CN109817215A - Speech recognition, assessment and the correcting system of English words and phrases - Google Patents
Speech recognition, assessment and the correcting system of English words and phrases Download PDFInfo
- Publication number
- CN109817215A CN109817215A CN201910199118.4A CN201910199118A CN109817215A CN 109817215 A CN109817215 A CN 109817215A CN 201910199118 A CN201910199118 A CN 201910199118A CN 109817215 A CN109817215 A CN 109817215A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- module
- voice
- speech recognition
- assessment
- 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
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses the speech recognitions of English words and phrases, assessment and correcting system, belong to English Phonetics technical field, including intelligent robot and intelligent spoken language system, intelligent spoken language system is connect by intelligent chip with intelligent robot, intelligent spoken language system includes speech recognition system, voice evaluation system and voice correcting system, speech recognition system includes recoding unit and recognition unit, intelligent identification module is equipped in recognition unit, voice evaluation system includes comparison unit and assessment unit, intelligent comparison module is equipped in comparison unit, voice correcting system is equipped with intelligence and corrects module, intelligence degree is high, it can better the problems in analytics hair tonic sound, the accuracy to correct one's pronunciation, student is preferably helped to issue the pronunciation of standard.
Description
Technical field
The present invention relates to English Phonetics technical field, more specifically to English words and phrases speech recognition, test and assess and entangle
Positive system.
Background technique
English is the language under Indo-European family of languages-Germanic branc, is formed by 26 monograms, English alphabet springs from drawing
T-shaped is female, and the Latin alphabet springs from Greek alphabet, and Greek alphabet is evolved by Phoenicia letter, and English is international
Specified official language, and widest first language in the world, English include about 490,000 words, additional technical term about 300,000
It is a, it is the official language of the most language of vocabulary and European Union and many international organizations and British commonwealth of nations, possesses the world
Mother tongue user's number of third position is only second to Chinese and Spanish mother tongue user's number.
The study majority of Oral English Practice is learnt by corresponding English study software or hardware at present, to correct
Whether the pronunciation of itself is correct, but more software is mostly using simple recording and comparison pronunciation, functional poor, entangles simultaneously
Whether positive is ineffective, and hardware has language repeater or point to read software etc., be to lean on the comparison pronunciation of student resource accurate, student is certainly
Main comparison is it is possible that error, poor so as to cause the effect of correction.
Summary of the invention
1. technical problems to be solved
Aiming at the problems existing in the prior art, the purpose of the present invention is to provide the speech recognitions of English words and phrases, assessment
And correcting system, its intelligence degree are high, can better the problems in analytics hair tonic sound, the accuracy to correct one's pronunciation, more
The good pronunciation for helping student to issue standard.
2. technical solution
To solve the above problems, the present invention adopts the following technical scheme that:
Speech recognition, assessment and the correcting system of English words and phrases, including intelligent robot and intelligent spoken language system, the intelligence
Energy spoken language system is connect by intelligent chip with intelligent robot, and the intelligence spoken language system includes speech recognition system, voice
Evaluation system and voice correcting system, the speech recognition system include recoding unit and recognition unit, in the recognition unit
Equipped with intelligent identification module, the voice evaluation system includes comparison unit and assessment unit, is equipped with intelligence in the comparison unit
Energy contrast module, the voice correcting system are equipped with intelligence and correct module, and intelligence degree is high, can better analytics hair tonic
The problems in sound, the accuracy to correct one's pronunciation preferably help student to issue the pronunciation of standard.
Further, the speech recognition system, voice evaluation system and voice correcting system are sane level relationship, and voice
Identifying system, voice evaluation system and voice correcting system complement each other, and the speech recognition system acts on voice assessment system
System, the voice evaluation system act on voice correcting system, and the voice correcting system acts on recoding unit, speech recognition
System passes data to voice evaluation system, by the assessment of voice evaluation system, passes information to voice correcting system,
To which voice correcting system is corrected, then recoding unit is fed back information to, after the identification of the speech recognition system of process
It continues cycling through.
Further, equipped with the basic term of English in daily life, the interior packet of local data base in the local data base
The basic term of English in a large amount of daily life is contained, such as " Good morning ", " Thank you " English are used substantially
Language, the data in local data base are recorded as original text.
Further, the intelligent spoken language system signal is connected with cloud database, and intelligent spoken language system passes through wireless network
Network transmission is connect with cloud database, and so as to realize the real-time update of local data base, and then it is Sino-British to supplement daily life
The basic term amount of language.
Further, the recoding unit includes intelligent removing module, recording acquisition module, recording storage module, recording
Listener modules and original text record playing module will be right after intelligent removing module receives recording after learner corrects
The inappropriate recording stored before carries out intelligent deletion, to save memory, recording acquisition module can acquire the record of learner
Sound can save the recording after acquisition module of recording collects the recording of learner, can by recording listener modules
To listen to oneself recording, original text record playing module can record to original text and play out.
Further, the assessment unit includes that intelligent testing is discussed and select model workers block, grade classification module and intellectual broadcast module, intelligence
Assessment module can to after the comparison of intelligent comparison module situation test and assess, and then be notified to by intellectual broadcast module, while right
The division of its evaluating result progress grade.
Further, the grade classification module includes first-class, the second grade and third gradegrade C three grades, first-class as outstanding, second
Deng be it is qualified, the third gradegrade C is as unqualified.
3. beneficial effect
Compared with the prior art, the present invention has the advantages that
Intelligence degree of the present invention is high, can better the problems in analytics hair tonic sound, the accuracy to correct one's pronunciation, more
The good pronunciation for helping student to issue standard.
Detailed description of the invention
Fig. 1 is functional block diagram of the invention；
Fig. 2 is the functional block diagram at recoding unit；
Fig. 3 is the functional block diagram at assessment unit.
Figure label explanation:
1 intelligent robot, 2 intelligent spoken language systems, 3 speech recognition systems, 31 recoding units, 311 intelligent removing modules,
312 recording acquisition modules, 313 recording storage modules, 314 recording listener modules, 315 original text record playing modules, 32 identifications are single
Member, 321 intelligent identification modules, 4 voice evaluation systems, 41 comparison units, 411 intelligent comparison modules, 42 assessment units, 421 intelligence
Module, 422 grade classification modules, 423 intellectual broadcast modules, 5 voice correcting systems, 51 intelligence of capable of testing and assessing correct module, 6 locally
Database, 7 cloud databases.
Specific embodiment
Technical solution in the embodiment of the present invention that following will be combined with the drawings in the embodiments of the present invention carries out clear, complete
Ground description.Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments, based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the instruction such as term " on ", "lower", "inner", "outside" " top/bottom end "
Orientation or positional relationship be based on the orientation or positional relationship shown in the drawings, be merely for convenience of description the present invention and simplification retouch
It states, rather than the device or element of indication or suggestion meaning must have a particular orientation, be constructed and operated in a specific orientation,
Therefore it is not considered as limiting the invention.In addition, term " first ", " second " are used for description purposes only, and cannot understand
For indication or suggestion relative importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation " " is set
Be equipped with ", " be arranged/connect ", " connection " etc., shall be understood in a broad sense, such as " connection ", may be a fixed connection, be also possible to removable
Connection is unloaded, or is integrally connected；It can be mechanical connection, be also possible to be electrically connected；It can be directly connected, it can also be in
Between medium be indirectly connected, can be the connection inside two elements.It for the ordinary skill in the art, can be specific
Situation understands the concrete meaning of above-mentioned term in the present invention.
Embodiment:
Referring to Fig. 1, the speech recognition of English words and phrases, assessment and correcting system, including intelligent robot 1 and intelligence spoken language
System 2, intelligent spoken language system 2 are connect with intelligent robot 1 by intelligent chip, by the effect of intelligent robot 1, make to learn
Person and intelligent robot 1 carry out human-computer dialogue training, are equipped with local data base 6 in intelligent spoken language system 2, in local data base 6
Equipped with the basic term of English in daily life, the English contained in a large amount of daily life in local data base 6 is used substantially
Language, such as " Good morning ", the basic term of " Thank you " English, the data in local data base 6 are recorded as original text
Sound, intelligent 2 signal of spoken language system are connected with cloud database 7, and intelligent spoken language system 2 passes through wireless network transmissions and cloud data
Library 7 connects, and so as to realize the real-time update of local data base 6, and then supplements the basic term amount of daily life English；
Please continue to refer to Fig. 1, intelligent spoken language system 2 includes that speech recognition system 3, voice evaluation system 4 and voice are corrected
System 5, speech recognition system 3 carry out the intelligent recognition of voice, and voice evaluation system 4 realizes the intelligence assessment of voice, and voice entangles
Positive system 5 realizes that the intelligence of voice is corrected, and speech recognition system 3, voice evaluation system 4 and voice correcting system 5 are sane level pass
System, and speech recognition system 3, voice evaluation system 4 and voice correcting system 5 complement each other, speech recognition system 3 acts on language
Sound evaluation system 4, voice evaluation system 4 act on voice correcting system 5, and voice correcting system 5 acts on recoding unit 31, language
Sound identifying system 3 passes data to voice evaluation system 4, by the assessment of voice evaluation system 4, passes information to voice
Correcting system 5, so that voice correcting system 5 is corrected, then feeds back information to recoding unit 31, the speech recognition system of process
It is continued cycling through after the identification of system 3；
Fig. 1 and Fig. 2 are please referred to, speech recognition system 3 includes recoding unit 31 and recognition unit 32, and recoding unit 31 includes
Intelligent removing module 311, recording acquisition module 312, recording storage module 313, recording listener modules 314 and original text recording broadcasting
Module 315 will be inappropriate to what is stored before after intelligent removing module 311 receives recording after learner corrects
Recording carry out intelligent deletion, to save memory, recording acquisition module 312 can acquire the recording of learner, when recording acquires
After module 312 collects the recording of learner, which can be saved, by recording, listener modules 314 can be listened to
The recording of oneself, original text record playing module 315 can record to original text and play out, and intelligent recognition mould is equipped in recognition unit 32
Block 321 can carry out intelligent recognition to recording, to judge the correctness of pronunciation by the effect of intelligent identification module 321；
Fig. 1 and Fig. 3 are please referred to, voice evaluation system 4 includes comparison unit 41 and assessment unit 42, is set in comparison unit 41
There is an intelligent comparison module 411, assessment unit 42 includes that intelligent testing is discussed and select model workers block 421, grade classification module 422 and intellectual broadcast module
423, grade classification module 422 includes first-class, the second grade and third gradegrade C three grades, and first-class as outstanding, the second grade is qualification, and the third gradegrade C is
To be unqualified, intelligent testing discuss and select model workers block 421 can to after the comparison of intelligent comparison module 411 situation test and assess, and then pass through intelligence
Broadcasting module 423 is notified to, while the division of grade is carried out to its evaluating result, and voice correcting system 5 is equipped with intelligence and corrects module
51, intelligence degree is high, can preferably the problems in analytics hair tonic sound, the accuracy to correct one's pronunciation, better help learn
Hair tonic goes out the pronunciation of standard.
Working principle: as learner in use, learner plays local data base 6 by original text record playing module 315
Interior original text recording, this system acquires the recording of learner itself by recording acquisition module 312, then passes through recording storage module
313 are stored, and learner can listen to the recording of itself by listener modules 314 of recording, and collect the recording of learner itself
Later, intelligent identification module 321 can effectively judge the correctness of pronunciation, so that the data that itself is recorded pass to voice assessment
Itself recording and original text recording are compared by intelligent comparison module 411, are discussed and select model workers the intelligence of block 421 through intelligent testing by system 4
Assessment, then the effect through grade classification module 422 can be divided first-class, the second grade and the third gradegrade C, while can pass through intellectual broadcast mould
Block 423 is broadcasted, and learner is allowed to quickly understand the study situation of itself, when grade is divided into the second grade and the third gradegrade C, intelligence
Intelligent correction can be carried out to incorrect place by correcting module 51, after learner is repaired, be recorded again, when intelligent deletion
After module 311 receives the recording after learner corrects, intelligent deletion will be carried out to the inappropriate recording stored before,
It to save memory, and then is corrected next time, by repeatedly comparing repeatedly with reading preferably student to be helped to issue standard
Pronunciation.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
It improves design and is subject to equivalent substitution or change, should be covered by the scope of protection of the present invention.
Claims (7)
1. the speech recognition of English words and phrases, assessment and correcting system, including intelligent robot (1) and intelligent spoken language system (2),
Be characterized in that: the intelligence spoken language system (2) is connect by intelligent chip with intelligent robot (1), the intelligence spoken language system
(2) local data base (6) are equipped in, the intelligence spoken language system (2) includes speech recognition system (3), voice evaluation system (4)
With voice correcting system (5), the speech recognition system (3) includes recoding unit (31) and recognition unit (32), the identification
Intelligent identification module (321) are equipped in unit (32), the voice evaluation system (4) includes comparison unit (41) and assessment unit
(42), intelligent comparison module (411) are equipped in the comparison unit (41), the voice correcting system (5) is equipped with intelligence and corrects
Module (51).
2. speech recognition, assessment and the correcting system of English words and phrases according to claim 1, it is characterised in that: institute's predicate
Sound identifying system (3), voice evaluation system (4) and voice correcting system (5) are sane level relationship, and speech recognition system (3), language
Sound evaluation system (4) and voice correcting system (5) complement each other, and the speech recognition system (3) acts on voice evaluation system
(4), the voice evaluation system (4) acts on voice correcting system (5), and it is single that the voice correcting system (5) acts on recording
First (31).
3. speech recognition, assessment and the correcting system of English words and phrases according to claim 1, it is characterised in that: described
Equipped with the basic term of English in daily life in ground database (6).
4. speech recognition, assessment and the correcting system of English words and phrases according to claim 1, it is characterised in that: the intelligence
Energy spoken language system (2) signal is connected with cloud database (7).
5. speech recognition, assessment and the correcting system of English words and phrases according to claim 1, it is characterised in that: the record
Sound unit (31) includes intelligent removing module (311), recording acquisition module (312), recording storage module (313), records and listen to
Module (314) and original text record playing module (315).
6. speech recognition, assessment and the correcting system of English words and phrases according to claim 1, it is characterised in that: the survey
Commenting unit (42) includes that intelligent testing is discussed and select model workers block (421), grade classification module (422) and intellectual broadcast module (423).
7. speech recognition, assessment and the correcting system of English words and phrases according to claim 4, it is characterised in that: described etc.
Grade division module (422) includes first-class, the second grade and third gradegrade C three grades.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199118.4A CN109817215A (en) | 2019-03-15 | 2019-03-15 | Speech recognition, assessment and the correcting system of English words and phrases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199118.4A CN109817215A (en) | 2019-03-15 | 2019-03-15 | Speech recognition, assessment and the correcting system of English words and phrases |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109817215A true CN109817215A (en) | 2019-05-28 |
Family
ID=66609200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910199118.4A Pending CN109817215A (en) | 2019-03-15 | 2019-03-15 | Speech recognition, assessment and the correcting system of English words and phrases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109817215A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211607A (en) * | 2019-07-04 | 2019-09-06 | 山东中医药高等专科学校 | A kind of English learning system based on sensing network |
| CN110263334A (en) * | 2019-06-06 | 2019-09-20 | 深圳市柯达科电子科技有限公司 | A kind of method and readable storage medium storing program for executing assisting foreign language learning |
| CN110444087A (en) * | 2019-07-26 | 2019-11-12 | 深圳市讯呼信息技术有限公司 | A kind of intelligent language teaching machine device people |
| CN110827588A (en) * | 2019-11-08 | 2020-02-21 | 东莞职业技术学院 | Device is corrected to sight dialogue spoken language, grammar of english study usefulness |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004246184A (en) * | 2003-02-14 | 2004-09-02 | Eigyotatsu Kofun Yugenkoshi | Language learning system and method with visualized pronunciation suggestion |
| CN204904612U (en) * | 2015-07-29 | 2015-12-23 | 嘉兴市莱沃机器人科技有限公司 | Human -like teaching machine people |
| CN205151944U (en) * | 2015-08-19 | 2016-04-13 | 广州市宝源节能环保科技有限公司 | Full -automatic medical effluent disposal system |
| CN106448288A (en) * | 2016-11-01 | 2017-02-22 | 安阳师范学院 | Interactive English learning system and method |
| CN106686248A (en) * | 2017-01-17 | 2017-05-17 | 维沃移动通信有限公司 | Illumination control method and mobile terminal |
| CN108597279A (en) * | 2018-04-13 | 2018-09-28 | 广东蓝盾乐庚技术信息有限公司 | A kind of integrated form safety of student emergency education system |
-
2019
- 2019-03-15 CN CN201910199118.4A patent/CN109817215A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004246184A (en) * | 2003-02-14 | 2004-09-02 | Eigyotatsu Kofun Yugenkoshi | Language learning system and method with visualized pronunciation suggestion |
| CN204904612U (en) * | 2015-07-29 | 2015-12-23 | 嘉兴市莱沃机器人科技有限公司 | Human -like teaching machine people |
| CN205151944U (en) * | 2015-08-19 | 2016-04-13 | 广州市宝源节能环保科技有限公司 | Full -automatic medical effluent disposal system |
| CN106448288A (en) * | 2016-11-01 | 2017-02-22 | 安阳师范学院 | Interactive English learning system and method |
| CN106686248A (en) * | 2017-01-17 | 2017-05-17 | 维沃移动通信有限公司 | Illumination control method and mobile terminal |
| CN108597279A (en) * | 2018-04-13 | 2018-09-28 | 广东蓝盾乐庚技术信息有限公司 | A kind of integrated form safety of student emergency education system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263334A (en) * | 2019-06-06 | 2019-09-20 | 深圳市柯达科电子科技有限公司 | A kind of method and readable storage medium storing program for executing assisting foreign language learning |
| CN110211607A (en) * | 2019-07-04 | 2019-09-06 | 山东中医药高等专科学校 | A kind of English learning system based on sensing network |
| CN110444087A (en) * | 2019-07-26 | 2019-11-12 | 深圳市讯呼信息技术有限公司 | A kind of intelligent language teaching machine device people |
| CN110827588A (en) * | 2019-11-08 | 2020-02-21 | 东莞职业技术学院 | Device is corrected to sight dialogue spoken language, grammar of english study usefulness |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109817215A (en) | Speech recognition, assessment and the correcting system of English words and phrases | |
| US11151892B2 (en) | Internet teaching platform-based following teaching system | |
| WO2019095446A1 (en) | Following teaching system having speech evaluation function | |
| US6988063B2 (en) | System and method for accurate grammar analysis using a part-of-speech tagged (POST) parser and learners' model | |
| KR100699663B1 (en) | Automated language assessment using speech recognition modeling | |
| US7013262B2 (en) | System and method for accurate grammar analysis using a learners' model and part-of-speech tagged (POST) parser | |
| US8271281B2 (en) | Method for assessing pronunciation abilities | |
| CN111526382A (en) | Live video text generation method, device, equipment and storage medium | |
| Peabody | Methods for pronunciation assessment in computer aided language learning | |
| CN110085210A (en) | Interactive information test method, device, computer equipment and storage medium | |
| CN109559580B (en) | Online learning system | |
| CN111951629A (en) | Pronunciation correction system, method, medium and computing device | |
| US8870575B2 (en) | Language learning system, language learning method, and computer program product thereof | |
| CN110796185A (en) | Method and device for detecting image annotation result | |
| CN111710348A (en) | Pronunciation evaluation method and terminal based on audio fingerprints | |
| CN109065024A (en) | abnormal voice data detection method and device | |
| CN110472054A (en) | A kind of data processing method and device | |
| CN113035236B (en) | Quality inspection method and device for voice synthesis data | |
| CN109949813A (en) | A kind of method, apparatus and system converting speech into text | |
| RU135830U1 (en) | TRAINING DEVICE FOR EXERCISING SKILLS IN LEARNING LANGUAGES | |
| CN110288977B (en) | Data processing method and device and electronic equipment | |
| CN111078746B (en) | Dictation content determining method and electronic equipment | |
| LU505091B1 (en) | English unit memory system based on forgetting curve and method thereof | |
| CN110751867A (en) | English teaching system | |
| CN111538808A (en) | Education training system for reciting lessons and working method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |