CN106653024A - Speech control method and device, balance car control method and device and balance car - Google Patents
Speech control method and device, balance car control method and device and balance car Download PDFInfo
- Publication number
- CN106653024A CN106653024A CN201611270826.5A CN201611270826A CN106653024A CN 106653024 A CN106653024 A CN 106653024A CN 201611270826 A CN201611270826 A CN 201611270826A CN 106653024 A CN106653024 A CN 106653024A
- Authority
- CN
- China
- Prior art keywords
- balance car
- control
- voice
- command code
- signal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000001914 filtration Methods 0.000 claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004321 preservation Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims 1
- 230000010354 integration Effects 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000003079 width control Methods 0.000 description 5
- 244000294411 Mirabilis expansa Species 0.000 description 3
- 235000015429 Mirabilis expansa Nutrition 0.000 description 3
- 235000013536 miso Nutrition 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0891—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- 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
- G10L15/08—Speech classification or search
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/72—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for transmitting results of analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Library & Information Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention provides a speech control method and a speech control device, a balance car control method and a balance car control device, and a balance car, wherein the speech control method is executed by a controller. The method comprises the following steps: receiving speech signals transmitted from a user by virtue of a speech acquisition device; in accordance with a preset rubbish word list, filtering the speech signals, wherein words, which are irrelevant to target identification key words, are saved in the rubbish word list; comparing the filtered speech signals with the target identification key words which are saved in a preset key word list, so that a speech recognition result is generated, wherein the speech recognition result contains control command; researching command codes, which correspond to the control commands, from a preset command code list; and transmitting the command codes to an executor, so that the executor can control the balance car to move in accordance with the speech recognition result. According to the invention, the speech recognition result can be rapidly and accurately acquired, so that the balance car can be controlled in accordance with the result; therefore, efficiency and precision of controlling the balance car can be improved.
Description
Technical field
The present invention relates to embedded Control technical field, more particularly, to a kind of sound control method and device, balance car
Control method and device and balance car.
Background technology
As developing rapidly for speech recognition technology, practicality improve constantly, increasing equipment is endowed in life
The function of " voice ".For example, in smart home, user can pass through the various furniture of Voice command;In toy for children, voice is handed over
Mutually it is even more the important task for having been assigned education.Two-wheel balance car is detected using gyroscope or acceleration transducer internal in car
The change of vehicle body attitude, and be adjusted using the accurate motor of controller, to keep the balance of system.
The commonly used speech chip of existing Voice command two-wheel balance car understood raw tone and analyzed, and then
It is changed into control signal and is sent to single-chip microcomputer, the single-chip microcomputer changes the motion shape of balance car according to control signal to balance car
State, so as to reach by Voice command purpose;But, the above-mentioned control method based on speech recognition is present using inconvenience, identification
The problems such as inaccurate, system design impersonality.
For the relatively low problem of existing sound control method accuracy, effective solution is not yet proposed.
The content of the invention
In view of this, it is an object of the invention to provide a kind of sound control method and device, balance car control method and
Device and balance car, rapidly and accurately to obtain voice identification result, and then according to the output control balance car, improve balance car
The Efficiency and accuracy of control.
In a first aspect, embodiments providing a kind of sound control method, the method is performed by controller, the control
Device is wirelessly connected with actuator, and the method includes:The voice signal sent by voice acquisition device receive user;According to advance
The rubbish vocabulary of setting, filters to voice signal;Wherein, save and target identification keyword in the rubbish vocabulary
Unrelated word;Voice signal after filtration is carried out with the target identification keyword of preservation in the key vocabularies table for pre-setting
Compare, generate voice identification result;Wherein, the voice identification result includes control command;From the command code row for pre-setting
Command code corresponding with control command is searched in table;Command code is sent to actuator, so that actuator is tied according to speech recognition
Fruit control balance car motion.
With reference in a first aspect, embodiments provide the first possible embodiment of first aspect, wherein, on
State according to the rubbish vocabulary for pre-setting, carrying out filtration to voice signal includes:Voice signal is split, segmentation is generated
One or more voice units afterwards;By one or more voice units after segmentation one by one with rubbish vocabulary in preserve word
Language is compared;If compared successfully, voice unit is deleted.
Second aspect, embodiments provides a kind of balance car control method, and the method is performed by actuator, and this is held
Row device is wirelessly connected with controller, and the method includes:Receive the command code that controller sends;Balance car is obtained by gyroscope
Motion state data;According to motion state data, the pulse control signal corresponding with command code is generated;By pulse control signal
Send to motor driver, so that motor driver controls balance car motion according to pulse control signal.
With reference to second aspect, the first possible embodiment of second aspect is embodiments provided, wherein, on
State and receive before the command code that controller sends, said method also includes:Receive the initial motion of the balance car that gyroscope sends
Status data;According to initial motion status data, self-balancing state is in using pid algorithm control balance car.
The third aspect, embodiments provides a kind of phonetic controller, and the device is arranged at controller, the control
Device is wirelessly connected with actuator, and the device includes:Signal receiving module, for what is sent by voice acquisition device receive user
Voice signal;Signal filtering module, for according to the rubbish vocabulary for pre-setting, filtering to voice signal;Wherein, should
The word unrelated with target identification keyword is saved in rubbish vocabulary;Comparing module, for by the voice signal after filtration
Compare with the target identification keyword preserved in the key vocabularies table for pre-setting, generate voice identification result;Wherein, should
Voice identification result includes control command;Searching modul, for searching from the command code list for pre-setting and control life
Make corresponding command code;First sending module, for command code to be sent to actuator, so that actuator is tied according to speech recognition
Fruit control balance car motion.
With reference to the third aspect, the first possible embodiment of the third aspect is embodiments provided, wherein, on
Stating signal filtering module includes:Signal cutting unit, for splitting to voice signal, generates one or more after segmentation
Voice unit;Comparing unit, for by one or more voice units after segmentation one by one with rubbish vocabulary in preserve word
Language is compared;Unit is deleted, if for comparing successfully, deleting voice unit.
Fourth aspect, embodiments provides a kind of balance truck control device, and the device is arranged at actuator, and this is held
Row device is wirelessly connected with controller, and the device includes:Command code receiver module, for receiving the command code of controller transmission;Shape
State data acquisition module, for obtaining the motion state data of balance car by gyroscope;Control signal generation module, for root
According to motion state data, the pulse control signal corresponding with command code is generated;Second sending module, for Pulse Width Control to be believed
Number send to motor driver, so that motor driver controls balance car motion according to pulse control signal.
With reference to fourth aspect, the first possible embodiment of fourth aspect is embodiments provided, wherein, on
Stating device also includes:Status data receiver module, for receiving the initial motion status data of the balance car of gyroscope transmission;Control
Molding block, for according to initial motion status data, using pid algorithm control balance car self-balancing state being in.
5th aspect, embodiments provides a kind of balance car, and the balance car includes:Balance car body and remote control
Device;Actuator, motor driver and gyroscope are provided with the balance car body;Controller and voice are provided with the remote control
Harvester.
With reference to the 5th aspect, the first possible embodiment of the 5th aspect is embodiments provided, wherein, on
Stating balance car also includes bluetooth transceiver module;The quantity of bluetooth transceiver module is two, is respectively arranged at balance car body and distant
On control device.
The embodiment of the present invention brings following beneficial effect:
A kind of sound control method provided in an embodiment of the present invention and device, balance car control method and device and balance
Car, filters according to the rubbish vocabulary for pre-setting to the voice signal that user sends;Voice letter after by filtration
Number compare with the key vocabularies table for pre-setting and to obtain voice identification result;Look into from the command code list for pre-setting again
Command code corresponding with control command in voice identification result is looked for, and is sent to actuator, so that actuator is according to speech recognition
Output control balance car is moved.Aforesaid way is filtered by rubbish vocabulary to voice signal, by key vocabularies table ratio
To obtaining voice identification result, voice identification result can more rapidly and accurately be obtained according to the voice signal of user, and then
According to the output control balance car, the Efficiency and accuracy of balance car control is improve.
Other features and advantages of the present invention will be illustrated in the following description, also, the partly change from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And in accompanying drawing specifically noted structure realizing and obtain.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Description of the drawings
In order to be illustrated more clearly that the specific embodiment of the invention or technical scheme of the prior art, below will be to concrete
The accompanying drawing to be used needed for embodiment or description of the prior art is briefly described, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, can be with according to these other accompanying drawings of accompanying drawings acquisition.
Fig. 1 is a kind of flow chart of sound control method provided in an embodiment of the present invention;
Fig. 2 is a kind of flow chart of balance car control method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of the hardware system of two-wheel balance car provided in an embodiment of the present invention;
Fig. 4 is a kind of flow process of two-wheel balance car wireless control method based on speech recognition provided in an embodiment of the present invention
Figure;
Fig. 5 is a kind of structural representation of phonetic controller provided in an embodiment of the present invention;
Fig. 6 is a kind of structural representation of balance truck control device provided in an embodiment of the present invention;
Fig. 7 is a kind of structural representation of balance car provided in an embodiment of the present invention.
Specific embodiment
To make purpose, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
In view of the relatively low problem of existing sound control method accuracy, a kind of voice control is embodiments provided
Method and apparatus processed, balance car control method and device and balance car, the technology can apply to voice-operated two-wheel or many
In wheel balance Toy vehicle, it is also possible in being applied to voice-operated manned two-wheel or many wheel balance cars;The technology can adopt phase
The software and hardware of pass is realized, is described below by embodiment.
Embodiment one:
A kind of flow chart of sound control method shown in Figure 1, the method by controller perform, the controller with hold
Row device wirelessly connects, and the method comprises the steps:
Step S102, the voice signal sent by voice acquisition device receive user;Wherein, the audio collecting device can
Think microphone;
Step S104, according to the rubbish vocabulary for pre-setting, filters to voice signal;Wherein, rubbish vocabulary
In save the word unrelated with target identification keyword;
For example, when above-mentioned target identification keyword is control command, comprising control life in the voice signal that user sends
Order, for example, " advance ", " retrogressing " etc.;But user not only may can send control command, can also send some modal particles, Huo Zheqi
His word unrelated with control command, for example, " advance ", " " and " immediately " in " retreating immediately " is not admitted to control to be ordered
Order;According to above-mentioned rubbish vocabulary, the word unrelated with control command that the possible Jing of user often sends is filtered out, be follow-up control
The identification of system order provides preferable data basis.
Step S106, the voice signal after filtration is crucial with the target identification of preservation in the key vocabularies table for pre-setting
Word is compared, and generates voice identification result;Wherein, voice identification result includes control command;
For example, when voice-operated object is dolly, the target identification keyword preserved in above-mentioned key vocabularies table is
The word related to control dolly, such as, and " advance ", " left-hand rotation ", " stopping " etc.;Further, above-mentioned voice-operated object
Can also be many dollies, now, what is preserved in key vocabularies table not only includes control command, also including control object, for example,
" dolly ", " No. two dollies " etc.;Now, upper speech recognition result includes control command, also including control object.
Step S108, searches command code corresponding with control command from the command code list for pre-setting;
Step S110, command code is sent to actuator, so that actuator controls balance car fortune according to voice identification result
It is dynamic.
Generally, above-mentioned control command is a string of character strings, if the character string is sent to actuator, the data of transmission compared with
It is many, may result in the delay of control time, it is also possible to which character string makes a mistake in transmitting procedure, cause control failure;Cause
This, command code is converted to according to command code list by control command;The command code can be such as table 1 with the corresponding relation of control command
It is shown:
Table 1
Control command | Command code |
Advance | 1 |
Retreat | 2 |
Stop | 3 |
Turn left | 4 |
Turn right | 5 |
Mentioned order code is numeral, can reduce the data volume transmitted, and improves control efficiency and accuracy rate.
A kind of sound control method provided in an embodiment of the present invention, is performed, according to the rubbish word for pre-setting by controller
Remittance table is filtered to the voice signal that user sends;Voice signal after by filtration and the key vocabularies table for pre-setting
Compare and obtain voice identification result;Search from the command code list for pre-setting again and control life in voice identification result
Corresponding command code is made, and is sent to actuator, so that actuator controls balance car motion according to voice identification result.Above-mentioned side
Formula is filtered by rubbish vocabulary to voice signal, is compared by key vocabularies table and is obtained voice identification result, can be with root
Voice identification result is more rapidly and accurately obtained according to the voice signal of user, and then according to the output control balance car, is improved
The Efficiency and accuracy of balance car control.
Further, the rubbish vocabulary that above-mentioned basis pre-sets, carries out filtration and comprises the steps to voice signal:
(1) voice signal is split, generates one or more voice units after segmentation;(2) by one or more after segmentation
Voice unit is compared one by one with the word of preservation in rubbish vocabulary;(3) if compared successfully, voice unit is deleted.
During practical application, the voice signal that above-mentioned user sends may be the sentence of multiple words composition, and protect in the rubbish vocabulary
That what is deposited is usually the word of one or more Chinese character compositions, and voice signal is divided into into word, can improve to rubbish vocabulary
Adaptability, and then improve the accuracy rate that rubbish word is filtered.
Embodiment two:
A kind of flow chart of balance car control method shown in Figure 2, the method by actuator perform, the actuator with
Controller wirelessly connects, and the method comprises the steps:
Step S202, receives the command code that controller sends;
Step S204, by gyroscope the motion state data of balance car is obtained;Wherein, the gyroscope can be six axle tops
Spiral shell instrument;
Step S206, according to motion state data, generates the pulse control signal corresponding with command code;
Step S208, pulse control signal is sent to motor driver, so that motor driver is believed according to Pulse Width Control
The motion of number control balance car.
A kind of balance car control method provided in an embodiment of the present invention, is performed, according to getting from gyroscope by actuator
Motion state data, generate the corresponding pulse control signal of command code with controller transmission;And believe the Pulse Width Control
Number send to motor driver, so that the motor driver controls balance car motion according to the pulse control signal.It is above-mentioned
The command code that sound signal processing that is that mode sends controller and being sent according to user is obtained is converted into can be with controlled motor
The pulse control signal of driver, and then balance car motion is controlled, improve the Efficiency and accuracy of balance car control.
Preferably, before the command code that above-mentioned reception controller sends, said method also comprises the steps:(1) receive
The initial motion status data of the balance car that gyroscope sends;(2) according to the initial motion status data, using pid algorithm control
Balance car processed is in self-balancing state.When actually realizing, the balance car is write from memory in electric power starting, and when sending without command code
Think the rotation status centered on the central point of two wheel lines;When command code is received, in order to be better carried out this
The control command that command code is represented, it is self-balancing state to need the Status Change of balance car, and the self-balancing state can also be managed
Solve as motion halted state.
Embodiment three:
In order to understand above-mentioned sound control method and balance car control method in more detail, one is embodiments provided
Plant based on the two-wheel balance car wireless control method of speech recognition;The method can be performed by the hardware system of two-wheel balance car,
For the ease of understanding the above-mentioned two-wheel balance car wireless control method based on speech recognition, the embodiment of the present invention is first to above-mentioned double
The hardware system of wheel balance car is described.
A kind of structural representation of the hardware system of two-wheel balance car shown in Figure 3;The hardware system includes
LD3320 voice recognition chips 302;Arduino atmega2560 controllers 304, HC-05 bluetooth hosts module 306, HC-06
Bluetooth slave module 307, the axle gyroscopes 308 of MPU6050 six, Arduino Leonardo controllers 310, A4988 stepper motors
The type stepper motor 314 of driver 312 and 42;Wherein, LD3320 chips 302, Arduino atmega2560 controllers 304, HC-
05 bluetooth host module 306 is arranged in the remote control of two-wheel balance car;The HC-06 bluetooth slaves module 307, axles of MPU6050 six
Gyroscope 308, Arduino Leonardo controllers 310, the type stepper motor 314 of A4988 stepper motor drivers 312 and 42 set
In being placed in two-wheel balance car body;Wherein, the two-wheel balance car is properly termed as balance car, it is also possible to which referred to as Double-wheel self-balancing is little
Car.
Specifically, in the program header file PinMap of Arduino atmega2560 controllers to SS, MOSI, MISO and
The regulation of SCK pins determines that LD3320 voice recognition chips are connected with the hardware of Arduino atmega2560 controllers and draws
Pin;The specific pin connected mode that ginseng is shown in Table 2, wherein, the connection of MOSI, MISO, SCK pin is needed by writing
LD3320 is set to adapt to Arduino in Arduino atmega2560 with regard to the pin header file PinMap.h of LD3320
Atmega2560 controllers;
Table 2
LD3320 | Arduino atmega2560 |
3.3V | VCC |
GND | GND |
MISO | D50 |
MOSI | D51 |
NC | Vacantly |
SCK | D52 |
NSS | D4 |
RST | D9 |
IRQ | D2 |
WR | GND |
A kind of flow chart of two-wheel balance car wireless control method based on speech recognition shown in Figure 4, the method
Comprise the steps:
Step S402, Arduino atmega2560 controllers control LD3320 voice recognition chip initialization LD3320's
Register, and it is loaded into the key vocabularies table and rubbish vocabulary write in advance;
Step S404, the voice control command that LD3320 voice recognition chip receive users send, by the language that will be input into
Sound control command is compared respectively with rubbish vocabulary and lists of keywords, to the output of Arduino atmega2560 controllers
Voice identification result;Wherein, rubbish vocabulary includes the order of close pronunciation;When implementing, key vocabularies table and rubbish
The vocabulary quantity stored in rubbish vocabulary determines the degree of accuracy of speech recognition.The establishment of lists of keywords need to be included and is possible to
The order used, and by its with pinyin representation out, in order to increase accuracy of identification, the phonetic or English word of dialect can be added
Phonetic;Show that the identification of voices such as " uh uh uh " " " belongs to the content of rubbish word lists, rubbish word by experiment
Remittance content is abundanter, and the accuracy of speech recognition is higher;
Step S406, Arduino atmega2560 controllers export different orders according to corresponding voice identification result
Code;Again two-wheel balance car is radioed to by HC-05 bluetooth host modules;For example, qianjin orders are corresponding to command code
" 1 ", houtui orders corresponding to command code " 2 ", by that analogy;
Step S408, the reception command code of HC-06 bluetooths slave module in two-wheel balance car, and by data receiver serial ports
The command code is sent to Arduino Leonardo controllers;
When actually realizing, two-wheel balance car is turn-taked for original place maintain self-balancing state in an initial condition, when bluetooth connects
After connecing, dolly state is changed into the static maintenance self-balancing state in original place, waits order to be received;Arduino Leonardo controllers are needed
With reference to the data of the axle gyroscopes of MPU6050 six, self-balancing state is maintained by pid algorithm;
Step S410, according to the command code for receiving, and the motion state data obtained from the axle gyroscopes of MPU6050 six,
Arduino Leonardo controllers continuously send out pulse to A9488 stepper motor drivers;
Step S412, A9488 stepper motor drivers according to the pulse for receiving, before driving two 42 stepper motors to make
Enter, retreat, the action such as left/right rotation.
A kind of two-wheel balance car wireless control method based on speech recognition provided in an embodiment of the present invention, LD3320 voices
Identification module receives the special sound control command that user sends, through Arduino atmega2560 controllers and LD3320
The process of sound identification module, forms command code, and is sent to two-wheel balance car by HC-05 bluetooth host modules;The two-wheel
It is pirouette round state under balance car original state, when the HC-06 bluetooth slave modules on two-wheel balance car receive command code
Afterwards, the state of two-wheel balance car is changed into static maintenance poised state;Finally with reference to the data of MPU6050 chips, two-wheel balance car
On Arduino Leonardo controllers according to the command code for receiving, drive 42 stepper motors to advance, retreat and left and right
Turn.The present invention has the advantages that voice-controlled operations are simple, accuracy of identification is high, command range is remote, improves conventional remote controls manual
By the method for key control.
Further, the embodiment of the present invention is by feasible technical scheme, with following some beneficial effect:(1) mitigate
Small two-wheel balance car must single artificial straighforward operation trouble, by voice-operated mode, make control process it is simple,
Easy, safety;(2) method for improving traditional wire control, the method using controlled in wireless in combination with Voice command makes control
Process processed more hommization;(3) the controller model at Voice command end can be changed according to adjustment PinMap.h files, is adapted to
Property is strong.
Example IV:
Corresponding to said method embodiment, a kind of structural representation of phonetic controller shown in Figure 5, the device
Controller is arranged at, the controller is wirelessly connected with actuator, the device includes following part:
Signal receiving module 502, for the voice signal sent by voice acquisition device receive user;
Signal filtering module 504, for according to the rubbish vocabulary for pre-setting, filtering to voice signal;Wherein,
The word unrelated with target identification keyword is saved in the rubbish vocabulary;
Comparing module 506, for the target that will be preserved in the voice signal after filtration and the key vocabularies table for pre-setting
Identification keyword is compared, and generates voice identification result;Wherein, the voice identification result includes control command;
Searching modul 508, for searching command code corresponding with control command from the command code list for pre-setting;
First sending module 510, for command code to be sent to actuator, so that actuator is according to voice identification result control
Balance car motion processed.
A kind of phonetic controller provided in an embodiment of the present invention, is arranged at controller, according to the rubbish word for pre-setting
Remittance table is filtered to the voice signal that user sends;Voice signal after by filtration and the key vocabularies table for pre-setting
Compare and obtain voice identification result;Search from the command code list for pre-setting again and control life in voice identification result
Corresponding command code is made, and is sent to actuator, so that actuator controls balance car motion according to voice identification result.Above-mentioned side
Formula is filtered by rubbish vocabulary to voice signal, is compared by key vocabularies table and is obtained voice identification result, can be with root
Voice identification result is more rapidly and accurately obtained according to the voice signal of user, and then according to the output control balance car, is improved
The Efficiency and accuracy of balance car control.
Further, above-mentioned signal filtering module includes:(1) signal cutting unit, for splitting to voice signal,
Generate one or more voice units after segmentation;(2) comparing unit, for by one or more voice units after segmentation by
One compares with the word of preservation in rubbish vocabulary;(3) unit is deleted, if for comparing successfully, deleting voice unit.
A kind of structural representation of balance truck control device shown in Figure 6, the device is arranged at actuator, the execution
Device is wirelessly connected with controller, and the device includes following part:
Command code receiver module 602, for receiving the command code of controller transmission;
State data acquisition module 604, for obtaining the motion state data of balance car by gyroscope;
Control signal generation module 606, for according to motion state data, generating the Pulse Width Control corresponding with command code
Signal;
Second sending module 608, for pulse control signal to be sent to motor driver so that motor driver according to
Pulse control signal control balance car motion.
A kind of balance truck control device provided in an embodiment of the present invention, is arranged at actuator, according to getting from gyroscope
Motion state data, generate the corresponding pulse control signal of command code with controller transmission;And believe the Pulse Width Control
Number send to motor driver, so that the motor driver controls balance car motion according to the pulse control signal.It is above-mentioned
The command code that sound signal processing that is that mode sends controller and being sent according to user is obtained is converted into can be with controlled motor
The pulse control signal of driver, and then balance car motion is controlled, improve the Efficiency and accuracy of balance car control.
Preferably, said apparatus also include:(1) status data receiver module, for receiving the balance car of gyroscope transmission
Initial motion status data;(2) control module, for according to initial motion status data, using pid algorithm balance car being controlled
In self-balancing state.
Embodiment five:
Corresponding to said method embodiment and device embodiment, a kind of structural representation of balance car shown in Figure 7,
The balance car includes:Balance car body 72 and remote control 74;Actuator 722, Motor drive is provided with the balance car body 72
Device 724 and gyroscope 726;Controller 742 and voice acquisition device 744 are provided with the remote control 74.
Those skilled in the art can be understood that, for convenience and simplicity of description, the balance of foregoing description
The specific work process of car, may be referred to the corresponding process in preceding method embodiment, will not be described here.
Further, above-mentioned balance car also includes bluetooth transceiver module;The quantity of the bluetooth transceiver module is two, respectively
It is arranged on balance car body and remote control.
Balance car provided in an embodiment of the present invention, the sound control method provided with above-described embodiment and device, balance car
Control method and device have identical technical characteristic, so can also solve identical technical problem, reach identical technology effect
Really.
Sound control method that the embodiment of the present invention is provided and device, balance car control method and device and balance car
Computer program, including the computer-readable recording medium for storing program code, the instruction that described program code includes
Can be used to perform the method described in previous methods embodiment, implement and can be found in embodiment of the method, will not be described here.
If the function is realized and as independent production marketing or when using using in the form of SFU software functional unit, can be with
In being stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the invention.
And aforesaid storage medium includes:USB flash disk, portable hard drive, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Finally it should be noted that:Embodiment described above, specific embodiment only of the invention, to illustrate the present invention
Technical scheme, rather than a limitation, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this
It is bright to be described in detail, it will be understood by those within the art that:Any those familiar with the art
The invention discloses technical scope in, it still can modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent is carried out to which part technical characteristic;And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of embodiment of the present invention technical scheme, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
1. a kind of sound control method, it is characterised in that methods described is performed by controller, and the controller is wireless with actuator
Connection, methods described includes:
The voice signal sent by voice acquisition device receive user;
According to the rubbish vocabulary for pre-setting, the voice signal is filtered;Wherein, preserve in the rubbish vocabulary
The word unrelated with target identification keyword;
The voice signal after by filtration is compared with the target identification keyword of preservation in the key vocabularies table for pre-setting
It is right, generate voice identification result;Wherein, institute's speech recognition result includes control command;
Command code corresponding with the control command is searched from the command code list for pre-setting;
The command code is sent to the actuator, so that the actuator is according to institute's speech recognition result control balance car
Motion.
2. method according to claim 1, it is characterised in that the rubbish vocabulary that the basis pre-sets, to described
Voice signal carries out filtration to be included:
The voice signal is split, one or more voice units after segmentation are generated;
One or more institute's speech units after segmentation are compared one by one with the word of preservation in the rubbish vocabulary;
If compared successfully, institute's speech units are deleted.
3. a kind of balance car control method, it is characterised in that methods described is performed by actuator, the actuator and controller without
Line connects, and methods described includes:
Receive the command code that the controller sends;
The motion state data of balance car is obtained by gyroscope;
According to the motion state data, the pulse control signal corresponding with the command code is generated;
The pulse control signal is sent to motor driver, so that the motor driver is according to the pulse control signal
Control balance car motion.
4. method according to claim 3, it is characterised in that described before receiving the command code that the controller sends
Method also includes:
Receive the initial motion status data of the balance car that the gyroscope sends;
According to the initial motion status data, using PID (Proportion Integration Differentiation,
PID) algorithm controls the balance car and is in self-balancing state.
5. a kind of phonetic controller, it is characterised in that described device is arranged at controller, and the controller is wireless with actuator
Connection, described device includes:
Signal receiving module, for the voice signal sent by voice acquisition device receive user;
Signal filtering module, for according to the rubbish vocabulary for pre-setting, filtering to the voice signal;Wherein, institute
State and the word unrelated with target identification keyword is saved in rubbish vocabulary;
Comparing module, for the target identification preserved in the voice signal after by filtration and the key vocabularies table for pre-setting
Keyword is compared, and generates voice identification result;Wherein, institute's speech recognition result includes control command;
Searching modul, for searching command code corresponding with the control command from the command code list for pre-setting;
First sending module, for the command code to be sent to the actuator, so that the actuator is according to the voice
Recognition result control balance car motion.
6. device according to claim 5, it is characterised in that the signal filtering module includes:
Signal cutting unit, for splitting to the voice signal, generates one or more voice units after segmentation;
Comparing unit, for by one or more the institute's speech units after segmentation one by one with the rubbish vocabulary in preserve
Word is compared;
Unit is deleted, if for comparing successfully, deleting institute's speech units.
7. a kind of balance truck control device, it is characterised in that described device is arranged at actuator, the actuator and controller without
Line connects, and described device includes:
Command code receiver module, for receiving the command code that the controller sends;
State data acquisition module, for obtaining the motion state data of balance car by gyroscope;
Control signal generation module, for according to the motion state data, generating the pulse control corresponding with the command code
Signal processed;
Second sending module, for the pulse control signal to be sent to motor driver, so that the motor driver root
According to pulse control signal control balance car motion.
8. device according to claim 7, it is characterised in that described device also includes:
Status data receiver module, for receiving the initial motion status data of the balance car that the gyroscope sends;
Control module, for according to the initial motion status data, controlling the balance car using pid algorithm and being in self-balancing
State.
9. a kind of balance car, it is characterised in that the balance car includes:Balance car body and remote control;
Actuator, motor driver and gyroscope are provided with the balance car body;Controller is provided with the remote control
And voice acquisition device.
10. balance car according to claim 9, it is characterised in that the balance car also includes bluetooth transceiver module;It is described
The quantity of bluetooth transceiver module is two, is respectively arranged on the balance car body and the remote control.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611270826.5A CN106653024A (en) | 2016-12-30 | 2016-12-30 | Speech control method and device, balance car control method and device and balance car |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611270826.5A CN106653024A (en) | 2016-12-30 | 2016-12-30 | Speech control method and device, balance car control method and device and balance car |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106653024A true CN106653024A (en) | 2017-05-10 |
Family
ID=58838282
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611270826.5A Pending CN106653024A (en) | 2016-12-30 | 2016-12-30 | Speech control method and device, balance car control method and device and balance car |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106653024A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107293293A (en) * | 2017-05-22 | 2017-10-24 | 深圳市搜果科技发展有限公司 | A kind of voice instruction recognition method, system and robot |
CN108376547A (en) * | 2018-05-08 | 2018-08-07 | 贵州大学 | A kind of array speech collecting system and acquisition method based on Arduino |
CN108768815A (en) * | 2018-06-11 | 2018-11-06 | 中国人民解放军空军工程大学 | A kind of signal processing system and signal processing method |
CN108806689A (en) * | 2018-07-30 | 2018-11-13 | 苏州工业职业技术学院 | Acoustic control self-balancing trolley and its control method |
CN108927815A (en) * | 2017-06-15 | 2018-12-04 | 北京猎户星空科技有限公司 | Robot brake control method, device and robot |
CN109625138A (en) * | 2019-01-11 | 2019-04-16 | 海南大学 | One kind two takes turns balance car |
CN110389532A (en) * | 2018-04-23 | 2019-10-29 | 珠海格力电器股份有限公司 | Control method and system based on intelligent sound box |
WO2021082954A1 (en) * | 2019-11-01 | 2021-05-06 | 浙江阿尔郎科技有限公司 | Main control system and control system for self-balancing vehicle, and self-balancing vehicle |
CN112765335A (en) * | 2021-01-27 | 2021-05-07 | 上海三菱电梯有限公司 | Voice calling landing system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020143554A1 (en) * | 2001-03-12 | 2002-10-03 | Shaw-Yuan Hou | Voice-activated control device for intelligent instruments |
CN101269638A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Vehicle electrical apparatus sound control method based on command word list |
TW200839605A (en) * | 2007-01-19 | 2008-10-01 | Microsoft Corp | Automatic reading tutoring with parallel polarized language modeling |
CN202608975U (en) * | 2012-05-08 | 2012-12-19 | 路海燕 | Remote control electric scooter capable of being changed into electric bicycle |
CN204415584U (en) * | 2015-03-08 | 2015-06-24 | 刘鹏军 | Sound-controlled electric car |
CN205010422U (en) * | 2015-08-28 | 2016-02-03 | 浙江璐琪智能科技有限公司 | Thinking car based on speech control |
CN105321518A (en) * | 2014-08-05 | 2016-02-10 | 中国科学院声学研究所 | Rejection method for low-resource embedded speech recognition |
CN205365279U (en) * | 2015-12-31 | 2016-07-06 | 杭州速控软件有限公司 | Electrodynamic balance car with speech recognition function |
-
2016
- 2016-12-30 CN CN201611270826.5A patent/CN106653024A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020143554A1 (en) * | 2001-03-12 | 2002-10-03 | Shaw-Yuan Hou | Voice-activated control device for intelligent instruments |
TW200839605A (en) * | 2007-01-19 | 2008-10-01 | Microsoft Corp | Automatic reading tutoring with parallel polarized language modeling |
CN101269638A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Vehicle electrical apparatus sound control method based on command word list |
CN202608975U (en) * | 2012-05-08 | 2012-12-19 | 路海燕 | Remote control electric scooter capable of being changed into electric bicycle |
CN105321518A (en) * | 2014-08-05 | 2016-02-10 | 中国科学院声学研究所 | Rejection method for low-resource embedded speech recognition |
CN204415584U (en) * | 2015-03-08 | 2015-06-24 | 刘鹏军 | Sound-controlled electric car |
CN205010422U (en) * | 2015-08-28 | 2016-02-03 | 浙江璐琪智能科技有限公司 | Thinking car based on speech control |
CN205365279U (en) * | 2015-12-31 | 2016-07-06 | 杭州速控软件有限公司 | Electrodynamic balance car with speech recognition function |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107293293A (en) * | 2017-05-22 | 2017-10-24 | 深圳市搜果科技发展有限公司 | A kind of voice instruction recognition method, system and robot |
CN108927815A (en) * | 2017-06-15 | 2018-12-04 | 北京猎户星空科技有限公司 | Robot brake control method, device and robot |
CN108927815B (en) * | 2017-06-15 | 2020-12-04 | 北京猎户星空科技有限公司 | Robot brake control method and device and robot |
CN110389532A (en) * | 2018-04-23 | 2019-10-29 | 珠海格力电器股份有限公司 | Control method and system based on intelligent sound box |
CN108376547A (en) * | 2018-05-08 | 2018-08-07 | 贵州大学 | A kind of array speech collecting system and acquisition method based on Arduino |
CN108768815A (en) * | 2018-06-11 | 2018-11-06 | 中国人民解放军空军工程大学 | A kind of signal processing system and signal processing method |
CN108806689A (en) * | 2018-07-30 | 2018-11-13 | 苏州工业职业技术学院 | Acoustic control self-balancing trolley and its control method |
CN109625138A (en) * | 2019-01-11 | 2019-04-16 | 海南大学 | One kind two takes turns balance car |
WO2021082954A1 (en) * | 2019-11-01 | 2021-05-06 | 浙江阿尔郎科技有限公司 | Main control system and control system for self-balancing vehicle, and self-balancing vehicle |
CN112765335A (en) * | 2021-01-27 | 2021-05-07 | 上海三菱电梯有限公司 | Voice calling landing system |
CN112765335B (en) * | 2021-01-27 | 2024-03-08 | 上海三菱电梯有限公司 | Voice call system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106653024A (en) | Speech control method and device, balance car control method and device and balance car | |
EP2045140B1 (en) | Adjustment of vehicular elements by speech control | |
WO2017210901A1 (en) | Speed planning method and apparatus and calculating apparatus for automatic driving of vehicle | |
CN105679316A (en) | Voice keyword identification method and apparatus based on deep neural network | |
CN108305634A (en) | Coding/decoding method, decoder and storage medium | |
CN107134279A (en) | A kind of voice awakening method, device, terminal and storage medium | |
CN107992016A (en) | A kind of automatic driving vehicle analog detection method | |
Wang et al. | Large-scale unsupervised pre-training for end-to-end spoken language understanding | |
CN106663422A (en) | Text rule based multi-accent speech recognition with single acoustic model and automatic accent detection | |
CN103531197A (en) | Command word recognition self-adaptive optimization method for carrying out feedback on user speech recognition result | |
CN104756185B (en) | Speech recognition equipment | |
CN107545029A (en) | Voice feedback method, equipment and the computer-readable recording medium of smart machine | |
CN108281138A (en) | Age discrimination model training and intelligent sound exchange method, equipment and storage medium | |
CN106057194A (en) | Voice interaction system | |
US20080300870A1 (en) | Method and Module for Improving Personal Speech Recognition Capability | |
CN104200805A (en) | Car driver voice assistant | |
US10909972B2 (en) | Spoken language understanding using dynamic vocabulary | |
CN106852596A (en) | A kind of intelligent gradevin and its control method | |
EP2507793A1 (en) | Multi-dictionary speech recognition | |
CN105739337A (en) | Man-machine interaction type voice control and demonstration system and method | |
CN106347260A (en) | Vehicle control system based on voice recognition and control method thereof | |
CN105469801A (en) | Input speech restoring method and device | |
CN104679733A (en) | Voice conversation translation method, device and system | |
CN110232918B (en) | Unmanned aerial vehicle ground control station voice control system and control method | |
US20190379777A1 (en) | Voice recognition apparatus, vehicle including the same, and control method thereof |
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: 20170510 |