situation；The control module that the present invention uses has integrated wireless driver module, is not necessarily to external wireless driver module.
Each module is used in the present invention voice acquisition module, sound identification module, TensorFlow convolutional neural networks
Model etc. develops the technology of comparative maturity now, together by the solution pool of each module through the invention, builds machine
People's remote voice control system realizes the remote control to robot.
Description of the drawings
Fig. 1 is a kind of structural representation of the robot remote speech control system based on TensorFlow frames of the present invention
Figure；
Fig. 2 is a kind of work flow diagram of the robot remote speech control system based on TensorFlow frames of the present invention.
Specific implementation mode
For technical scheme of the present invention is understood in detail, technical scheme of the present invention is further described below in conjunction with the accompanying drawings.
As shown in Figure 1, a kind of robot remote speech control system based on TensorFlow frames, including：Mobile phone is whole
End, robot, communication module；The mobile phone terminal includes：Voice acquisition module acquires phonetic order；Sound identification module leads to
Cell phone application acquisition voice is crossed, TensorFlow convolutional neural networks Model Identification voices are used；The robot includes：Machine
People controls chip, using Raspberry Pi 3 generation b types development board；Wireless driver module, the signal for receiving app transmissions, and passed
Pass motor drive module；Motor drive module, using the control motor rotation of L298N motor driving plates；The communication module, fortune
Realize that the communication of app and robot control chip includes with the libraries socket：Instruction issue unit is located on mobile phone terminal, is used for
Send an instruction to robot control chip；Instruction accepting unit：In robot, sended over for receiving mobile phone terminal
Instruction.
The communication module can be used wifi, bluetooth, ZigBee transmission modes and be communicated, and wifi is used in the present embodiment
Communication mode is communicated.
To simplify manufacture craft and cost, the robot in the present embodiment is by control integrated chip wireless driver module.
Sound identification module in the present embodiment acquires voice signal using APP modes by mobile microphone, passes through
MFCC methods extract characteristic value, and input uses the trained models of TensorFlow, identifies voice messaging in advance；Then by
The libraries socket send information to robot control module.The training of the model be by build TensorFlow flow charts,
Training set voice data is initialized, input CNN models are trained, and obtain model parameter.
As shown in Fig. 2, the flow of the control system of the present embodiment at work is as follows：
S1：Start robot, opens mobile phone terminal APP；
S2：Voice acquisition module is started to work, and voice is acquired；Judge whether there is voice, if any then continue in next step, as nothing if after
Continue this step；
S3：Sound identification module identifies collected voice, and phonetic order is converted to communication signal by data processing；
S4：Signal is sent to instruction accepting unit by the instruction issue unit of communication module by wifi communication modes；
S5：Robot control chip parses the command signal received, and sends an instruction to robot motor's drive module, controls
Robot motion processed.
Claims (5)
1. a kind of robot remote speech control system based on TensorFlow frames, including：Mobile phone terminal, leads to robot
Interrogate module；It is characterized in that：
The mobile phone terminal includes：
Voice acquisition module acquires phonetic order；
Sound identification module acquires voice by cell phone application, uses TensorFlow convolutional neural networks Model Identification voices；
The robot includes：
Robot controls chip, using Raspberry Pi 3 generation b types development board；
Wireless driver module, the signal for receiving app transmissions, and pass it to motor drive module；
Motor drive module, using the control motor rotation of L298N motor driving plates；
The communication module, the communication for controlling chip with robot with the libraries socket realization app include：
Instruction issue unit is located on the mobile phone terminal, and chip is controlled for sending an instruction to robot；
Instruction accepting unit：In the robot, the instruction that is sended over for receiving mobile phone terminal.
2. a kind of robot remote speech control system based on TensorFlow frames according to claim 1, special
Sign is：The communication module is communicated using wifi, bluetooth, ZigBee transmission modes.
3. a kind of robot remote speech control system based on TensorFlow frames according to claim 1, special
Sign is：The robot controls integrated chip wireless driver module.
4. a kind of robot remote speech control system based on TensorFlow frames according to claim 1, special
Sign is：The sound identification module acquires voice signal using APP modes by mobile microphone, is extracted by MFCC methods
Characteristic value, input use the trained models of TensorFlow, identify voice messaging in advance；Then information is sent out by the libraries socket
Give robot control module.
5. a kind of robot remote speech control system based on TensorFlow frames according to claim 4, special
Sign is：The training of the model is by building TensorFlow flow charts, training set voice data being initialized, input
CNN models are trained, and obtain model parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810363531.5A CN108364640A (en) | 2018-04-21 | 2018-04-21 | A kind of robot remote speech control system based on TensorFlow frames |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810363531.5A CN108364640A (en) | 2018-04-21 | 2018-04-21 | A kind of robot remote speech control system based on TensorFlow frames |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108364640A true CN108364640A (en) | 2018-08-03 |
Family
ID=63009305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810363531.5A Pending CN108364640A (en) | 2018-04-21 | 2018-04-21 | A kind of robot remote speech control system based on TensorFlow frames |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108364640A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961777A (en) * | 2019-02-16 | 2019-07-02 | 天津大学 | A kind of voice interactive method based on intelligent robot |
| CN110420466A (en) * | 2019-08-14 | 2019-11-08 | 北京技德系统技术有限公司 | A kind of Intelligent voice toy vehicle based on microcontroller |
| WO2021104085A1 (en) * | 2019-11-29 | 2021-06-03 | 中国科学院深圳先进技术研究院 | Speech interaction controller and system, and robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090157221A1 (en) * | 2007-12-14 | 2009-06-18 | Hon Hai Precision Industry Co., Ltd. | Robotic system, robot and mobile phone |
| CN201889796U (en) * | 2010-09-06 | 2011-07-06 | 武汉智达星机器人有限公司 | Internet-based speech recognition robot |
| CN204462733U (en) * | 2015-02-27 | 2015-07-08 | 青岛里奥机器人技术有限公司 | A kind of Study of Intelligent Robot Control system based on android system |
| CN105550519A (en) * | 2015-12-16 | 2016-05-04 | 杭州市第一人民医院 | Mobile robot based delivery system and delivery method for medical consumables in operating room |
| CN106782559A (en) * | 2016-12-31 | 2017-05-31 | 广东博意建筑设计院有限公司 | Smart home house keeper central control system and its control method with telecommunication control |
| US20170308800A1 (en) * | 2016-04-26 | 2017-10-26 | Smokescreen Intelligence, LLC | Interchangeable Artificial Intelligence Perception Systems and Methods |
-
2018
- 2018-04-21 CN CN201810363531.5A patent/CN108364640A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090157221A1 (en) * | 2007-12-14 | 2009-06-18 | Hon Hai Precision Industry Co., Ltd. | Robotic system, robot and mobile phone |
| CN201889796U (en) * | 2010-09-06 | 2011-07-06 | 武汉智达星机器人有限公司 | Internet-based speech recognition robot |
| CN204462733U (en) * | 2015-02-27 | 2015-07-08 | 青岛里奥机器人技术有限公司 | A kind of Study of Intelligent Robot Control system based on android system |
| CN105550519A (en) * | 2015-12-16 | 2016-05-04 | 杭州市第一人民医院 | Mobile robot based delivery system and delivery method for medical consumables in operating room |
| US20170308800A1 (en) * | 2016-04-26 | 2017-10-26 | Smokescreen Intelligence, LLC | Interchangeable Artificial Intelligence Perception Systems and Methods |
| CN106782559A (en) * | 2016-12-31 | 2017-05-31 | 广东博意建筑设计院有限公司 | Smart home house keeper central control system and its control method with telecommunication control |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961777A (en) * | 2019-02-16 | 2019-07-02 | 天津大学 | A kind of voice interactive method based on intelligent robot |
| CN110420466A (en) * | 2019-08-14 | 2019-11-08 | 北京技德系统技术有限公司 | A kind of Intelligent voice toy vehicle based on microcontroller |
| WO2021104085A1 (en) * | 2019-11-29 | 2021-06-03 | 中国科学院深圳先进技术研究院 | Speech interaction controller and system, and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110209791B (en) | Multi-round dialogue intelligent voice interaction system and device | |
| CN108364640A (en) | A kind of robot remote speech control system based on TensorFlow frames | |
| CN102500113A (en) | Comprehensive greeting robot based on smart phone interaction | |
| CN103365836B (en) | A kind of mutual implementation method and system thereof of distributed intelligence that adopts natural language | |
| CN106847274B (en) | Man-machine interaction method and device for intelligent robot | |
| CN107479400A (en) | Control method, device, home appliance and the readable storage medium storing program for executing of home appliance | |
| CN106653020A (en) | Multi-business control method and system for smart sound and video equipment based on deep learning | |
| CN108198559A (en) | A kind of voice control robot system for learning action | |
| WO2016027909A1 (en) | Data structure, interactive voice response device, and electronic device | |
| US10292194B2 (en) | Voice input/output apparatus, wireless connection method, and voice interaction system | |
| CN106584486A (en) | Voice recognition based industrial robot control system and method | |
| CN109448714A (en) | The method that voice Rouser, robot and voice wake up | |
| CN2486896Y (en) | Voice control air conditioner | |
| CN206892866U (en) | Intelligent dialogue device with scenario analysis function | |
| CN101299333A (en) | Built-in speech recognition system and inner core technique thereof | |
| CN114999496A (en) | Audio transmission method, control equipment and terminal equipment | |
| KR100414064B1 (en) | Mobile communication device control system and method using voice recognition | |
| CN210325192U (en) | Off-line voice terminal | |
| CN107520849A (en) | A kind of SCM Based Voice command robot expression display device | |
| CN107452377A (en) | Massage armchair and its information interaction system | |
| JP6583193B2 (en) | Spoken dialogue system and spoken dialogue method | |
| CN108154883A (en) | A kind of compact shelving management system for having voice control function | |
| CN110853634A (en) | Multi-mode voice interaction feedback response control method, computer readable storage medium and air conditioner | |
| CN207781195U (en) | Sound equipment voice activated control based on Android speech recognitions | |
| CN112399020A (en) | Intelligent voice customer service system |
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 |
Application publication date: 20180803 |