CN107789842A - A kind of intelligent toy robot and its control system and method based on speech recognition technology - Google Patents
A kind of intelligent toy robot and its control system and method based on speech recognition technology Download PDFInfo
- Publication number
- CN107789842A CN107789842A CN201711148697.7A CN201711148697A CN107789842A CN 107789842 A CN107789842 A CN 107789842A CN 201711148697 A CN201711148697 A CN 201711148697A CN 107789842 A CN107789842 A CN 107789842A
- Authority
- CN
- China
- Prior art keywords
- signal
- unit
- sound
- module
- voice 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 16
- 238000005516 engineering process Methods 0.000 title claims abstract description 10
- 238000012795 verification Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 28
- 230000015572 biosynthetic process Effects 0.000 claims description 22
- 238000003786 synthesis reaction Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 18
- 230000033228 biological regulation Effects 0.000 claims description 15
- 238000010183 spectrum analysis Methods 0.000 claims description 15
- 239000000428 dust Substances 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 9
- 230000003321 amplification Effects 0.000 claims description 7
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000003139 buffering effect Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000005406 washing Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004088 simulation Methods 0.000 abstract description 2
- 230000006854 communication Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 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
- 238000011160 research Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
- A63H3/00—Dolls
- A63H3/10—Flat toy figures provided with limbs, with or without arrangements for making them stand up
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
- A63H3/00—Dolls
- A63H3/28—Arrangements of sound-producing means in dolls; Means in dolls for producing sounds
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
- A63H3/00—Dolls
- A63H3/36—Details; Accessories
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63H—TOYS, e.g. TOPS, DOLLS, HOOPS OR BUILDING BLOCKS
- A63H5/00—Musical or noise- producing devices for additional toy effects other than acoustical
-
- 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
- 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
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a kind of intelligent toy robot based on speech recognition technology and its control system and method, the robot includes：Head, its bottom are provided with two spikes；Left hand portion, its right side top are provided with a right plug；Right hand portion, its left side top are provided with a left plug；Leg, its top are provided with an ornament；The head is provided with voice acquisition device；The head is internally provided with speech recognition system.There are good effect, self verification, simulation muli-sounds and be not easy to be disturbed.
Description
Technical field
The present invention relates to robotic technology field, more particularly to a kind of intelligent toy robot based on speech recognition technology
And its control system and method.
Background technology
At present, the living standard of people increasingly improves, and the attention for child is also increasingly strengthened.Parent respects the happiness of child
It is good, can be that child spends substantial amounts of money, wherein, toy is exactly the essential content of each child.In existing toy, cage
System ground can be summarized as two classes, and one kind is the toy that can be deformed, such as worldwide transformer is serial, a robot
It can be become by the change of mechanical mechanism and turn to the moulding such as an aircraft or automobile；Another kind of is changeless toy, example
Such as Barbie doll, ball.
Inventor has found after years of researches, for possessing deformation function, with regard to toy itself,
It is fewer to imitate the species of the toy of home appliance, and this type toy can more obtain the favor of parent due to closeness to life,
Also the dense learning interest of child can be caused.Meanwhile inventor is, it was also found that conventional form deformation toy is entered for personage mostly
The toy of row deformation, the Sun Wukong's toy that can such as deform, the superman's toy that can be deformed, with it is close in children life
The form deformation toy of related article, the form deformation toy being particularly the theme with home appliance.
Therefore, on the one hand, be necessary to release the toy being the theme with home appliance, on the other hand, it is contemplated that if imitated
If the toy of home appliance simply immobilizes, its form is excessively stiff, is unfavorable for attracting the interest of child, so, invention
People thinks that the toy for the imitation home appliance that manufacture can deform more has the market space.
The content of the invention
It is an object of the invention to provide a kind of intelligent toy robot and its control system based on speech recognition technology
And method, there are good effect, self verification, simulation muli-sounds and be not easy to be disturbed.
The technical solution adopted by the present invention is as follows：
A kind of intelligent toy robot based on speech recognition technology, the robot include：Head, its bottom are provided with two
Spike；Left hand portion, its right side top are provided with a right plug；Right hand portion, its left side top are provided with a left plug；Leg
Portion, its top are provided with an ornament；The head is provided with voice acquisition device；The head is internally provided with speech recognition
System.
Further, the profile on the head is a toy television shape, and the profile in the left hand portion is drunk for a toy
Water dispenser shape, the profile of the right hand portion are a right hand portion shape, and the profile of the leg is a toy refrigerator shape, the chest
The profile in portion is a toy washing machine shape.
Further, the right hand portion includes：The columned dust catcher cylinder of half；With the bottom of the dust catcher cylinder
The feet being connected, the feet are a movable part with the position that is connected of the dust catcher cylinder, and the feet can be around institute
State another semicircle that connecting portion is front and rear to be rotated, and its described dust catcher cylinder of insertion is lacked after the feet rotates 180 degree
In cylinder.
A kind of speech control system, it is characterised in that the system includes：Voice recognition unit, sound intensity detection unit, language
Sound synthesis unit, panel control unit, panel, main controller and host computer；Signal is connected to voice knowledge to the master controller respectively
Other unit, sound intensity detection unit, phonetic synthesis unit, panel control unit and host computer；The panel control unit signal connects
It is connected to panel.
Further, the voice recognition unit, for identifying the password of operating personnel；It includes：Sound input module,
Spectrum analysis module, characteristic extracting module, sound identification module, speech recognition device, lists of keywords, pinyin string and MCU processing
Device；The sound input module signal is connected to spectrum analysis module；The spectrum analysis module signal is connected to feature extraction
Module；The characteristic extracting module signal is connected to speech recognition device；The speech recognizer level signal is connected to MCU processing
Device and lists of keywords；The lists of keywords signal is connected to pinyin string；The MCU processor signals are connected to pinyin string.
Further, the sound input module, for receiving the voice signal after coming from master controller processing；It is described
Spectrum analysis module, for carrying out spectrum analysis to the voice signal of acquisition, the voice signal after analysis is sent to feature and carried
Modulus block；The characteristic extracting module, feature extraction is carried out to voice signal, the signal after processing is sent to speech recognition mould
Block；The sound identification module, voice signal is identified for the keyword in lists of keywords, after identification
Voice signal send to；The MCU processors, for handle user input keyword, by the keyword after processing send to
Pinyin string；The pinyin string, for the keyword after processing to be converted into pinyin string, pinyin string is sent to lists of keywords
Row storage, so as to update lists of keywords.
Further, the sound intensity detection unit, for detecting whether the voice signal received is to be carried out to the equipment
The password of control；The sound intensity detection unit includes：Sound acquisition module, D/A converter module, sound intensity judge module, signal are put
Big module and signal sampling module；The sound acquisition module, for being acquired to external voice signal；The digital-to-analogue conversion
Module, for the voice signal collected to be converted into electric signal；The sound intensity judge module, for the signal intensity received
Judged, signal amplification module is sent the signal to if the sound intensity exceedes the threshold value of setting, if the sound intensity is not less than the threshold of setting
Value, then deleted the signal received；The signal amplification module, for signal to be amplified；The signal sampling
Module, for being sampled to signal, the voice signal after sampling is sent to controller.
Further, the phonetic synthesis unit, including the regulation of speaker selecting unit, word speed adjustment unit, intonation are single
Member, sound volume regulation unit and synthesis unit；Signal is connected to word speed adjustment unit to the speaker selecting unit respectively, intonation is adjusted
Save unit and sound volume regulation unit, for according to the voice signal after speech recognition signal identifies that controller sends over
Machine selects different speakers, phonetic feature corresponding to the speaker is respectively sent into word speed adjustment unit, intonation adjusts list
Member and sound volume regulation unit；The word speed adjustment unit, for according to the speaker feature received, word speed corresponding to generation to be special
Sign；The intonation adjustment unit, the speaker feature received for basis, intonation feature corresponding to generation；The volume is adjusted
Unit is saved, the speaker feature received for basis, volume characteristics corresponding to generation；The synthesis unit difference signal connection
In word speed adjustment unit, intonation adjustment unit and sound volume regulation unit, for according to receive word speed feature, intonation feature and
Volume characteristics synthesize final voice signal.
A kind of sound control method, it is characterised in that the described method comprises the following steps：
Step 1：Sound intensity detection unit carries out sound intensity detection to the voice signal received, if the sound intensity has exceeded the threshold value of setting
Voice signal is pre-processed, is then forwarded to controller, performs step 2；If the sound intensity will connect not less than the threshold value of setting
The signal received is deleted；
Step 2：Controller sends pretreated voice signal to voice recognition unit；Voice recognition unit is to receiving
Voice signal carries out voice recognition processing, and the voice signal after processing is sent to controller；
Step 3：Controller sends the voice signal after voice recognition processing to phonetic synthesis unit；Phonetic synthesis unit docks
The voice signal after voice recognition unit identifies received is synthesized, and generates final voice signal.
Further, the method that the host computer is played back to voice signal comprises the following steps：
Step 1：Host computer sends serial port command to controller；Monitoring control devices serial ports 0 whether terminal, step is performed if terminal
Rapid 2, without processing if non-terminal；
Step 2：Controller receives the control command of host computer, whether there is the machine address in the data for judging to receive, if
In the presence of then execution step 3, step 1 is continued executing with if there is no then rebound；
Step 3：Address is stored in buffering area by controller, judges whether address receives completely, if it is performs step 4, if
It is not to continue executing with step 1；
Step 4：Controller proceeds by CRC check, if verification is correct, performs step 5, the rebound if verification is incorrect
Perform step 1；
Step 5：Signal return is performed, voice signal is sent to host computer.
Beneficial effects of the present invention are as follows：
Using above technical scheme, present invention produces following beneficial effect：
1st, different sound can be synthesized：The present invention can synthesize the voice signal of different types, can cause the person of being trained to can
To receive the training of different type sound, the effect of teaching is lifted.
2nd, it is not easy to be disturbed：The present invention can differentiate the sound or environment of manipulator by the identification to intensity of sound
Interference sound, avoid part interference.
3rd, teaching efficiency is good：The present invention improves religion by accurately identifying and synthesizing different types of sound to sound
Effect.
4th, communication efficiency is good：Multiple-authentication has been carried out in the host computer of the present invention and the communication process of controller, ensure that
The stabilization of communication process and accurate.
Brief description of the drawings
Fig. 1 is the structural representation of the robot of the present invention.
Fig. 2 is the structural representation of the speech control system of the present invention.
Wherein：1- right hand portions, 2- legs, 3- heads, 4- left hands portion, 5- body part.
Specific embodiment
All features disclosed in this specification, or disclosed all methods or during the step of, except mutually exclusive
Feature and/or step beyond, can combine in any way.
This specification（Including any accessory claim, summary）Disclosed in any feature, unless specifically stated otherwise,
Replaced by other equivalent or with similar purpose alternative features.I.e., unless specifically stated otherwise, each feature is a series of
An example in equivalent or similar characteristics.
Embodiment 1：
As shown in figure 1, a kind of intelligent toy robot based on speech recognition technology, the robot include：Head, its bottom
It is provided with two spikes；Left hand portion, its right side top are provided with a right plug；Right hand portion, its left side top are provided with one
Left plug；Leg, its top are provided with an ornament；The head is provided with voice acquisition device；Set inside the head
There is speech recognition system.
Further, the profile on the head is a toy television shape, and the profile in the left hand portion is drunk for a toy
Water dispenser shape, the profile of the right hand portion are a right hand portion shape, and the profile of the leg is a toy refrigerator shape, the chest
The profile in portion is a toy washing machine shape.
Further, the right hand portion includes：The columned dust catcher cylinder of half；With the bottom of the dust catcher cylinder
The feet being connected, the feet are a movable part with the position that is connected of the dust catcher cylinder, and the feet can be around institute
State another semicircle that connecting portion is front and rear to be rotated, and its described dust catcher cylinder of insertion is lacked after the feet rotates 180 degree
In cylinder.
Embodiment 2：
As shown in Fig. 2 a kind of speech control system, it is characterised in that the system includes：Voice recognition unit, sound intensity detection
Unit, phonetic synthesis unit, panel control unit, panel, main controller and host computer；Signal is connected to the master controller respectively
Voice recognition unit, sound intensity detection unit, phonetic synthesis unit, panel control unit and host computer；The panel control unit
Signal is connected to panel.
Further, the voice recognition unit, for identifying the password of operating personnel；It includes：Sound input module,
Spectrum analysis module, characteristic extracting module, sound identification module, speech recognition device, lists of keywords, pinyin string and MCU processing
Device；The sound input module signal is connected to spectrum analysis module；The spectrum analysis module signal is connected to feature extraction
Module；The characteristic extracting module signal is connected to speech recognition device；The speech recognizer level signal is connected to MCU processing
Device and lists of keywords；The lists of keywords signal is connected to pinyin string；The MCU processor signals are connected to pinyin string.
Further, the sound input module, for receiving the voice signal after coming from master controller processing；It is described
Spectrum analysis module, for carrying out spectrum analysis to the voice signal of acquisition, the voice signal after analysis is sent to feature and carried
Modulus block；The characteristic extracting module, feature extraction is carried out to voice signal, the signal after processing is sent to speech recognition mould
Block；The sound identification module, voice signal is identified for the keyword in lists of keywords, after identification
Voice signal send to；The MCU processors, for handle user input keyword, by the keyword after processing send to
Pinyin string；The pinyin string, for the keyword after processing to be converted into pinyin string, pinyin string is sent to lists of keywords
Row storage, so as to update lists of keywords.
Further, the sound intensity detection unit, for detecting whether the voice signal received is to be carried out to the equipment
The password of control；The sound intensity detection unit includes：Sound acquisition module, D/A converter module, sound intensity judge module, signal are put
Big module and signal sampling module；The sound acquisition module, for being acquired to external voice signal；The digital-to-analogue conversion
Module, for the voice signal collected to be converted into electric signal；The sound intensity judge module, for the signal intensity received
Judged, signal amplification module is sent the signal to if the sound intensity exceedes the threshold value of setting, if the sound intensity is not less than the threshold of setting
Value, then deleted the signal received；The signal amplification module, for signal to be amplified；The signal sampling
Module, for being sampled to signal, the voice signal after sampling is sent to controller.
Further, the phonetic synthesis unit, including the regulation of speaker selecting unit, word speed adjustment unit, intonation are single
Member, sound volume regulation unit and synthesis unit；Signal is connected to word speed adjustment unit to the speaker selecting unit respectively, intonation is adjusted
Save unit and sound volume regulation unit, for according to the voice signal after speech recognition signal identifies that controller sends over
Machine selects different speakers, phonetic feature corresponding to the speaker is respectively sent into word speed adjustment unit, intonation adjusts list
Member and sound volume regulation unit；The word speed adjustment unit, for according to the speaker feature received, word speed corresponding to generation to be special
Sign；The intonation adjustment unit, the speaker feature received for basis, intonation feature corresponding to generation；The volume is adjusted
Unit is saved, the speaker feature received for basis, volume characteristics corresponding to generation；The synthesis unit difference signal connection
In word speed adjustment unit, intonation adjustment unit and sound volume regulation unit, for according to receive word speed feature, intonation feature and
Volume characteristics synthesize final voice signal.
Embodiment 3：
A kind of sound control method, it is characterised in that the described method comprises the following steps：
Step 1：Sound intensity detection unit carries out sound intensity detection to the voice signal received, if the sound intensity has exceeded the threshold value of setting
Voice signal is pre-processed, is then forwarded to controller, performs step 2；If the sound intensity will connect not less than the threshold value of setting
The signal received is deleted；
Step 2：Controller sends pretreated voice signal to voice recognition unit；Voice recognition unit is to receiving
Voice signal carries out voice recognition processing, and the voice signal after processing is sent to controller；
Step 3：Controller sends the voice signal after voice recognition processing to phonetic synthesis unit；Phonetic synthesis unit docks
The voice signal after voice recognition unit identifies received is synthesized, and generates final voice signal.
Further, the method that the host computer is played back to voice signal comprises the following steps：
Step 1：Host computer sends serial port command to controller；Monitoring control devices serial ports 0 whether terminal, step is performed if terminal
Rapid 2, without processing if non-terminal；
Step 2：Controller receives the control command of host computer, whether there is the machine address in the data for judging to receive, if
In the presence of then execution step 3, step 1 is continued executing with if there is no then rebound；
Step 3：Address is stored in buffering area by controller, judges whether address receives completely, if it is performs step 4, if
It is not to continue executing with step 1；
Step 4：Controller proceeds by CRC check, if verification is correct, performs step 5, the rebound if verification is incorrect
Perform step 1；
Step 5：Signal return is performed, voice signal is sent to host computer.
It is described above, be only presently preferred embodiments of the present invention, any formal limitation not done to the present invention, it is every according to
Any simply modification, the equivalent variations made according to the technical spirit of the present invention to above example, each fall within the protection of the present invention
Within the scope of.
Claims (10)
1. a kind of intelligent toy robot based on speech recognition technology, it is characterised in that the robot includes：Head, its
Bottom is provided with two spikes；Left hand portion, its right side top are provided with a right plug；Right hand portion, its left side top are provided with
One left plug；Leg, its top are provided with an ornament；The head is provided with voice acquisition device；Inside the head
It is provided with speech recognition system.
2. meccano robot according to claim 1, it is characterised in that the profile on the head is a toy TV
Machine shape, the profile in the left hand portion is a toy water dispenser shape, and the profile of the right hand portion is a right hand portion shape, described
The profile of leg is a toy refrigerator shape, and the profile of the chest is a toy washing machine shape.
3. meccano robot according to claim 2, it is characterised in that the right hand portion includes：One semi-cylindrical
Dust catcher cylinder；The feet being connected with the bottom of the dust catcher cylinder, the feet and the phase of the dust catcher cylinder
Connecting portion is a movable part, and the feet can rotate before and after the connecting portion, when the feet rotate 180 degree after its
In another semicylinder that the embedded dust catcher cylinder is lacked.
A kind of 4. speech control system of the robot based on described in one of claims 1 to 3, it is characterised in that the system
Including：Voice recognition unit, sound intensity detection unit, phonetic synthesis unit, panel control unit, panel, main controller and host computer；
Signal is connected to voice recognition unit, sound intensity detection unit, phonetic synthesis unit, panel control unit to the master controller respectively
And host computer；The panel control unit signal is connected to panel.
5. speech control system as claimed in claim 4, it is characterised in that the voice recognition unit, operated for identifying
The password of personnel；It includes：Sound input module, spectrum analysis module, characteristic extracting module, sound identification module, voice are known
Other device, lists of keywords, pinyin string and MCU processors；The sound input module signal is connected to spectrum analysis module；It is described
Spectrum analysis module signal is connected to characteristic extracting module；The characteristic extracting module signal is connected to speech recognition device；It is described
Speech recognizer level signal is connected to MCU processors and lists of keywords；The lists of keywords signal is connected to pinyin string；
The MCU processor signals are connected to pinyin string.
6. speech control system as claimed in claim 5, it is characterised in that the sound input module, come from for receiving
Voice signal after master controller processing；The spectrum analysis module, for carrying out spectrum analysis to the voice signal of acquisition,
Voice signal after analysis is sent to characteristic extracting module；The characteristic extracting module, feature extraction is carried out to voice signal,
Signal after processing is sent to sound identification module；The sound identification module, for the key in lists of keywords
Voice signal is identified word, by the voice signal after identification send to；The MCU processors, for handling user's input
Keyword, the keyword after processing is sent to pinyin string；The pinyin string, for the keyword after processing to be converted into spelling
Sound string, pinyin string is sent to lists of keywords and stored, so as to update lists of keywords.
7. speech control system as claimed in claim 6, it is characterised in that the sound intensity detection unit, received for detecting
To voice signal whether be the password that is controlled to the equipment；The sound intensity detection unit includes：Sound acquisition module, number
Mould modular converter, sound intensity judge module, signal amplification module and signal sampling module；The sound acquisition module, for external
Portion's voice signal is acquired；The D/A converter module, for the voice signal collected to be converted into electric signal；The sound
Strong judge module, the signal intensity for receiving are judged, letter is sent the signal to if the sound intensity exceedes the threshold value of setting
Number amplification module, if the sound intensity is deleted the signal received not less than the threshold value of setting；The signal amplification module,
For signal to be amplified；The signal sampling module, for being sampled to signal, the voice signal after sampling is sent
To controller.
8. speech control system as claimed in claim 7, it is characterised in that the phonetic synthesis unit, including pronunciation person
Select unit, word speed adjustment unit, intonation adjustment unit, sound volume regulation unit and synthesis unit；The speaker selecting unit point
Level signal is connected to word speed adjustment unit, intonation adjustment unit and sound volume regulation unit, for what is sended over according to controller
Voice signal after speech recognition signal identifies randomly chooses different speakers, by phonetic feature corresponding to the speaker point
Do not send to word speed adjustment unit, intonation adjustment unit and sound volume regulation unit；The word speed adjustment unit, for according to reception
The speaker feature arrived, word speed feature corresponding to generation；The intonation adjustment unit, for special according to the speaker received
Sign, intonation feature corresponding to generation；The sound volume regulation unit, for according to the speaker feature that receives, corresponding to generation
Volume characteristics；Signal is connected to word speed adjustment unit, intonation adjustment unit and sound volume regulation unit to the synthesis unit respectively, uses
According to the final voice signal of word speed feature, intonation feature and the volume characteristics synthesis received.
A kind of 9. method of the speech control system based on described in one of claim 4 to 8, it is characterised in that methods described bag
Include following steps：
Step 1：Sound intensity detection unit carries out sound intensity detection to the voice signal received, if the sound intensity has exceeded the threshold value of setting
Voice signal is pre-processed, is then forwarded to controller, performs step 2；If the sound intensity will connect not less than the threshold value of setting
The signal received is deleted；
Step 2：Controller sends pretreated voice signal to voice recognition unit；Voice recognition unit is to receiving
Voice signal carries out voice recognition processing, and the voice signal after processing is sent to controller；
Step 3：Controller sends the voice signal after voice recognition processing to phonetic synthesis unit；Phonetic synthesis unit docks
The voice signal after voice recognition unit identifies received is synthesized, and generates final voice signal.
10. sound control method as claimed in claim 9, it is characterised in that the host computer plays back to voice signal
Method comprise the following steps：
Step 1：Host computer sends serial port command to controller；Monitoring control devices serial ports 0 whether terminal, step is performed if terminal
Rapid 2, without processing if non-terminal；
Step 2：Controller receives the control command of host computer, whether there is the machine address in the data for judging to receive, if
In the presence of then execution step 3, step 1 is continued executing with if there is no then rebound；
Step 3：Address is stored in buffering area by controller, judges whether address receives completely, if it is performs step 4, if
It is not to continue executing with step 1；
Step 4：Controller proceeds by CRC check, if verification is correct, performs step 5, the rebound if verification is incorrect
Perform step 1；
Step 5：Signal return is performed, voice signal is sent to host computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711148697.7A CN107789842A (en) | 2017-11-17 | 2017-11-17 | A kind of intelligent toy robot and its control system and method based on speech recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711148697.7A CN107789842A (en) | 2017-11-17 | 2017-11-17 | A kind of intelligent toy robot and its control system and method based on speech recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107789842A true CN107789842A (en) | 2018-03-13 |
Family
ID=61536163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711148697.7A Pending CN107789842A (en) | 2017-11-17 | 2017-11-17 | A kind of intelligent toy robot and its control system and method based on speech recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107789842A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108594672A (en) * | 2018-03-16 | 2018-09-28 | 中国地质大学（武汉） | A kind of drinking-water service robot active service method understood based on intention |
-
2017
- 2017-11-17 CN CN201711148697.7A patent/CN107789842A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108594672A (en) * | 2018-03-16 | 2018-09-28 | 中国地质大学（武汉） | A kind of drinking-water service robot active service method understood based on intention |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110444191A (en) | A kind of method, the method and device of model training of prosody hierarchy mark | |
| US10963493B1 (en) | Interactive game with robot system | |
| US20050154594A1 (en) | Method and apparatus of simulating and stimulating human speech and teaching humans how to talk | |
| CN203300127U (en) | Children teaching and monitoring robot | |
| CN108231070A (en) | Voice dialogue device, speech dialog method, voice dialogue program and robot | |
| CN107767861A (en) | voice awakening method, system and intelligent terminal | |
| CN108711430A (en) | Audio recognition method, smart machine and storage medium | |
| CN101524594A (en) | Anthropomorphic robot autonomously dancing along with rhythm | |
| CN101357269A (en) | Intelligent toy and use method thereof | |
| US11433302B2 (en) | Interactive play apparatus | |
| CN203812410U (en) | A touch screen display all-in-one machine intelligence development experience device | |
| CN106297784A (en) | Intelligent terminal plays the method and system of quick voice responsive identification | |
| WO2019216016A1 (en) | Information processing device, information processing method, and program | |
| CN109935226A (en) | A kind of far field speech recognition enhancing system and method based on deep neural network | |
| CN109712449A (en) | A kind of intellectual education learning system improving child's learning initiative | |
| CN107789842A (en) | A kind of intelligent toy robot and its control system and method based on speech recognition technology | |
| JP2001154685A (en) | Device and method for voice recognition and recording medium | |
| KR102171428B1 (en) | Dancing Robot that learns the relationship between dance and music | |
| CN108305527B (en) | A kind of memory training and test method based on speech recognition | |
| CN208065768U (en) | A kind of intelligent toy robot and its control system based on speech recognition technology | |
| CN108305629A (en) | A kind of scene learning Content acquisition methods, device, facility for study and storage medium | |
| CN105727572B (en) | A kind of self-learning method and self study device based on speech recognition of toy | |
| CN102141812A (en) | Robot | |
| US20150238877A1 (en) | Language translating doll | |
| CN112420063A (en) | Voice enhancement method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180313 |
|
| WD01 | Invention patent application deemed withdrawn after publication |