CN107424450A - Pronunciation correction system and method - Google Patents
Pronunciation correction system and method Download PDFInfo
- Publication number
- CN107424450A CN107424450A CN201710666754.4A CN201710666754A CN107424450A CN 107424450 A CN107424450 A CN 107424450A CN 201710666754 A CN201710666754 A CN 201710666754A CN 107424450 A CN107424450 A CN 107424450A
- Authority
- CN
- China
- Prior art keywords
- pronunciation
- user
- difference
- signal
- video
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000005070 sampling Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims description 19
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 210000000214 mouth Anatomy 0.000 claims description 9
- 210000003128 head Anatomy 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 abstract description 8
- 210000001097 facial muscle Anatomy 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a kind of pronunciation correction system and method, the pronunciation correction system is used for the pronunciation for correcting user, the pronunciation correction system includes a signal sampling module and a signal processing module, the signal sampling module is used to gather signal during user pronunciation, the signal processing module, for the RP signal according to corresponding to signal acquisition during user pronunciation, and the signal during user pronunciation and the RP signal are contrasted, if the difference between signal and the RP signal during user pronunciation meets pre-provisioning request, it is correct then to prompt the user with pronunciation；If the difference between signal and the RP signal during user pronunciation is unsatisfactory for pre-provisioning request, pronunciation mistake is prompted the user with.The present invention realizes carries out result feedback by signal processing module at once after a word is run through, and judges whether user pronunciation is correct, interactive height, contrasts the pronunciation and standard pronunciation of user in real time, immediately convenient.
Description
Technical field
The present invention relates to intelligent CAL technical field, more particularly to a kind of pronunciation correction system and method.
Background technology
The use of English is now more and more common, the grammer of English, write, combine into syllables etc. it is all entirely different with Chinese, in
Study introduction of the literary crowd for mother tongue to English certainly will have difficulty to a certain extent, and the pronunciation for spoken language needs to practice repeatedly
Practise the requirement that can be only achieved pronunciation standard.In default of the language environment of an immersion, and English equivalents method and Chinese
Difference, even if the study of many people often for many years is still Dumb English.
The content of the invention
It is interactive to solve existing pronunciation correction it is an object of the invention to provide a kind of pronunciation correction system and method
The problem of low.
In order to solve the above technical problems, the present invention provides a kind of pronunciation correction system, the pronunciation correction system is used to entangle
The pronunciation of positive user, the pronunciation correction system include：
One signal sampling module, signal during for gathering user pronunciation；And
One signal processing module, for the RP signal according to corresponding to the signal acquisition during user pronunciation, and
The signal during user pronunciation and the RP signal are contrasted, if the signal during user pronunciation with it is described
Difference between RP signal meets pre-provisioning request, then it is correct to prompt the user with pronunciation；If the letter during user pronunciation
Difference number between the RP signal is unsatisfactory for pre-provisioning request, then prompts the user with pronunciation mistake and according to the use
The difference between signal and RP signal when family is pronounced directly gives correcting method.
Optionally, in described pronunciation correction system, in addition to：
One standard signal library module, RP signal is stored with the standard signal library module.
Optionally, in described pronunciation correction system, the signal during user pronunciation includes figure during user pronunciation
Voice when picture or video and/or user pronunciation, the RP signal include RP image or video and/or standard
Pronounce voice.
Optionally, in described pronunciation correction system, the signal processing module includes an image or video decomposes mould
Block and image or video contrast module are wanted, wherein：
Described image or video decomposing module by the image during user pronunciation or video according to the lip motion of user,
Nozzle type change, lip folding angle and/or tongue are in the oral cavity or extrabuccal position is decomposed, and form multiple user pronunciations
Section image or video；
The RP image or video include multiple RP section images or video；
Described image or video contrast module send out multiple user pronunciation section images or video with multiple standards
Segment image or video are contrasted, and draw difference lip motion, the change of difference nozzle type, difference lip folding angle and/or difference
Different tongue position.
Optionally, in described pronunciation correction system, the signal processing module also include a speech decomposition module and
One Speech comparison module, wherein：
The speech decomposition module is by the voice during user pronunciation according to the tone of user, frequency, tone color, phoneme
And/or phoneme is decomposed, multiple user pronunciation section voices are formed；
The RP voice includes multiple RP section voices；
The Speech comparison module carries out multiple user pronunciation section voices and multiple RP section voices
Contrast, draws difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme.
Optionally, in described pronunciation correction system, the pronunciation correction system also include a voice output module and
One image or Video Output Modules, wherein：
Whether the voice output module and described image or Video Output Modules prompting user speech are correct, and nozzle type
Whether correct, user chooses whether to listen to RP voice and RP section voice, and user chooses whether to check mark
Quasi- pronunciation image or video and/or RP section image or video；
The voice output module is according to difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme
Prompting is made to user, and is pronounced voice and/or RP section voice to user's outputting standard；
Described image or Video Output Modules are according to difference lip motion, the change of difference nozzle type, difference lip folding angle
And/or difference tongue position makes prompting to user, and pronounce image or video and/or RP section to user's outputting standard
Image or video.
The present invention also provides a kind of pronunciation correction method, and the pronunciation correction method includes：
Gather signal during user pronunciation；And
The signal during user pronunciation and a RP signal are contrasted；If the signal during user pronunciation
Difference between the RP signal meets pre-provisioning request, then it is correct to prompt the user with pronunciation；If the user pronunciation
When signal and the RP signal between difference be unsatisfactory for pre-provisioning request, then prompt the user with pronunciation mistake and basis
The difference between signal and the RP signal during user pronunciation directly gives correcting method.
Optionally, in described pronunciation correction method, the signal during user pronunciation includes figure during user pronunciation
Voice when picture or video and/or user pronunciation, the RP signal include RP image or video and/or standard
Pronounce voice.
Optionally, in described pronunciation correction method, signal processing module is by the signal during user pronunciation and institute
Stating RP signal and carrying out contrast includes：
Image or video decomposing module are by the lip motion of the image during user pronunciation or video according to user, nozzle type
Change, lip folding angle and/or tongue are in the oral cavity or extrabuccal position is decomposed, and form multiple user pronunciation section figures
Picture or video；
The RP image or video include multiple RP section images or video；
Image or video contrast module are by multiple user pronunciation section images or video and multiple RP sections
Image or video are contrasted, and draw difference lip motion, the change of difference nozzle type, difference lip folding angle and/or difference tongue
Head position.
Optionally, in described pronunciation correction method, signal processing module is by the signal during user pronunciation and institute
Stating RP signal and being contrasted also includes：
Speech decomposition module by the voice during user pronunciation according to the tone of user, frequency, tone color, phoneme and/or
Phoneme is decomposed, and forms multiple user pronunciation section voices；
The RP voice includes multiple RP section voices；
Speech comparison module is contrasted multiple user pronunciation section voices and multiple RP section voices,
Draw difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme.
Optionally, in described pronunciation correction method, providing correcting method includes：
Whether voice output module and image or Video Output Modules prompting user speech are correct, and just whether nozzle type
Really, user chooses whether to listen to RP voice and RP section voice, and user chooses whether to check RP
Image or video and/or RP section image or video；
Voice output module according to difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme to
Prompting is made at family, and pronounces voice and/or RP section voice to user's outputting standard；
Image or Video Output Modules according to difference lip motion, the change of difference nozzle type, difference lip folding angle and/or
Difference tongue position makes prompting to user, and pronounces image or video and/or RP section image to user's outputting standard
Or video.
In pronunciation correction system and method provided by the invention, by the signal processing module by the user pronunciation
When signal contrasted with the RP signal, if the signal during user pronunciation and the RP signal it
Between difference meet pre-provisioning request, then it is correct to prompt the user with pronunciation；If the signal during user pronunciation is sent out with the standard
Difference between sound signal is unsatisfactory for pre-provisioning request, then prompts the user with pronunciation mistake, it is possible to achieve after a word is run through
Result feedback is carried out by signal processing module at once, judges whether user pronunciation is correct, interactive height, contrasts user's in real time
Pronunciation and standard pronunciation, it is immediately convenient.
The present invention provides a kind of intelligent CAL and the method for correcting foreign language pronunciation, using existing mobile phone, due to mesh
Preceding mobile phone has front camera (image or video during user pronunciation can be gathered as signal sampling module), display screen
(can be used as image or Video Output Modules), earphone (can be used as voice output module) and microphone (can be used as signal
Sampling module gathers voice during user pronunciation), so more hardware costs, features simple structure need not be increased.
Naturally the various combinations pronunciation with phonetic symbol is combined built in pronunciation correction system into syllables, corresponding video display animation and corresponding
Pronunciation rule.Related software corresponding to the pronunciation correction system provided in user is on mobile phone using the present invention carries out English
, can be with the word sentence pattern of reading English during study.After reading, mobile phone camera catches the nozzle type of user automatically, and facial muscle changes,
What is stored in the state and data of tooth tongue carries out contrast confirmation, while sound and standard voice are contrasted, and works as discovery
When having notable difference, voice reports to user speech rule, and user can select to examine to read Show Me animation.
It is and described if image or video during the user pronunciation and the RP image or the comparing result of video
Voice during user pronunciation is different from the comparing result of the RP voice, then voice output module and image or video are defeated
Voice when going out module prompts user pronunciation is correct, and the image or video during pronunciation are incorrect, i.e., when nozzle type and standard not phase
Symbol, but when pronunciation and standard pronunciation approximation, system can prompt user to have a good pronunciation, and nozzle type is incorrect.All are defined by practicality, user
It can select voluntarily to consult Demonstration of standardization video or listen to standard pronunciation demonstration.
Brief description of the drawings
Fig. 1 is the pronunciation correction system schematic in one embodiment of the invention；
Fig. 2 is the pronunciation correction method schematic diagram in one embodiment of the invention；
Shown in figure：10- signal sampling modules；11- images or video sampling module；12- speech sample modules；20- is marked
Calibration signal library module；21- standard pictures or video library module；22- received pronunciation library modules；30- signal processing modules；31- schemes
Picture or video decomposing module；32- images or video contrast module；33- speech decomposition modules；34- Speech comparison modules；40- languages
Sound output module；50- images or Video Output Modules.
Embodiment
In the introduction it has been already mentioned that many people learn foreign languages (such as English) for many years but pronunciation is still nonstandard.Therefore, once
Attempt to catch pronunciation video using camera, to attempt to correct one's pronunciation, but this person of needing to use oneself playback is watched, and not
Pronunciation guidance can be targetedly provided, can only simply provide the marking different with demonstration sound, or repeats playing demonstration sound, it is interactive
Property is not high, can not targetedly lift the validity of verbal learning.
Based on the studies above, present inventor proposes a kind of interactive high pronunciation correction system, by user pronunciation
When signal contrasted with RP signal, if between the signal and the RP signal during user pronunciation
Difference meets that pre-provisioning request then prompts the user with pronunciation correctly, if signal and the RP signal during user pronunciation
Between difference be unsatisfactory for pre-provisioning request and then prompt the user with pronunciation mistake, it is possible to achieve at once by believing after a word is run through
Number processing module carries out result feedback, judges whether user pronunciation is correct, interactive height, contrasts the pronunciation and mark of user in real time
Quasi- pronunciation, it is immediately convenient.
Pronunciation correction system and method proposed by the present invention are made below in conjunction with the drawings and specific embodiments further detailed
Explanation.According to following explanation and claims, advantages and features of the invention will become apparent from.It should be noted that accompanying drawing is adopted
Non- accurately ratio is used with very simplified form and, only to convenience, lucidly aid in illustrating the embodiment of the present invention
Purpose.
As shown in figure 1, the present embodiment provides a kind of pronunciation correction system, the pronunciation correction system is used to correct user's
Pronunciation, the pronunciation correction system include signal sampling module 10, standard signal library module 20, signal processing module 30.It is described
Signal sampling module 10 is used to gather signal during user pronunciation.RP letter is stored with the standard signal library module 20
Number.The signal processing module 30 is used for the RP signal according to corresponding to the signal acquisition during user pronunciation, and will
The signal during user pronunciation is contrasted with the RP signal, if the signal during user pronunciation and the mark
Difference between quasi- pronunciation signal meets pre-provisioning request, then it is correct to prompt the user with pronunciation；If the signal during user pronunciation
Difference between the RP signal is unsatisfactory for pre-provisioning request, then prompts the user with pronunciation mistake and according to the user
The difference between signal and RP signal during pronunciation directly gives correcting method.The signal during user pronunciation
Difference between the RP signal meets that pre-provisioning request refers to that both gaps require less than difference threshold, or similar
Degree is more than similarity threshold requirement.The difference between signal and the RP signal during user pronunciation is unsatisfactory for pre-
Provisioning request refers to both gaps more than difference threshold requirement, or similarity is less than similarity threshold requirement.
Specifically, in described pronunciation correction system, signal sampling module 10 includes an image or video sampling module
11 and a speech sample module 12, image or video sampling module 11 gather the image or video during user pronunciation, speech sample
Image or video when signal during voice, i.e. user pronunciation when module 12 gathers user pronunciation includes user pronunciation
And/or voice during user pronunciation.Standard signal library module 20 includes standard picture or video library module 21 and received pronunciation storehouse
Module 22, standard picture or video library module 21 are stored with RP image or video, and received pronunciation library module 22 is stored with
RP voice, i.e., described RP signal include RP image or video and/or RP voice.
Further, in described pronunciation correction system, the signal processing module 30 includes an image or video point
Solve the image of module 31 and one or video contrast module 32.Described image or video decomposing module 31 are by the figure during user pronunciation
As or video changed according to the lip motion of user, nozzle type, lip folding angle and/or tongue in the oral cavity or extrabuccal position
Put and decomposed, form multiple user pronunciation section images or video；The RP image or video are sent out including multiple standards
Segment image or video；Described image or video contrast module 32 are by multiple user pronunciation section images or video and multiple institutes
State RP section image or video is contrasted, draw difference lip motion, the change of difference nozzle type, difference lip folding angle
And/or difference tongue position.
In addition, the signal processing module 30 may also include a speech decomposition module 33 and a Speech comparison module 34.Institute
Speech decomposition module 33 is stated by the voice during user pronunciation according to the tone of user, frequency, tone color, phoneme and/or phoneme
Decomposed, form multiple user pronunciation section voices；The RP voice includes multiple RP section voices；Institute's predicate
Sound contrast module 34 is contrasted multiple user pronunciation section voices and multiple RP section voices, draws difference
Tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme.
As shown in figure 1, in described pronunciation correction system, the pronunciation correction system also includes a voice output module
40 and image or a Video Output Modules 50.The voice output module 40 and described image or the prompting of Video Output Modules 50 are used
Whether family voice is correct, and whether nozzle type is correct, and user chooses whether to listen to RP voice and RP section voice,
And user chooses whether to check RP image or video and/or RP section image or video；The voice output
Module 40 makes prompting according to difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme to user, and to
User's outputting standard pronunciation voice and/or RP section voice；Described image or Video Output Modules 50 are according to difference lip
Action, the change of difference nozzle type, difference lip folding angle and/or difference tongue position make prompting to user, and defeated to user
Go out RP image or video and/or RP section image or video.Specifically, voice output module 40 and image or regarding
The output prompting result of frequency output module 50 includes, the difference between signal and the RP signal when the user pronunciation
Different when meeting pre-provisioning request, voice output module 40 issues the user with the voice of " correct ", or image or Video Output Modules
Show the picture of " correct "；The difference between signal and the RP signal when the user pronunciation is unsatisfactory for pre-
During provisioning request, voice output module 40 issues the user with the voice of " mistake ", or image or Video Output Modules show " mistake
Picture by mistake ", further, voice output module 40 and image or Video Output Modules 50 can also show pronunciation to user
Voice mistake (such as：Phoneme not to) or pronunciation image or video error (such as：Nozzle type not to), further, language
Sound output module 40 and image or Video Output Modules 50 can also export correctly pronunciation voice and image or video, to enter one
Step helps user to be corrected.
Finally, in described pronunciation correction system, if the image or video during the user pronunciation are sent out with the standard
The comparing result of sound image or video, with the comparing result of the voice during user pronunciation and the RP voice not
Together, then voice output module and voice when image or Video Output Modules prompting user pronunciation are correct, image during pronunciation or
Video is incorrect, or is defined by the comparing result of the voice during user pronunciation and the RP voice.
In pronunciation correction system and method provided by the invention, the user is sent out by the signal processing module 30
Signal during sound is contrasted with the RP signal, if the signal during user pronunciation and the RP signal
Between difference meet pre-provisioning request, then it is correct to prompt the user with pronunciation；If signal and the standard during user pronunciation
Difference between pronunciation signal is unsatisfactory for pre-provisioning request, then prompts the user with pronunciation mistake, it is possible to achieve running through a word
Result feedback is carried out by signal processing module 30 at once afterwards, judges whether user pronunciation is correct, interactive height, in real time contrast is used
The pronunciation and standard pronunciation at family, it is immediately convenient.
The present invention provides a kind of intelligent CAL and the method for correcting foreign language pronunciation, using existing mobile phone, due to mesh
Preceding mobile phone has front camera (image or video during user pronunciation can be gathered as signal sampling module), display screen
(can be used as image or Video Output Modules), earphone (can be used as voice output module) and microphone (can be used as signal
Sampling module gathers voice during user pronunciation), so more hardware costs, features simple structure need not be increased.Certainly, also may be used
During using the camera of other mobile terminals such as PAD outside using mobile phone as signal sampling module to gather user pronunciation
Image or video, or can also using PC camera as signal sampling module to gather user pronunciation when image or regard
Frequently.Similarly, described image or Video Output Modules, voice output module etc. are also not limited to the accessory of mobile phone, and can use
The accessories of other mobile terminals or PC realizes above-mentioned function.
Naturally the various combinations pronunciation with phonetic symbol is combined built in pronunciation correction system into syllables, corresponding video display animation and corresponding
Pronunciation rule.Related software corresponding to the pronunciation correction system provided in user is on mobile phone using the present invention carries out English
, can be with the word sentence pattern of reading English during study.After reading, mobile phone camera catches the nozzle type of user automatically, and facial muscle changes,
What is stored in the state and data of tooth tongue carries out contrast confirmation, while sound and standard voice are contrasted, and works as discovery
When having notable difference, voice reports to user speech rule, and user can select to examine to read Show Me animation.
It is and described if image or video during the user pronunciation and the RP image or the comparing result of video
Voice during user pronunciation is different from the comparing result of the RP voice, then voice output module and image or video are defeated
Voice when going out module prompts user pronunciation is correct, and the image or video during pronunciation are incorrect, i.e., when nozzle type and standard not phase
Symbol, but when pronunciation and standard pronunciation approximation, system can prompt user to have a good pronunciation, and nozzle type is incorrect, and all are defined by practicality, user
It can select voluntarily to consult Demonstration of standardization video or listen to standard pronunciation demonstration.
To sum up, the various configuration of pronunciation correction system is described in detail above-described embodiment, and certainly, the present invention includes
But configuration cited in above-mentioned implementation is not limited to, is entered on the basis of any configuration provided in above-described embodiment in line translation
Hold, belong to the scope that the present invention is protected.Those skilled in the art can draw inferences about other cases from one instance according to the content of above-described embodiment.
As shown in Fig. 1~2, the present embodiment also provides a kind of pronunciation correction method, and a pronunciation correction system corrects user's
Pronunciation, the pronunciation correction method include：Signal sampling module 10, gather signal during user pronunciation；Standard signal library module
RP signal is stored with 20；Signal processing module 30 is by the signal during user pronunciation and the RP signal
Contrasted, if the difference between the signal and the RP signal during user pronunciation meets pre-provisioning request, to
User prompts pronunciation correct；If the difference between signal and the RP signal during user pronunciation is unsatisfactory for making a reservation for
It is required that then prompting the user with pronunciation mistake and according to the difference between the signal during user pronunciation and the RP signal
It is different to directly give correcting method.
Specifically, in described pronunciation correction method, image or video sampling module 11 gather figure during user pronunciation
As or video, speech sample module 12 gather user pronunciation when voice, the i.e. user pronunciation when signal include user hair
Voice during image or video and/or user pronunciation during sound, standard picture or video library module 21 are stored with RP figure
Picture or video, received pronunciation library module 22 are stored with RP voice, i.e., described RP signal includes RP figure
Picture or video and/or RP voice.
Further, in described pronunciation correction method, signal processing module 30 is by the signal during user pronunciation
Carrying out contrast with the RP signal includes：Image or video decomposing module 31 by the image during user pronunciation or regard
Frequency changes according to the lip motion of user, nozzle type, lip folding angle and/or tongue in the oral cavity or extrabuccal position is carried out
Decompose, form multiple user pronunciation section images or video；The RP image or video include multiple RP section figures
Picture or video；Image or video contrast module 32 are by multiple user pronunciation section images or video and multiple RP
Section image or video are contrasted, and draw difference lip motion, the change of difference nozzle type, difference lip folding angle and/or difference
Tongue position.
As shown in Fig. 2 in described pronunciation correction method, signal processing module 30 is by the signal during user pronunciation
Being contrasted with the RP signal also includes：Speech decomposition module 33 is by the voice during user pronunciation according to user
Tone, frequency, tone color, phoneme and/or phoneme decomposed, form multiple user pronunciation section voices；The RP language
Sound includes multiple RP section voices；Speech comparison module 34 is by multiple user pronunciation section voices and multiple standards
Voiced segments voice is contrasted, and draws difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme.
Specifically, in described pronunciation correction method, according to the signal during user pronunciation and the RP
Difference between signal includes：Whether voice output module 40 and image or Video Output Modules 50 prompt user speech correct,
And whether nozzle type is correct, user chooses whether to listen to RP voice and RP section voice, and user's selection is
It is no to check RP image or video and/or RP section image or video；Voice output module 40 according to difference tone,
Difference frequencies, difference tone color, difference phoneme and/or difference phoneme make prompting to user, and pronounce language to user's outputting standard
Sound and/or RP section voice；Image or Video Output Modules 50 are according to difference lip motion, the change of difference nozzle type, difference
Lip folding angle and/or difference tongue position make prompting to user, and to user's outputting standard pronounce image or video and/
Or RP section image or video.Specifically, voice output module 40 and image or Video Output Modules 50 can be exported and carried
Show that result includes, when the difference between signal and the RP signal when the user pronunciation meets pre-provisioning request,
Voice output module 40 issues the user with the voice of " correct ", or image or Video Output Modules show the picture of " correct "
Face；When the difference between signal and the RP signal when the user pronunciation is unsatisfactory for pre-provisioning request, voice is defeated
Go out the voice that module 40 issues the user with " mistake ", or image or Video Output Modules show the picture of " mistake ", enter one
Step, voice output module 40 and image or Video Output Modules 50 can also be shown to user pronunciation voice mistake (such as：
Phoneme not to) or pronunciation image or video error (such as：Nozzle type not to), further, the He of voice output module 40
Image or Video Output Modules 50 can also export correctly pronunciation voice and image or video, further to help user to carry out
Correct.
Finally, in described pronunciation correction method, if the image or video during the user pronunciation are sent out with the standard
The comparing result of sound image or video, with the comparing result of the voice during user pronunciation and the RP voice not
Together, then voice output module and voice when image or Video Output Modules prompting user pronunciation are correct, image during pronunciation or
Video is incorrect, or is defined by the comparing result of the voice during user pronunciation and the RP voice.
The pronunciation and standard pronunciation of contrast user in real time of the invention, it is immediately convenient, and user is corrected and prompted with voice
The pronunciation rule of pronunciation need to be accordingly corrected, and is placed with Show Me animation, it is very easy-to-understand for young English learner, due to
Mobile device is easy to carry, and 24 hours all-weathers carry out spoken pronunciation aided education and the correction of English at any time.
The present embodiment is illustrated to the pronunciation correction method：User has indivedual pronunciations not mark when using English
On time, mobile phone carries out automatic speech prompting.And contrasted the pronunciation of user and primary standard pronunciation, it can play and answer repeatedly
Read.It can also be carried out contrasting marking etc. according to the difference with pronunciation and standard pronunciation.
Such as：When user reads Plum【plΛm】, it is read as【plΛ】.Shooting as image or video acquisition module
Head catches the nozzle type change of user, and the angle for finding lip is finally to open, and is not closed.Pass through Speech comparison module simultaneously
34 contrast, voice when finding user pronunciation have lacked last compared with RP voice【m】Pronunciation.
Voice output module 40 prompts plum【plΛm】, while pin can intelligently be played according to judgement, signal processing module 30
The phonetic rules of case are prompted, such as " Ohdear, last or end syllable【m】Missing, lips are asked to close, tongue is laid flat, and chatter band, is allowed
Air-flow releases from nasal passage.Try again" X keys are pressed, it can be examined by image or Video Output Modules 50 and read RP figure
Pronunciation shape of the mouth as one speaks demonstration animation in picture or video.
User tries again, and camera catches the nozzle type for finding user when for the second time with reading, and is made that lip closure
Action, the contrast of Speech comparison module 34 find that voice during user pronunciation has【m】Sound is sent, but compared with RP voice still
Have gap, then intelligent playing standard pronunciation voice several times, and voice output module 40 provide incentive prompting " Goodtry,
onceagain”。
User again attempts to, until pronunciation standard, intelligence encourages " Welldone ".
If for user when attempting for second, the still not closed shape of the mouth as one speaks, then camera is after signal acquisition, voice output module
40 promptings provided are " Ohdear, last or end syllable【m】Missing, upper lower lip is please touched send【m】Sound, try again”
If user in pronunciation, has multiple garbled voices, such as will【plΛm】It is read as【plɑi】, voice message sound
Nozzle type is corrected since first wrong sound, prompts user to read【Λ】Rather than【ɑi】If first spelling has a good pronunciation
Afterwards, it is further continued for correcting the syllable subsequently lacked【m】.
To sum up be only one embodiment, voice and RP voice when spirit of the invention is to utilize user pronunciation
Also the mouth of many indexes such as nozzle type, facial muscle change, the position of tongue and standard pronunciation is judged while contrast with camera
Type demonstration is contrasted, and is provided and is targetedly prompted, for example face should magnify as far as possible, volume etc. on tongue.Rather than simple machine
Tool plays unified pronunciation rule.More preferable interaction effect can be increased, lift user experience.
When nozzle type is not consistent with standard, but when pronunciation and standard pronunciation approximation, system can prompt user to have a good pronunciation, nozzle type
Incorrect, all are defined by practicality, and user can select voluntarily to consult Demonstration of standardization video or listen to standard pronunciation demonstration.
In a word, in pronunciation correction system and method provided by the invention, by the signal processing module 30 by described in
Signal during user pronunciation is contrasted with the RP signal, if the signal during user pronunciation is sent out with the standard
Difference between sound signal meets pre-provisioning request, then it is correct to prompt the user with pronunciation；If signal and institute during the user pronunciation
State the difference between RP signal and be unsatisfactory for pre-provisioning request, then prompt the user with pronunciation mistake, it is possible to achieve run through one
Result feedback is carried out by signal processing module 30 at once after individual word, judges whether user pronunciation is correct, interactive height, in real time
The pronunciation and standard pronunciation of user is contrasted, it is immediately convenient.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be and other
The difference of embodiment, between each embodiment identical similar portion mutually referring to.For system disclosed in embodiment
For, due to corresponding to the method disclosed in Example, so description is fairly simple, related part is referring to method part illustration
.
Foregoing description is only the description to present pre-ferred embodiments, not to any restriction of the scope of the invention, this hair
Any change, the modification that the those of ordinary skill in bright field does according to the disclosure above content, belong to the protection of claims
Scope.
Claims (11)
1. a kind of pronunciation correction system, the pronunciation correction system is used for the pronunciation for correcting user, it is characterised in that the pronunciation
Correcting system includes：
One signal sampling module, signal during for gathering user pronunciation；And
One signal processing module, for the RP signal according to corresponding to the signal acquisition during user pronunciation, and by institute
Signal when stating user pronunciation is contrasted with the RP signal, if the signal during user pronunciation and the standard
Difference between pronunciation signal meets pre-provisioning request, then it is correct to prompt the user with pronunciation；If signal during the user pronunciation with
Difference between the RP signal is unsatisfactory for pre-provisioning request, then prompts the user with pronunciation mistake and sent out according to the user
The difference between signal and RP signal during sound directly gives correcting method.
2. pronunciation correction system as claimed in claim 1, it is characterised in that also include：
One standard signal library module, RP signal is stored with the standard signal library module.
3. pronunciation correction system as claimed in claim 2, it is characterised in that the signal during user pronunciation is sent out including user
Voice during image or video and/or user pronunciation during sound, the RP signal include RP image or video
And/or RP voice.
4. pronunciation correction system as claimed in claim 3, it is characterised in that the signal processing module includes an image or regarded
Frequency decomposing module and an image or video contrast module, wherein：
Described image or video decomposing module are by the lip motion of the image during user pronunciation or video according to user, nozzle type
Change, lip folding angle and/or tongue are in the oral cavity or extrabuccal position is decomposed, and form multiple user pronunciation section figures
Picture or video；
The RP image or video include multiple RP section images or video；
Described image or video contrast module are by multiple user pronunciation section images or video and multiple RP sections
Image or video are contrasted, and draw difference lip motion, the change of difference nozzle type, difference lip folding angle and/or difference tongue
Head position.
5. pronunciation correction system as claimed in claim 4, it is characterised in that the signal processing module also includes a voice point
Module and a Speech comparison module are solved, wherein：
The speech decomposition module by the voice during user pronunciation according to the tone of user, frequency, tone color, phoneme and/or
Phoneme is decomposed, and forms multiple user pronunciation section voices；
The RP voice includes multiple RP section voices；
The Speech comparison module is contrasted multiple user pronunciation section voices and multiple RP section voices,
Draw difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme.
6. pronunciation correction system as claimed in claim 5, it is characterised in that it is defeated that the pronunciation correction system also includes a voice
Go out module and an image or Video Output Modules, wherein：
The voice output module and described image or Video Output Modules prompting user speech it is whether correct, and nozzle type whether
Correctly, user chooses whether to listen to RP voice and RP section voice, and user chooses whether to check that standard is sent out
Sound image or video and/or RP section image or video；
The voice output module according to difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme to
Prompting is made at family, and pronounces voice and/or RP section voice to user's outputting standard；
Described image or Video Output Modules according to difference lip motion, the change of difference nozzle type, difference lip folding angle and/or
Difference tongue position makes prompting to user, and pronounces image or video and/or RP section image to user's outputting standard
Or video.
A kind of 7. pronunciation correction method, it is characterised in that the pronunciation correction method includes：
Gather signal during user pronunciation；And
The signal during user pronunciation and a RP signal are contrasted；If signal and institute during the user pronunciation
State the difference between RP signal and meet pre-provisioning request, then it is correct to prompt the user with pronunciation；If during the user pronunciation
Difference between signal and the RP signal is unsatisfactory for pre-provisioning request, then prompts the user with pronunciation mistake, and according to institute
The difference between signal and RP signal when stating user pronunciation directly gives correcting method.
8. pronunciation correction method as claimed in claim 7, it is characterised in that the signal during user pronunciation is sent out including user
Voice during image or video and/or user pronunciation during sound, the RP signal include RP image or video
And/or RP voice.
9. pronunciation correction method as claimed in claim 8, it is characterised in that signal processing module is by during the user pronunciation
Signal carries out contrast with the RP signal to be included：
Image or video decomposing module become the image during user pronunciation or video according to the lip motion of user, nozzle type
Change, lip folding angle and/or tongue are in the oral cavity or extrabuccal position is decomposed, and form multiple user pronunciation section images
Or video；
The RP image or video include multiple RP section images or video；
Image or video contrast module are by multiple user pronunciation section images or video and multiple RP section images
Or video is contrasted, difference lip motion, the change of difference nozzle type, difference lip folding angle and/or difference tongue position are drawn
Put.
10. pronunciation correction method as claimed in claim 9, it is characterised in that when signal processing module is by the user pronunciation
Signal contrasted with the RP signal and also included：
Speech decomposition module is by the voice during user pronunciation according to the tone of user, frequency, tone color, phoneme and/or phoneme
Decomposed, form multiple user pronunciation section voices；
The RP voice includes multiple RP section voices；
Speech comparison module is contrasted multiple user pronunciation section voices and multiple RP section voices, is drawn
Difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme.
11. pronunciation correction method as claimed in claim 10, it is characterised in that according to the signal during user pronunciation and institute
The difference stated between RP signal includes：
Whether voice output module and image or Video Output Modules prompting user speech are correct, and whether nozzle type is correct, uses
Family chooses whether to listen to RP voice and RP section voice, and user choose whether to check RP image or
Video and/or RP section image or video；
Voice output module is made according to difference tone, difference frequencies, difference tone color, difference phoneme and/or difference phoneme to user
Go out prompting, and pronounce voice and/or RP section voice to user's outputting standard；
Image or Video Output Modules are according to difference lip motion, the change of difference nozzle type, difference lip folding angle and/or difference
Tongue position makes prompting to user, and to user's outputting standard pronunciation image or video and/or RP section image or regards
Frequently.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710666754.4A CN107424450A (en) | 2017-08-07 | 2017-08-07 | Pronunciation correction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710666754.4A CN107424450A (en) | 2017-08-07 | 2017-08-07 | Pronunciation correction system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107424450A true CN107424450A (en) | 2017-12-01 |
Family
ID=60437446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710666754.4A Pending CN107424450A (en) | 2017-08-07 | 2017-08-07 | Pronunciation correction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107424450A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108206019A (en) * | 2017-12-29 | 2018-06-26 | 上海与德科技有限公司 | Assisted learning method, robot and the computer readable storage medium of infant |
| CN108470476A (en) * | 2018-05-15 | 2018-08-31 | 黄淮学院 | A kind of pronunciation of English matching correcting system |
| CN108492641A (en) * | 2018-03-26 | 2018-09-04 | 贵州西西沃教育科技股份有限公司 | A kind of English phonetic learning system |
| CN108520650A (en) * | 2018-03-27 | 2018-09-11 | 深圳市神经科学研究院 | An intelligent language training system and method |
| CN108648524A (en) * | 2018-05-02 | 2018-10-12 | 周志娟 | A kind of English word learning device and method |
| CN109064799A (en) * | 2018-08-31 | 2018-12-21 | 苏州竹原信息科技有限公司 | A kind of Language Training system and method based on virtual reality |
| CN109102824A (en) * | 2018-07-06 | 2018-12-28 | 北京比特智学科技有限公司 | Voice error correction method and device based on human-computer interaction |
| CN109598991A (en) * | 2019-01-11 | 2019-04-09 | 张翩 | A kind of pronunciation of English tutoring system, device and method |
| CN109671308A (en) * | 2018-09-18 | 2019-04-23 | 张滕滕 | A kind of generation method of pronunciation mouth shape correction system |
| CN109697976A (en) * | 2018-12-14 | 2019-04-30 | 北京葡萄智学科技有限公司 | A kind of pronunciation recognition methods and device |
| CN109741642A (en) * | 2018-07-11 | 2019-05-10 | 北京美高森教育科技有限公司 | Detection method of asking a question and answer it oneself, apparatus and system for sentence expansion |
| CN109920304A (en) * | 2019-04-19 | 2019-06-21 | 沈阳凯森教育科技有限公司 | A kind of pronounciation training system and pronounciation training method |
| CN109979433A (en) * | 2019-04-02 | 2019-07-05 | 北京儒博科技有限公司 | Voice is with reading processing method, device, equipment and storage medium |
| CN110047511A (en) * | 2019-04-23 | 2019-07-23 | 赵旭 | A kind of speech training method, device, computer equipment and its storage medium |
| CN110046354A (en) * | 2019-04-24 | 2019-07-23 | 广东小天才科技有限公司 | Reading guiding method, device, equipment and storage medium |
| CN110164414A (en) * | 2018-11-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Method of speech processing, device and smart machine |
| CN111047922A (en) * | 2019-12-27 | 2020-04-21 | 浙江工业大学之江学院 | Pronunciation teaching method, device, system, computer equipment and storage medium |
| CN111292769A (en) * | 2020-03-04 | 2020-06-16 | 苏州驰声信息科技有限公司 | Method, system, device and storage medium for correcting pronunciation of spoken language |
| CN111833859A (en) * | 2020-07-22 | 2020-10-27 | 科大讯飞股份有限公司 | Pronunciation error detection method and device, electronic equipment and storage medium |
| CN111951629A (en) * | 2019-05-16 | 2020-11-17 | 上海流利说信息技术有限公司 | Pronunciation correction system, method, medium and computing device |
| CN111951626A (en) * | 2019-05-16 | 2020-11-17 | 上海流利说信息技术有限公司 | Language learning apparatus, method, medium, and computing device |
| CN111968676A (en) * | 2020-08-18 | 2020-11-20 | 北京字节跳动网络技术有限公司 | Pronunciation correction method and device, electronic equipment and storage medium |
| CN112309390A (en) * | 2020-03-05 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information interaction method and device |
| CN112699275A (en) * | 2021-01-14 | 2021-04-23 | 江西师范大学 | English pronunciation calibrating device and system |
| CN112949554A (en) * | 2021-03-22 | 2021-06-11 | 湖南中凯智创科技有限公司 | Intelligent children accompanying education robot |
| CN113035235A (en) * | 2021-03-19 | 2021-06-25 | 北京有竹居网络技术有限公司 | Pronunciation evaluation method and apparatus, storage medium, and electronic device |
| CN113053186A (en) * | 2019-12-26 | 2021-06-29 | 京东数字科技控股有限公司 | Interaction method, interaction device and storage medium |
| CN113051985A (en) * | 2019-12-26 | 2021-06-29 | 深圳云天励飞技术有限公司 | Information prompting method and device, electronic equipment and storage medium |
| CN113066487A (en) * | 2019-12-16 | 2021-07-02 | 广东小天才科技有限公司 | Accent correction learning method, system, device and storage medium |
| CN113077819A (en) * | 2021-03-19 | 2021-07-06 | 北京有竹居网络技术有限公司 | Pronunciation evaluation method and device, storage medium and electronic equipment |
| CN113257231A (en) * | 2021-07-07 | 2021-08-13 | 广州思正电子股份有限公司 | Language sound correcting system method and device |
| CN113297924A (en) * | 2021-04-30 | 2021-08-24 | 北京有竹居网络技术有限公司 | Method, device, storage medium and electronic equipment for correcting pronunciation |
| CN114730530A (en) * | 2019-09-30 | 2022-07-08 | 知识方正有限公司 | language teaching machine |
| CN114842690A (en) * | 2022-04-26 | 2022-08-02 | 深圳市企鹅网络科技有限公司 | Pronunciation interaction method and system for language course, electronic equipment and storage medium |
| CN115273898A (en) * | 2022-08-16 | 2022-11-01 | 安徽淘云科技股份有限公司 | Pronunciation training method and device, electronic equipment and storage medium |
| CN116206496A (en) * | 2023-01-30 | 2023-06-02 | 齐齐哈尔大学 | An analysis and comparison system for oral English practice based on artificial intelligence |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1787035A (en) * | 2005-11-04 | 2006-06-14 | 黄中伟 | Method for computer assisting learning of deaf-dumb Chinese language pronunciation |
| US20070061139A1 (en) * | 2005-09-14 | 2007-03-15 | Delta Electronics, Inc. | Interactive speech correcting method |
| CN102663928A (en) * | 2012-03-07 | 2012-09-12 | 天津大学 | Electronic teaching method for deaf people to learn speaking |
| CN105070118A (en) * | 2015-07-30 | 2015-11-18 | 广东小天才科技有限公司 | Pronunciation correcting method and device for language learning |
| CN105261246A (en) * | 2015-12-02 | 2016-01-20 | 武汉慧人信息科技有限公司 | Spoken English error correcting system based on big data mining technology |
| CN105390049A (en) * | 2014-08-25 | 2016-03-09 | 卡西欧计算机株式会社 | Electronic apparatus, pronunciation learning support method |
| CN105551327A (en) * | 2016-03-07 | 2016-05-04 | 浙江理工大学 | Interactive pronunciation correcting system and method based on soft electronic skin |
| CN106357715A (en) * | 2015-07-17 | 2017-01-25 | 深圳新创客电子科技有限公司 | Method, toy, mobile terminal and system for correcting pronunciation |
| CN106571075A (en) * | 2016-10-18 | 2017-04-19 | 广东工业大学 | Multi-mode language rehabilitation and learning system |
| CN106971743A (en) * | 2016-01-14 | 2017-07-21 | 广州酷狗计算机科技有限公司 | User's singing data treating method and apparatus |
-
2017
- 2017-08-07 CN CN201710666754.4A patent/CN107424450A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070061139A1 (en) * | 2005-09-14 | 2007-03-15 | Delta Electronics, Inc. | Interactive speech correcting method |
| CN1787035A (en) * | 2005-11-04 | 2006-06-14 | 黄中伟 | Method for computer assisting learning of deaf-dumb Chinese language pronunciation |
| CN102663928A (en) * | 2012-03-07 | 2012-09-12 | 天津大学 | Electronic teaching method for deaf people to learn speaking |
| CN105390049A (en) * | 2014-08-25 | 2016-03-09 | 卡西欧计算机株式会社 | Electronic apparatus, pronunciation learning support method |
| CN106357715A (en) * | 2015-07-17 | 2017-01-25 | 深圳新创客电子科技有限公司 | Method, toy, mobile terminal and system for correcting pronunciation |
| CN105070118A (en) * | 2015-07-30 | 2015-11-18 | 广东小天才科技有限公司 | Pronunciation correcting method and device for language learning |
| CN105261246A (en) * | 2015-12-02 | 2016-01-20 | 武汉慧人信息科技有限公司 | Spoken English error correcting system based on big data mining technology |
| CN106971743A (en) * | 2016-01-14 | 2017-07-21 | 广州酷狗计算机科技有限公司 | User's singing data treating method and apparatus |
| CN105551327A (en) * | 2016-03-07 | 2016-05-04 | 浙江理工大学 | Interactive pronunciation correcting system and method based on soft electronic skin |
| CN106571075A (en) * | 2016-10-18 | 2017-04-19 | 广东工业大学 | Multi-mode language rehabilitation and learning system |
Cited By (49)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108206019A (en) * | 2017-12-29 | 2018-06-26 | 上海与德科技有限公司 | Assisted learning method, robot and the computer readable storage medium of infant |
| CN108492641A (en) * | 2018-03-26 | 2018-09-04 | 贵州西西沃教育科技股份有限公司 | A kind of English phonetic learning system |
| CN108520650A (en) * | 2018-03-27 | 2018-09-11 | 深圳市神经科学研究院 | An intelligent language training system and method |
| CN108648524A (en) * | 2018-05-02 | 2018-10-12 | 周志娟 | A kind of English word learning device and method |
| CN108470476B (en) * | 2018-05-15 | 2020-06-30 | 黄淮学院 | An English pronunciation matching correction system |
| CN108470476A (en) * | 2018-05-15 | 2018-08-31 | 黄淮学院 | A kind of pronunciation of English matching correcting system |
| CN109102824A (en) * | 2018-07-06 | 2018-12-28 | 北京比特智学科技有限公司 | Voice error correction method and device based on human-computer interaction |
| CN109741642A (en) * | 2018-07-11 | 2019-05-10 | 北京美高森教育科技有限公司 | Detection method of asking a question and answer it oneself, apparatus and system for sentence expansion |
| CN109064799A (en) * | 2018-08-31 | 2018-12-21 | 苏州竹原信息科技有限公司 | A kind of Language Training system and method based on virtual reality |
| CN109671308A (en) * | 2018-09-18 | 2019-04-23 | 张滕滕 | A kind of generation method of pronunciation mouth shape correction system |
| CN109671308B (en) * | 2018-09-18 | 2022-04-22 | 张滕滕 | Generation method of pronunciation mouth shape correction system |
| CN110164414B (en) * | 2018-11-30 | 2023-02-14 | 腾讯科技（深圳）有限公司 | Voice processing method and device and intelligent equipment |
| CN110164414A (en) * | 2018-11-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Method of speech processing, device and smart machine |
| CN109697976A (en) * | 2018-12-14 | 2019-04-30 | 北京葡萄智学科技有限公司 | A kind of pronunciation recognition methods and device |
| CN109697976B (en) * | 2018-12-14 | 2021-05-25 | 北京葡萄智学科技有限公司 | Pronunciation recognition method and device |
| CN109598991A (en) * | 2019-01-11 | 2019-04-09 | 张翩 | A kind of pronunciation of English tutoring system, device and method |
| CN109979433A (en) * | 2019-04-02 | 2019-07-05 | 北京儒博科技有限公司 | Voice is with reading processing method, device, equipment and storage medium |
| CN109920304A (en) * | 2019-04-19 | 2019-06-21 | 沈阳凯森教育科技有限公司 | A kind of pronounciation training system and pronounciation training method |
| CN110047511A (en) * | 2019-04-23 | 2019-07-23 | 赵旭 | A kind of speech training method, device, computer equipment and its storage medium |
| CN110046354A (en) * | 2019-04-24 | 2019-07-23 | 广东小天才科技有限公司 | Reading guiding method, device, equipment and storage medium |
| CN111951626A (en) * | 2019-05-16 | 2020-11-17 | 上海流利说信息技术有限公司 | Language learning apparatus, method, medium, and computing device |
| CN111951629A (en) * | 2019-05-16 | 2020-11-17 | 上海流利说信息技术有限公司 | Pronunciation correction system, method, medium and computing device |
| CN114730530A (en) * | 2019-09-30 | 2022-07-08 | 知识方正有限公司 | language teaching machine |
| CN113066487A (en) * | 2019-12-16 | 2021-07-02 | 广东小天才科技有限公司 | Accent correction learning method, system, device and storage medium |
| CN113051985A (en) * | 2019-12-26 | 2021-06-29 | 深圳云天励飞技术有限公司 | Information prompting method and device, electronic equipment and storage medium |
| CN113051985B (en) * | 2019-12-26 | 2024-07-05 | 深圳云天励飞技术有限公司 | Information prompting method, device, electronic equipment and storage medium |
| CN113053186A (en) * | 2019-12-26 | 2021-06-29 | 京东数字科技控股有限公司 | Interaction method, interaction device and storage medium |
| CN111047922A (en) * | 2019-12-27 | 2020-04-21 | 浙江工业大学之江学院 | Pronunciation teaching method, device, system, computer equipment and storage medium |
| CN111292769A (en) * | 2020-03-04 | 2020-06-16 | 苏州驰声信息科技有限公司 | Method, system, device and storage medium for correcting pronunciation of spoken language |
| CN112309390A (en) * | 2020-03-05 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information interaction method and device |
| CN111833859B (en) * | 2020-07-22 | 2024-02-13 | 科大讯飞股份有限公司 | Pronunciation error detection method and device, electronic equipment and storage medium |
| CN111833859A (en) * | 2020-07-22 | 2020-10-27 | 科大讯飞股份有限公司 | Pronunciation error detection method and device, electronic equipment and storage medium |
| CN111968676A (en) * | 2020-08-18 | 2020-11-20 | 北京字节跳动网络技术有限公司 | Pronunciation correction method and device, electronic equipment and storage medium |
| CN112699275B (en) * | 2021-01-14 | 2025-10-03 | 江西师范大学 | English pronunciation calibration device and system |
| CN112699275A (en) * | 2021-01-14 | 2021-04-23 | 江西师范大学 | English pronunciation calibrating device and system |
| WO2022194044A1 (en) * | 2021-03-19 | 2022-09-22 | 北京有竹居网络技术有限公司 | Pronunciation assessment method and apparatus, storage medium, and electronic device |
| CN113077819A (en) * | 2021-03-19 | 2021-07-06 | 北京有竹居网络技术有限公司 | Pronunciation evaluation method and device, storage medium and electronic equipment |
| CN113077819B (en) * | 2021-03-19 | 2024-11-22 | 北京有竹居网络技术有限公司 | Pronunciation evaluation method and device, storage medium and electronic device |
| CN113035235A (en) * | 2021-03-19 | 2021-06-25 | 北京有竹居网络技术有限公司 | Pronunciation evaluation method and apparatus, storage medium, and electronic device |
| CN112949554A (en) * | 2021-03-22 | 2021-06-11 | 湖南中凯智创科技有限公司 | Intelligent children accompanying education robot |
| CN112949554B (en) * | 2021-03-22 | 2022-02-08 | 湖南中凯智创科技有限公司 | Intelligent children accompanying education robot |
| CN113297924A (en) * | 2021-04-30 | 2021-08-24 | 北京有竹居网络技术有限公司 | Method, device, storage medium and electronic equipment for correcting pronunciation |
| CN113257231A (en) * | 2021-07-07 | 2021-08-13 | 广州思正电子股份有限公司 | Language sound correcting system method and device |
| CN113257231B (en) * | 2021-07-07 | 2021-11-26 | 广州思正电子股份有限公司 | Language sound correcting system method and device |
| CN114842690B (en) * | 2022-04-26 | 2024-03-01 | 深圳市企鹅网络科技有限公司 | Pronunciation interaction method, system, electronic equipment and storage medium for language courses |
| CN114842690A (en) * | 2022-04-26 | 2022-08-02 | 深圳市企鹅网络科技有限公司 | Pronunciation interaction method and system for language course, electronic equipment and storage medium |
| CN115273898A (en) * | 2022-08-16 | 2022-11-01 | 安徽淘云科技股份有限公司 | Pronunciation training method and device, electronic equipment and storage medium |
| CN116206496B (en) * | 2023-01-30 | 2023-08-18 | 齐齐哈尔大学 | An analysis and comparison system for oral English practice based on artificial intelligence |
| CN116206496A (en) * | 2023-01-30 | 2023-06-02 | 齐齐哈尔大学 | An analysis and comparison system for oral English practice based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107424450A (en) | Pronunciation correction system and method | |
| Sidnell et al. | The handbook of conversation analysis | |
| CN107909995B (en) | Voice interaction method and device | |
| CN113077819B (en) | Pronunciation evaluation method and device, storage medium and electronic device | |
| Griol et al. | Developing multimodal conversational agents for an enhanced e-learning experience | |
| US20220015687A1 (en) | Method for Screening Psychiatric Disorder Based On Conversation and Apparatus Therefor | |
| Wells et al. | Children's intonation: a framework for practice and research | |
| KR20140078810A (en) | Apparatus and method for learning rhythm patterns using language data and pronunciation data of native speakers | |
| KR20070103095A (en) | How to Learn English Using Frequency Bandwidth | |
| Ilhan et al. | HAPOVER: A Haptic Pronunciation Improver Device | |
| KR101681673B1 (en) | English trainning method and system based on sound classification in internet | |
| KR20140107067A (en) | Apparatus and method for learning word by using native speakerpronunciation data and image data | |
| JP6155102B2 (en) | Learning support device | |
| KR20110065276A (en) | Method and apparatus for pronunciation exercise using comparison video | |
| KR20140087953A (en) | Apparatus and method for language education by using native speaker's pronunciation data and thoughtunit | |
| KR20140082127A (en) | Apparatus and method for learning word by using native speaker's pronunciation data and origin of a word | |
| Lacerda | On the emergence of early linguistic functions: A biological and interactional perspective | |
| KR20140073768A (en) | Apparatus and method for language education using meaning unit and pronunciation data of native speakers | |
| CN112863268B (en) | A human-machine dialogue device for spoken English | |
| KR102019613B1 (en) | Method for learning and practicing pronunciation based on tongue movement | |
| Hanson | Computing technologies for deaf and hard of hearing users | |
| KR20140078082A (en) | Apparatus and method for Language Pattern Education by using sentence data. | |
| TWI683290B (en) | Spoken language teaching auxiliary method and device | |
| Chi | HOW TO IMPROVE YOUR ENGLISH PRONUNCIATION | |
| KR20140087957A (en) | Apparatus and method for Language Pattern Education by using sentence data. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| 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: 20171201 |