CN108172226A - A kind of voice control robot for learning response voice and action - Google Patents
A kind of voice control robot for learning response voice and action Download PDFInfo
- Publication number
- CN108172226A CN108172226A CN201810079661.6A CN201810079661A CN108172226A CN 108172226 A CN108172226 A CN 108172226A CN 201810079661 A CN201810079661 A CN 201810079661A CN 108172226 A CN108172226 A CN 108172226A
- Authority
- CN
- China
- Prior art keywords
- voice
- unit
- language
- training
- action
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0638—Interactive procedures
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
One embodiment of present specification discloses a kind of voice control robot for learning response voice,Including voice recognition unit,Put question to language recording unit,Response language recording unit,Voice map unit,Voice match unit,Voice call unit,The training voice of the voice recognition unit recognition training person,According to preset partitioning algorithm,Training voice is divided,Generate preceding language and rear language,Using preceding language as enquirement language,The enquirement language recording unit is written,Using rear language as response language,The response language recording unit is written,Voice map unit record puts question to the mapping relations of language and response language,Voice recognition unit identifies the control voice of controller,Voice match unit matches the enquirement language with control voice best match in language recording unit is putd question to,The mapping relations for puing question to language and response language that voice call unit is recorded according to voice map unit,Call the response language with language is putd question to there are mapping relations,The voice-output unit of robot plays response language.
Description
Technical field
Present specification belongs to robotic technology field, and in particular, to a kind of language for learning response voice and action
Sound control robot.
Technical background
The household service robot of many types all has certain speech recognition capabilities at present, and developer utilizes its voice
Recognition capability increases the functions such as voice control, question response, but this kind of function is generally all customized by developer for robot,
The diversified demand of ordinary user can not be met.For example, ordinary user may wish to robot, to a problem, there are one special
Different answer-mode, and robot usually only can search for a given answer by networking.For another example ordinary user wishes to use
The voice of oneself controls robot to do a series of actions, but can only use basic " going ahead " at present, " turning left ", " stretches
Go out arm " the control voice customized.Herein described technical solution can partly solve above two usage scenario
The problems in.
Invention content
【One】In order to allowing ordinary user according to the actual conditions of oneself, allow robot to it is certain the problem of make it is specific
Answer or specific response is made to general language, the technical solution of present specification, which discloses one kind, can learn response
The voice control robot of voice.
The voice control robot for learning response voice including voice recognition unit, enquirement language recording unit, is answered
Answer language recording unit, voice map unit, the training voice of the voice recognition unit recognition training person, according to preset segmentation
Training voice is divided, generates preceding language and rear language by algorithm, and using preceding language as language is putd question to, the enquirement language recording unit is written, will
Language is as response language afterwards, is written the response language recording unit, and the voice map unit record puts question to reflecting for language and response language
Penetrate relationship.
The voice control robot for learning response voice, further includes voice match unit, voice call unit, institute
State voice recognition unit identification controller control voice, the voice match unit matched in language recording unit is putd question to and
The enquirement language of control voice best match, the enquirement language and answer that the voice call unit is recorded according to the voice map unit
The mapping relations of language are answered, call the response language with language is putd question to there are mapping relations, the voice-output unit of robot plays response language.
The technical solution of present specification also discloses a kind of sound control method, applied to above-mentioned robot, including such as
Lower step：
According to preset partitioning algorithm, training voice is divided for S101, the training voice of voice recognition unit recognition training person,
Preceding language and rear language are generated, using preceding language as language is putd question to, language recording unit is putd question in write-in, using rear language as response language, described in write-in
Response language recording unit；
S102, the voice map unit record put question to the mapping relations of language and response language；
S201, voice recognition unit identify the control voice of controller, and voice match unit matches in language recording unit is putd question to
Go out the enquirement language with control voice best match；
S202, the mapping relations for puing question to language and response language that voice call unit is recorded according to the voice map unit, is called
With language is putd question to have the response language of mapping relations；
S203, the voice-output unit of robot play response language.
【Two】In order to allow ordinary user according to the actual conditions of oneself, robot is allowed to respond certain control voice, is made
Go out specific action or action sequence, the technical solution of present specification discloses a kind of voice control machine for learning action
People.
The voice control robot for learning action, including voice recognition unit, voice memorized unit, action recognition
Unit, action record unit and information MAP unit, the training voice of the voice recognition unit recognition training person, the voice
Recording unit records train voice, and the training action of the action recognition unit recognition training person obtains training action feature ginseng
Number table, the action record unit record training action characteristic parameter table, described information map unit record training voice and instruction
Practice the mapping relations of motion characteristic parameter list.
The voice control robot for learning action further includes voice match unit, action invocation unit, action mould
Quasi-simple member, the control voice of the voice recognition unit identification controller, obtains control voice information, the voice match unit
The training voice with control voice best match is matched in the voice memorized unit, the action invocation unit is according to institute
The training voice of information MAP unit record and the mapping relations of training action characteristic parameter table are stated, calls to have with training voice and reflect
The training action characteristic parameter table of relationship is penetrated, the action simulation unit is made simulation according to training action characteristic parameter table and moved
Make.
The voice control robot for learning action, voice recognition unit, voice match unit, action invocation list
Member and action simulation unit can process the control voice of a sequence context, make the simulated action of a sequence context.
The technical solution of present specification also discloses a kind of sound control method, applied to above-mentioned robot, including such as
Lower step：
S301, the training voice of voice recognition unit recognition training person, voice memorized unit record training voice；
S302, the training action of action recognition unit recognition training person obtain training action characteristic parameter table, action record unit
Record training action characteristic parameter table；
The mapping relations of S303, information MAP unit record training voice and training action characteristic parameter table；
S401, voice recognition unit identify the control voice of controller, and voice match unit matches in voice memorized unit
With the training voice of control voice best match；
S402, training voice that action invocation unit is recorded according to described information map unit and training action characteristic parameter table
Mapping relations call the training action characteristic parameter table for having mapping relations with training voice；
S403, action simulation unit make simulated action according to training action characteristic parameter table.
In above-mentioned steps, S301, S302, S303 can first be implemented repeatedly so that the multiple trained languages of information MAP unit record
The mapping relations of sound and training action characteristic parameter table.
In above-mentioned steps S401, if to a control voice identification and matching multiple trained voices, a sequence is formed
Training voice, then step S402, S404 can implement repeatedly.Therefore, the voice recognition unit, voice match unit, action
Call unit and action simulation unit can process a sequence context or non-coherent control voice, make a sequence context or
Non-coherent simulated action.
Description of the drawings
Fig. 1 is the robot schematic diagram of embodiment 1；
Fig. 2 is the robot schematic diagram of embodiment 2.
Specific embodiment
In order to enable the technical characteristic of the present invention is definitely, intuitively, embodiment is described below in conjunction with the accompanying drawings, this
The technical staff in field is it should be understood that these embodiments are exemplary in nature, not to the limitation of technical solution of the present invention, and
And section Example can be combined with each other or be combined with other known solutions.
【Embodiment 1】
In order to allowing ordinary user according to the actual conditions of oneself, allow robot to it is certain the problem of make specific answer or
Specific response is made to general language, present embodiment discloses a kind of voice control robots for learning response voice.
The voice control robot for learning response voice including voice recognition unit, enquirement language recording unit, is answered
Answer language recording unit, voice map unit.The division of the unit, only a kind of division of logic function, in actual implementation may be used
To there is other dividing mode.Multiple units can be combined or be integrated on software and hardware or some features can be ignored,
Or it does not perform.It will be understood by those skilled in the art that the unit may be realized by the form of hardware or software or software and hard
The form that part combines is realized.
The voice recognition unit includes voice sensing device, also including speech recognition software or voice recognition chip.When
Trainer sends out voice, the training voice of voice recognition unit recognition training person, according to preset partitioning algorithm, by training voice
Segmentation, generates preceding language and rear language.There are many partitioning algorithms.
For example, trainer sends out voice " if someone asks you ' what is your name ', you just answer ' I cries sprouts king greatly ' ",
Voice recognition unit identifies voice segments A " if someone asks you " and voice segments C " being answered if you ", according to voice partitioning algorithm
Voice segments B " what is your name " between voice segments A and C is denoted as preceding language, " I cries greatly by the voice segments D after voice segments C
Sprout king " it is used as rear language.
For another example trainer is two people, a people puts question to " child has gone to school today ", and a people, which answers, " goes to auntie house
Play ", then preset partitioning algorithm can be according to languages such as the range informations of voiceprint or sound of quizmaster and the person of answering
" child has gone to school today " is used as preceding language by sound characteristic information, " auntie house will be gone to play " and is used as rear language.
For another example trainer while voice " I likes you very much " is sent out according to " preceding language " button on robot body,
According to " rear language " button on robot body while voice " I also likes you " is sent out, then preset partitioning algorithm only needs root
According to the difference of button, " I likes you very much " is used as preceding language, " I also likes you " is used as rear language.
Optionally, above-mentioned " preceding language ", " rear language " are the voice recorded；Optionally, above-mentioned " preceding language ", " rear language " are electronization
Word, word or sentence, the word, word and sentence are converted from raw tone.
The enquirement language recording unit is written using preceding language as language is putd question in voice recognition unit, using rear language as response language,
The response language recording unit is written, the voice map unit record puts question to the mapping relations of language and response language.
Preferably, it is the database being made of the voice document of the label of each enquirement language to put question to language recording unit；
Preferably, response language recording unit is the database being made of the voice document of the label of each response language；
Preferably, text form document of the language recording unit for electronization is putd question to, is carried wherein having recorded each sentence that training obtains
Ask language；
Preferably, text form document of the response language recording unit for electronization is answered wherein having recorded each sentence that training obtains
Answer language.
Preferably, the voice map unit is form document, and language recording unit and response language note are putd question to wherein having recorded
There is the index putd question between language and response language of mapping relations in record unit per a pair.
Preferably, language and response language is putd question to form mapping or index relative using its filename or call number.
Preferably, language is putd question to and during response language in generation, if language recording unit is putd question to have an identical enquirement language, and response language
When recording unit has different response languages, with response language old in newly-generated response language update response language recording unit.
The voice control robot for learning response voice, further includes voice match unit, voice call unit.
After the completion of training, controller can be interacted by voice and robot.Aforementioned voice recognition unit identifies
The control voice of controller, voice match unit match the enquirement with control voice best match in language recording unit is putd question to
Language, mapping, the index relative of puing question to language and response language that the voice call unit is recorded according to the voice map unit, is adjusted
With with put question to language have mapping, index relative response language, the voice-output unit of robot plays response language.
Such as：
Controller sends out voice " what is your name " or " your name is ", and voice recognition unit identifies control voice " you
What is your name " or " your name is ", voice match unit match immediate enquirement language in language recording unit is putd question to
" what is your name ".Voice call unit is rely the hardware resource of operation for voice or text processing software and software.Voice
The filename or call number of enquirement language that call unit reading matches, according to puing question to language and response language in voice map unit
Mapping, index relative, get response language " I cries sprouts king greatly ".The voice-output unit of robot plays response language, and " I cries greatly
Sprout king ".
The present embodiment also discloses a kind of sound control method, applied to above-mentioned robot, includes the following steps：
According to preset partitioning algorithm, training voice is divided into for S101, the training voice of voice recognition unit recognition training person
Preceding language and rear language, using preceding language as language is putd question to, write-in puts question to language recording unit, using rear language as response language, the response is written
Language recording unit；
S102, the voice map unit record put question to mapping, the index relative of language and response language；
S201, voice recognition unit identify the control voice of controller, and voice match unit matches in language recording unit is putd question to
Go out the enquirement language with control voice best match；
S202, mapping, the index relative of puing question to language and response language that voice call unit is recorded according to the voice map unit,
Call with put question to language have mapping, index relative response language；
S203, the voice-output unit of robot play response language.
The technical staff in this category field can be understood that, for convenience and simplicity of description, the method for foregoing description
In, the concrete property and the course of work of each functional unit belonging to robot can refer to pair in aforementioned system embodiment
Situation is answered, details are not described herein.
【Embodiment 2】
In order to allow ordinary user according to the actual conditions of oneself, robot is allowed to respond certain control voice, is made specific
Action or action sequence, present embodiment discloses a kind of voice control robots for learning action.
The voice control robot for learning action, including voice recognition unit, voice memorized unit, action recognition
Unit, action record unit and information MAP unit, voice match unit, action invocation unit, action simulation unit.The list
The division of member, only a kind of division of logic function can have other dividing mode in actual implementation.Multiple units can be tied
It closes or is integrated on software and hardware or some features can be ignored or does not perform.It will be understood by those skilled in the art that
The form that the unit may be realized by the form of hardware or software or software and hardware combines is realized.
The voice recognition unit include voice sensing device, also including speech recognition software and or voice recognition chip.
When trainer sends out voice in the sphere of action of voice recognition unit, the training voice of voice recognition unit recognition training person,
The voice memorized unit record training voice.
The action recognition unit includes image sensing device, also including image recognition software and or image recognition chip.
When trainer makes action in the sphere of action of action recognition unit, the training action of action recognition unit recognition training person,
Obtain training action characteristic parameter table, the action record unit record training action characteristic parameter table.
Mapping, the index relative of described information map unit record training voice and training action characteristic parameter table.
Trainer can open the training mode of robot by modes such as voice, buttons, be entered as to training voice
And training action.
Such as：
Trainer can say initiating speech " starting to train ", and the sound identification module of robot identifies " starting to train ", then
Robot control system starts the training mode of robot；
When robot enters training mode, trainer first says one section of trained voice, for example, " jump one I practiced January 25
Good dancing ", robot voice recognition unit recognition training person training voice " dance one I practiced January 25
Step ", voice memorized unit record trains voice, and robot prompts trainer to open by voice, screen, action or indicator light later
Beginning does training action；
Trainer makes one section of training action, that is, jumps out a trained dancing on January 25, action recognition unit recognition training
The training action of person, obtains training action characteristic parameter table, i.e., image recognition software and or image recognition chip to image sensing
The image of the trainer of device intake is handled, and obtains space shape of each component part of trainer's limbs at a sequence moment
State by reference records such as the spatiality coordinate of each moment limbs each section, angles, forms the training action of time series
Parameter list, action record unit record training action characteristic parameter table, in practical situations, action record Single Component Management multiple
Training action characteristic parameter list file；
After training action, trainer says end voice " terminating training ", and the sound identification module of robot identifies
" terminating training ", the training voice that information MAP unit record newly obtains and the training action characteristic parameter table newly obtained reflect
It penetrates, index relative, robot control system closes training mode.
After the completion of training, controller can be made by voice control robot has mapping, index relative with voice
Action.
Controller sends out control voice, for example, " jump one my the dancing practiced on January 25 " or " jumping what I trained January
Dancing ", the control voice " jump one my dancing practice on January 25 " of above-mentioned voice recognition unit identification controller or " jump
Wave the dancing of training in January ", the voice match unit matches and control voice best match in the voice memorized unit
Training voice " jump one my dancing practiced on January 25 ", the action invocation unit is according to described information map unit
The training voice of record and mapping, the index relative of training action characteristic parameter table, call has mapping, index to close with training voice
The training action characteristic parameter table of system.
The action simulation unit includes motion control software, processor, anthropomorphous machine's structure etc., anthropomorphous machine's structure
It can be corresponded with limbs each section of trainer, each moment limbs each section in training action characteristic parameter table
The parameters such as coordinate, angle, motion control software is under the assistance of the hardware resources such as processor so that anthropomorphous machine mechanism it is each
Partial simulation limbs each section, makes whole body echomotism with joint efforts, trainer before imitating " jump one I practiced January 25
Good dancing ".
The voice control robot for learning action, voice recognition unit, voice match unit, action invocation list
Member and action simulation unit can process the control voice of a sequence context, make the simulated action of a sequence context.
For example, trainer allows robot to obtain trained voice respectively by sending out trained voice and making training action
" turning left ", " five steps of going ahead ", " turning right " corresponding training action characteristic parameter table and mapping, index relative, then control
Person can send out the control voice of " turning left, five steps of going ahead, then turn right ", and voice recognition unit identifies the control language of controller
Sound, voice match unit match the training voice with control voice best match in voice memorized unit, according to three
Control voice is divided into order three to control languages by the training voice " turning left " known, " five steps of going ahead ", " turning right "
Sound finally sequentially calls three training action characteristic parameter tables for having mapping relations with three trained voices, moves respectively
Make analogue unit and coherent simulated action is made according to the precedence of three training action characteristic parameter tables.
The present embodiment also discloses a kind of sound control method, applied to above-mentioned robot, includes the following steps：
S301, the training voice of voice recognition unit recognition training person, voice memorized unit record training voice；
S302, the training action of action recognition unit recognition training person obtain training action characteristic parameter table, action record unit
Record training action characteristic parameter table；
The mapping relations of S303, information MAP unit record training voice and training action characteristic parameter table；
S401, voice recognition unit identify the control voice of controller, and voice match unit matches in voice memorized unit
With the training voice of control voice best match；
S402, training voice that action invocation unit is recorded according to described information map unit and training action characteristic parameter table
Mapping relations call the training action characteristic parameter table for having mapping relations with training voice；
S403, action simulation unit make simulated action according to training action characteristic parameter table.
In above-mentioned steps, S301, S302, S303 can first be implemented repeatedly so that the multiple trained languages of information MAP unit record
The mapping relations of sound and training action characteristic parameter table.
In above-mentioned steps S401, if to a control voice identification and matching multiple trained voices, a sequence is formed
Training voice, then step S402, S404 can implement repeatedly.
The voice recognition unit, voice match unit, action invocation unit and action simulation unit can connect a sequence
It passes through or non-coherent control voice processes, make a sequence context or non-coherent simulated action.
The technical staff in this category field can be understood that, for convenience and simplicity of description, the method for foregoing description
In, the concrete property and the course of work of each functional unit belonging to robot can refer to pair in aforementioned system embodiment
Situation is answered, details are not described herein.
Above example is only to illustrate the technical solution of present specification rather than its technical solution is limited, this
The technical staff in field is it is understood that carry out the technical solution recorded in foregoing embodiments the obtained skill of non-creative modification
Art scheme carries out which part technical characteristic the technical solution that equivalent replacement is obtained, its essence is not made to be detached from this
The range of technical solution described in application documents.
Claims (10)
1. a kind of voice control robot for learning response voice, which is characterized in that including voice recognition unit, put question to language note
Record unit, response language recording unit, voice map unit, the training voice of the voice recognition unit recognition training person, according to
Training voice is divided, generates preceding language and rear language by preset partitioning algorithm, and using preceding language as language is putd question to, the enquirement language is written
Using rear language as response language, the response language recording unit is written in recording unit, the voice map unit record put question to language and
The mapping relations of response language.
2. robot as claimed in claim 1, which is characterized in that further include voice match unit, voice call unit, the voice
Recognition unit identifies the control voice of controller, and the voice match unit matches and control language in language recording unit is putd question to
The enquirement language of sound best match, the voice call unit put question to language and response language according to what the voice map unit recorded
Mapping relations, call the response language with language is putd question to have mapping relations, and the voice-output unit of robot plays response language.
3. a kind of sound control method, which is characterized in that include the following steps：
According to preset partitioning algorithm, training voice is divided into for S101, the training voice of voice recognition unit recognition training person
Preceding language and rear language, using preceding language as language is putd question to, write-in puts question to language recording unit, using rear language as response language, the response is written
Language recording unit；
S102, the voice map unit record put question to the mapping relations of language and response language.
4. sound control method as claimed in claim 6, which is characterized in that further include following steps：
S201, voice recognition unit identify the control voice of controller, and voice match unit matches in language recording unit is putd question to
Go out the enquirement language with control voice best match；
S202, the mapping relations for puing question to language and response language that voice call unit is recorded according to the voice map unit, is called
With language is putd question to have the response language of mapping relations；
S203, the voice-output unit of robot play response language.
5. a kind of voice control robot for learning action, which is characterized in that including voice recognition unit, voice record list
Member, action recognition unit, action record unit and information MAP unit, the training language of the voice recognition unit recognition training person
Sound, the voice memorized unit record training voice, the training action of the action recognition unit recognition training person are trained
Motion characteristic parameter list, the action record unit record training action characteristic parameter table, described information map unit record instruction
Practice the mapping relations of voice and training action characteristic parameter table.
6. robot as claimed in claim 5, which is characterized in that further include voice match unit, action invocation unit, action simulation
Unit, the control voice of the voice recognition unit identification controller, the voice match unit is in the voice memorized unit
In match training voice with control voice best match, the action invocation unit is recorded according to described information map unit
Training voice and training action characteristic parameter table mapping relations, call has the training action of mapping relations special with training voice
Parameter list is levied, the action simulation unit makes simulated action according to training action characteristic parameter table.
7. robot as claimed in claim 6, which is characterized in that the voice recognition unit, voice match unit, action invocation list
Member and action simulation unit can process the control voice of a sequence, make the simulated action of a sequence.
8. a kind of sound control method, which is characterized in that include the following steps：
S301, the training voice of voice recognition unit recognition training person, voice memorized unit record training voice；
S302, the training action of action recognition unit recognition training person obtain training action characteristic parameter table, action record unit
Record training action characteristic parameter table；
The mapping relations of S303, information MAP unit record training voice and training action characteristic parameter table.
9. sound control method as claimed in claim 8, which is characterized in that further include following steps：
S401, voice recognition unit identify the control voice of controller, and voice match unit matches in voice memorized unit
With the training voice of control voice best match；
S402, training voice that action invocation unit is recorded according to described information map unit and training action characteristic parameter table
Mapping relations call the training action characteristic parameter table for having mapping relations with training voice；
S403, action simulation unit make simulated action according to training action characteristic parameter table.
10. sound control method as claimed in claim 9, which is characterized in that
Described step S301, S302, S303 can first be implemented repeatedly so that the multiple trained voices of information MAP unit record and training
The mapping relations of motion characteristic parameter list；
In the step S401, if to a control voice identification and matching multiple trained voices, the instruction of a sequence is formed
Practice voice, then step S402, S404 can be implemented repeatedly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810079661.6A CN108172226A (en) | 2018-01-27 | 2018-01-27 | A kind of voice control robot for learning response voice and action |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810079661.6A CN108172226A (en) | 2018-01-27 | 2018-01-27 | A kind of voice control robot for learning response voice and action |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108172226A true CN108172226A (en) | 2018-06-15 |
Family
ID=62516088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810079661.6A Pending CN108172226A (en) | 2018-01-27 | 2018-01-27 | A kind of voice control robot for learning response voice and action |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108172226A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113438564A (en) * | 2021-06-22 | 2021-09-24 | 武汉领普科技有限公司 | Control system, terminal processing method, wireless switch and processing method thereof |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6266635B1 (en) * | 1999-07-08 | 2001-07-24 | Contec Medical Ltd. | Multitasking interactive voice user interface |
| CN1380846A (en) * | 2000-03-31 | 2002-11-20 | 索尼公司 | Robot device, robot device action control method, external force detecting device and method |
| CN1507617A (en) * | 2002-03-06 | 2004-06-23 | ���ṫ˾ | Learning apparatus, learning method, and robot apparatus |
| CN104392720A (en) * | 2014-12-01 | 2015-03-04 | 江西洪都航空工业集团有限责任公司 | Voice interaction method of intelligent service robot |
| CN104965426A (en) * | 2015-06-24 | 2015-10-07 | 百度在线网络技术（北京）有限公司 | Intelligent robot control system, method and device based on artificial intelligence |
| CN105528349A (en) * | 2014-09-29 | 2016-04-27 | 华为技术有限公司 | Method and apparatus for analyzing question based on knowledge base |
| CN105825268A (en) * | 2016-03-18 | 2016-08-03 | 北京光年无限科技有限公司 | Method and system for data processing for robot action expression learning |
| CN106292424A (en) * | 2016-08-09 | 2017-01-04 | 北京光年无限科技有限公司 | Music data processing method and device for anthropomorphic robot |
| CN106326208A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | System and method for training robot via voice |
| CN106547884A (en) * | 2016-11-03 | 2017-03-29 | 深圳量旌科技有限公司 | A kind of behavior pattern learning system of augmentor |
| CN106601237A (en) * | 2016-12-29 | 2017-04-26 | 上海智臻智能网络科技股份有限公司 | Interactive voice response system and voice recognition method thereof |
| CN106649825A (en) * | 2016-12-29 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Voice interaction system, establishment method and device thereof |
| CN106782539A (en) * | 2017-01-16 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent sound exchange method, apparatus and system |
| CN106847279A (en) * | 2017-01-10 | 2017-06-13 | 西安电子科技大学 | Man-machine interaction method based on robot operating system ROS |
| CN107450367A (en) * | 2017-08-11 | 2017-12-08 | 上海思依暄机器人科技股份有限公司 | A kind of voice transparent transmission method, apparatus and robot |
| CN107443396A (en) * | 2017-08-25 | 2017-12-08 | 魔咖智能科技（常州）有限公司 | A kind of intelligence for imitating human action in real time accompanies robot |
| CN107463636A (en) * | 2017-07-17 | 2017-12-12 | 北京小米移动软件有限公司 | Data configuration method, device and the computer-readable recording medium of interactive voice |
-
2018
- 2018-01-27 CN CN201810079661.6A patent/CN108172226A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6266635B1 (en) * | 1999-07-08 | 2001-07-24 | Contec Medical Ltd. | Multitasking interactive voice user interface |
| CN1380846A (en) * | 2000-03-31 | 2002-11-20 | 索尼公司 | Robot device, robot device action control method, external force detecting device and method |
| CN1507617A (en) * | 2002-03-06 | 2004-06-23 | ���ṫ˾ | Learning apparatus, learning method, and robot apparatus |
| CN105528349A (en) * | 2014-09-29 | 2016-04-27 | 华为技术有限公司 | Method and apparatus for analyzing question based on knowledge base |
| CN104392720A (en) * | 2014-12-01 | 2015-03-04 | 江西洪都航空工业集团有限责任公司 | Voice interaction method of intelligent service robot |
| CN104965426A (en) * | 2015-06-24 | 2015-10-07 | 百度在线网络技术（北京）有限公司 | Intelligent robot control system, method and device based on artificial intelligence |
| CN106326208A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | System and method for training robot via voice |
| CN105825268A (en) * | 2016-03-18 | 2016-08-03 | 北京光年无限科技有限公司 | Method and system for data processing for robot action expression learning |
| CN106292424A (en) * | 2016-08-09 | 2017-01-04 | 北京光年无限科技有限公司 | Music data processing method and device for anthropomorphic robot |
| CN106547884A (en) * | 2016-11-03 | 2017-03-29 | 深圳量旌科技有限公司 | A kind of behavior pattern learning system of augmentor |
| CN106601237A (en) * | 2016-12-29 | 2017-04-26 | 上海智臻智能网络科技股份有限公司 | Interactive voice response system and voice recognition method thereof |
| CN106649825A (en) * | 2016-12-29 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Voice interaction system, establishment method and device thereof |
| CN106847279A (en) * | 2017-01-10 | 2017-06-13 | 西安电子科技大学 | Man-machine interaction method based on robot operating system ROS |
| CN106782539A (en) * | 2017-01-16 | 2017-05-31 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent sound exchange method, apparatus and system |
| CN107463636A (en) * | 2017-07-17 | 2017-12-12 | 北京小米移动软件有限公司 | Data configuration method, device and the computer-readable recording medium of interactive voice |
| CN107450367A (en) * | 2017-08-11 | 2017-12-08 | 上海思依暄机器人科技股份有限公司 | A kind of voice transparent transmission method, apparatus and robot |
| CN107443396A (en) * | 2017-08-25 | 2017-12-08 | 魔咖智能科技（常州）有限公司 | A kind of intelligence for imitating human action in real time accompanies robot |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113438564A (en) * | 2021-06-22 | 2021-09-24 | 武汉领普科技有限公司 | Control system, terminal processing method, wireless switch and processing method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6816925B2 (en) | Data processing method and equipment for childcare robots | |
| CN108000526B (en) | Dialogue interaction method and system for intelligent robot | |
| US20200210901A1 (en) | Dynamic learning method and system for robot, robot and cloud server | |
| CN112204564A (en) | System and method for speech understanding via integrated audio and visual based speech recognition | |
| US11017551B2 (en) | System and method for identifying a point of interest based on intersecting visual trajectories | |
| CN111801730A (en) | System and method for artificial intelligence driven automated companion | |
| CN105723360A (en) | Improving natural language interactions using emotional modulation | |
| US11308312B2 (en) | System and method for reconstructing unoccupied 3D space | |
| US20190251350A1 (en) | System and method for inferring scenes based on visual context-free grammar model | |
| US20210043106A1 (en) | Technology based learning platform for persons having autism | |
| CN106774845B (en) | intelligent interaction method, device and terminal equipment | |
| US20190304451A1 (en) | Dialogue method, dialogue system, dialogue apparatus and program | |
| US10607504B1 (en) | Computer-implemented systems and methods for a crowd source-bootstrapped spoken dialog system | |
| Strauss et al. | Proactive spoken dialogue interaction in multi-party environments | |
| WO2021003471A1 (en) | System and method for adaptive dialogue management across real and augmented reality | |
| US20190253724A1 (en) | System and method for visual rendering based on sparse samples with predicted motion | |
| Lison et al. | Spoken dialogue systems: the new frontier in human-computer interaction | |
| CN112204563A (en) | System and method for visual scene construction based on user communication | |
| CN110134863A (en) | The method and device that application program is recommended | |
| WO2020256993A1 (en) | System and method for personalized and multimodal context aware human machine dialogue | |
| KR20160051020A (en) | User-interaction toy and interaction method of the toy | |
| JP2023055910A (en) | Robot, dialogue system, information processing method, and program | |
| CN109741744B (en) | AI robot conversation control method and system based on big data search | |
| CN117541444B (en) | Interactive virtual reality talent expression training method, device, equipment and medium | |
| CN108172226A (en) | A kind of voice control robot for learning response voice and action |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180615 |
|
| WD01 | Invention patent application deemed withdrawn after publication |