CN108735220A - A kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction method - Google Patents
A kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction method Download PDFInfo
- Publication number
- CN108735220A CN108735220A CN201810319502.9A CN201810319502A CN108735220A CN 108735220 A CN108735220 A CN 108735220A CN 201810319502 A CN201810319502 A CN 201810319502A CN 108735220 A CN108735220 A CN 108735220A
- Authority
- CN
- China
- Prior art keywords
- voice
- document
- text
- module
- error
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000003993 interaction Effects 0.000 title claims abstract description 23
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 12
- 238000012937 correction Methods 0.000 claims abstract description 62
- 238000005516 engineering process Methods 0.000 claims abstract description 25
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 21
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 21
- 238000006243 chemical reaction Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 13
- 238000013473 artificial intelligence Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000013519 translation Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 230000036651 mood Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 206010048865 Hypoacusis Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72433—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for voice messaging, e.g. dictaphones
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention provides a kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction methods.In the present invention, the former voice document of learner is obtained first, and carrying out text file conversion to the original voice document using speech recognition technology obtains original text this document；Wrong point list is obtained to original text this document error correction later；Then feedback error point list, and according to wrong point list, each erroneous point in original text this document is replaced with into correct machine language text to be formed and corrects version text file；Version voice document is corrected followed by phonetic synthesis correction version text file acquisition and plays to learner.By error correction, feedback and replacement, when learner hears that the content that earphone plays is the sound of oneself, illustrate this part spoken language inerrancy, when hearing machine language, illustrates wrong herein, need to be corrected with reference to correct machine language, add to practice as needed.
Description
Technical field
The present invention relates to technical field of intelligent interaction more particularly to a kind of language learning intelligent earphone, intelligent interaction systems
System and man-machine interaction method.
Background technology
Wireless Bluetooth headsets are developed to from wired earphone, from function earphone is listened to music merely to can be with the intelligence of human-computer interaction
Earphone, the type and function of earphone are more and more abundant.
In addition, as what is exchanged between various countries increases, people are also more and more for the demand of foreign language language.Existing language
Learn in product, can only realize the function of listening and read, such as some language learning cell phone applications, it can not be to learner
It practises situation and provides specific feedback, this causes learner that can not look into scarce mending-leakage, in place of specific aim is covered the shortage.
Invention content
The goal of the invention of the present invention is to provide a kind of language learning intelligent earphone, intelligent interactive system and human-computer interaction side
Method can designate that the mistake place in learner's spoken language and feed back to learner, for learner's repetition learning to reinforce practicing.
To achieve the above object, the present invention provides a kind of language learning intelligent earphone, including：Recording module, voice are known
Other module, correction module, feedback module, text processing module, voice synthetic module and playing module；
Wherein, the recording module is used for the study phonetic acquisition original voice document of typing learner；
The sound identification module is used to carry out text file conversion to the former voice document using speech recognition technology,
Obtain original text this document；
The correction module is used to obtain wrong point list to original text this document error correction using artificial intelligence technology；
The feedback module is for feeding back the wrong point list；
The wrong point list of the text processing module based on feedback, by each erroneous point in described original text this document
Correct machine language text is replaced with, is formed and corrects version text file；
The voice synthetic module is used to carry out voice document to the correction version text file using speech synthesis technique
Conversion obtains and corrects version voice document；
The playing module plays the correction version voice document by earphone.
Optionally, the correction module uses artificial intelligence technology to original text this document error correction.
Optionally, the wrong point list of the text processing module based on feedback, also forms revised text file；Institute
State the type of error text file and corresponding correct machine language text file that revised text file is each erroneous point；It is described
Voice synthetic module also carries out voice document conversion using speech synthesis technique to the revised text file, obtains each erroneous point
Type of error voice document and corresponding machine talk file；The playing module also plays the type of error by earphone
Voice document and machine talk file.
Optionally, the revised text file is interspersed in the correction version text file by the text processing module,
Or it is put in before or after the correction version text file.
Optionally, further include voice storage module, version voice is corrected for storing.
Optionally, further include voice storage module, type of error voice for storing each erroneous point and corresponding correct
Machine language voice.
Optionally, the intelligent earphone is translation earphone, the sound identification module, voice synthetic module and broadcasting mould
Block is served as by sound identification module, voice synthetic module and the playing module of the translation earphone.
The present invention also provides a kind of language learning intelligent interactive systems, including：
Above-mentioned intelligent earphone and mobile terminal；
Wherein, the mobile terminal and the intelligent earphone interactive communication, the APP on the mobile terminal, which is synchronized, obtains institute
State former voice document and the correction version voice document.
The present invention further provides a kind of man-machine interaction methods of intelligent earphone, including：
The study phonetic acquisition original voice document of typing learner；
Text file conversion is carried out to the former voice document using speech recognition technology, obtains original text this document；
To original text this document error correction, wrong point list is obtained；
It feeds back the wrong point list and each erroneous point in described original text this document is replaced with into correct machine language
Text forms and corrects version text file；
Voice document conversion is carried out to the correction version text file using speech synthesis technique, obtains and corrects version voice text
Part；
The correction version voice document is played by earphone.
Optionally, using artificial intelligence technology to original text this document error correction.
Optionally, the wrong point list is fed back, revised text file is also formed；The revised text file is each mistake
The type of error text file and corresponding correct machine language text file of point；It is also repaiied to described using speech synthesis technique
It orders text file and carries out voice document conversion, obtain the type of error voice document and corresponding machine talk text of each erroneous point
Part；The type of error voice document and machine talk file are played by earphone.
Optionally, when broadcasting, the type of error voice document and machine talk file are interspersed in the correction version voice
It is interior, or be put in before or after the correction version voice.
Optionally, the correction version voice is also stored, to call study repeatedly.
Optionally, the type of error voice document and machine talk file are also stored, to call study repeatedly.
Optionally, the different type of error text files of each erroneous point are distinguished using different code.
Optionally, the type of error of each erroneous point includes：Word or byte pronunciation mistake, tone or stress mistake,
With pause or not familiar mistake.
Optionally, further include the APP being synchronized to former voice document with the correction version voice document on mobile phone.
Optionally, further include by former voice document, the type of error language for correcting version voice document and each erroneous point
APP on sound file and corresponding machine talk file synchronization to mobile phone.
Compared with prior art, the beneficial effects of the present invention are：
1) in the present invention, the former voice document of learner is obtained first, using speech recognition technology to the original voice document
It carries out text file conversion and obtains original text this document；Wrong point list is obtained to original text this document error correction later；Then it feeds back
Mistake point list, and according to wrong point list, each erroneous point in original text this document is replaced with into correct machine language text
Version text file is corrected to be formed；Version voice document is corrected followed by phonetic synthesis correction version text file acquisition and is played to
Learner.As can be seen that by error correction, feedback and replacement, when learner hears that the content that earphone plays is the sound of oneself
When, illustrate this part spoken language inerrancy, when hearing machine language, illustrate it is wrong herein, need to be with reference to correct machine language
It corrects, adds to practice as needed.
2) in alternative, in error correction step, a) the representative normative text number in the data packet that can be prestored with earphone
According to being compared, big data error correction of the artificial intelligence technology by internet can also b) be used.
3) in alternative, version voice document is corrected in addition to playing, can also be stored in earphone, be adjusted repeatedly for learner
It takes hard of hearing.
Still optionally further, the correction version voice document can be stored, can also store and correct version text file, benefit exists
In：Reduce the memory space occupied, or in the case where memory space is certain, stores several sections more.
Still optionally further, memory block can be opened in earphone, can also be opened in the shifting that LAN can be formed with the earphone
In dynamic terminal.
4) in alternative, learner can not only hear complete correction version voice, can also hear the mistake of each erroneous point
The voice of type and corresponding correct machine language.Above-mentioned purpose by feedback error point list simultaneously, also formed revision text
This document；Revised text file is the type of error text file of each erroneous point and corresponding correct machine language text text
Part.Later revised text file with correct version text file respectively respectively or together, played after phonetic synthesis.About each mistake
The type of error and corresponding correct machine language voice of point can be interspersed in and correct in version voice, or be put in when playing
Before or after the correction version voice.
Still optionally further, in addition to playing, it is also sent to the APP of mobile terminal, APP is opened whenever and wherever possible for learner
It practises.Above-mentioned transmission opportunity can be：A) learner is actively in the APP of mobile terminal when synchronous study result；Or b) learner
When opening the APP of mobile terminal, earphone is actively sent；Or c) mobile terminal is once in earphone under same LAN, earphone
Actively send.
5) in alternative, the type of error of each erroneous point includes：Word or byte pronunciation mistake, tone or stress are wrong
Mistake and pause or not familiar mistake.Each type of error is refined, the emphasis that learner can be prompted to correct targetedly corrects mistake.
Description of the drawings
Fig. 1 is the module map of the language learning intelligent earphone in one embodiment of the invention；
Fig. 2 is the flow chart of the man-machine interaction method of the intelligent earphone in Fig. 1：
Fig. 3 is the flow chart of the man-machine interaction method of the intelligent earphone in another embodiment of the present invention.
Specific implementation mode
To make the above purposes, features and advantages of the invention more obvious and understandable, below in conjunction with the accompanying drawings to the present invention
Specific embodiment be described in detail.
Fig. 1 is the module map of the language learning intelligent earphone in one embodiment of the invention.
Shown in referring to Fig.1, which includes：Recording module 11, sound identification module 12, error correction
Module 13, feedback module 14, text processing module 15, voice synthetic module 16 and playing module 17.
The function of each module is introduced individually below.
Recording module 11 is used for the study phonetic acquisition original voice document of typing learner.
The study voice of learner can be one or a few words, one or several phrases, even one or several words.It learns
The content of the study voice of habit person can be based at that time, local, mood is extemporaneously played instantly, can also be with reference on intelligent terminal
The learning Content presented in APP application programs.
The former voice document of typing can be stored in voice storage module.
Sound identification module 12 is used to carry out text file conversion to former voice document using speech recognition technology, obtains former
Text file.
Speech recognition technology can be existing speech recognition technology, such as using at present using more depth nerve net
Network (Deep Neural Network, DNN), recurrent neural network (Recurrent Neural Network, RNN).It is converted into
First text file occupies memory space small, is second conducive to subsequently compare error correction in big data.
Correction module 13 is used to, to original text this document error correction, obtain wrong point list.
Error correction can be there are two types of approach.First, the study voice for being directed to learner is originated from and is answered with reference to the APP on intelligent terminal
The case where with the learning Content presented in program, can be compared with the representative normative text data in pre stored data.
Second, for the study voice of learner content be based at that time, it is local, mood is extemporaneously played instantly the case where, using artificial
Intellectual technology error correction.The use of artificial intelligence technology error correction refer to capturing to compare in big data on the internet.Earphone can lead to
It crosses bluetooth to connect with mobile terminal, big data is obtained using mobile terminal as hot spot.Earphone can also with mobile terminal and
Router forms LAN, and big data is obtained using the communication of router.
Mistake point list includes the correspondence of the position and wrong content of each mistake.
Feedback module 14 is for feeding back the mistake point list.
Feedback module 14 forms a kind of feedback mechanism so that learner has practiced spoken language not only through saying, and knows mistake
Accidentally place, targetedly to repeat.
Wrong point list of the text processing module 15 based on feedback, each erroneous point in original text this document is replaced with correctly
Machine language text, formed correct version text file.
About correct machine language text when replacing, acquisition modes can have：A) correction module 13 not only obtains
The position of erroneous point and erroneous point content can also compare according to data packet or big data and obtain correct machine language text；It should
Correct machine language text can be together listed in position, wrong content in wrong point list；Or b) text processing module 15
The machine language for calling earphone to prestore.
Voice synthetic module 16 is used to carry out voice document conversion to correcting version text file using speech synthesis technique, obtains
Version voice document must be corrected.Speech synthesis technique is referred to existing speech synthesis technique, such as uses WaveNet softwares.
Playing module 17 plays the correction version voice document by earphone.
Version voice document is corrected in addition to playing, can also be stored in voice storage module, be called repeatedly for learner.
Learner can be turned over the former voice document of calling up and down by the button on earphone 1 and/or correct version voice document, also
It can be called by the APP of intelligent terminal.
When learner hears that the content that earphone 1 plays is oneself sound, illustrate this part spoken language inerrancy, when hearing
When machine language, illustrate wrong herein, need to be corrected with reference to correct machine language, can also add to practice as needed.
Intelligent earphone 1 in the present embodiment can be translation earphone.In other words, which is based on existing translation
Earphone carries out functions expanding, in this way：Sound identification module 12, voice synthetic module 16 and playing module 17 can be by translation ears
Sound identification module, voice synthetic module and the playing module of machine serve as.
One embodiment of the invention also provides a kind of language learning intelligent interactive system, including：
Above-mentioned intelligent earphone 1 and mobile terminal；
Wherein, mobile terminal and 1 interactive communication of intelligent earphone, the APP on mobile terminal synchronize obtain former voice document with
Correct version voice document.
Intelligent earphone 1 can pass through bluetooth and mobile terminal interactive communication.Intelligent earphone 1 can also with mobile terminal and
Router forms LAN, the interactive communication in LAN.
Fig. 2 is the flow chart of the man-machine interaction method of the intelligent earphone in Fig. 1.
Each step is introduced individually below.
With reference to shown in Fig. 2, step S1, the study phonetic acquisition original voice document of typing learner is first carried out.
The study voice of learner can be one or a few words, one or several phrases, even one or several words.It learns
The content of the study voice of habit person can be based at that time, local, mood is extemporaneously played instantly, can also be with reference on intelligent terminal
The learning Content presented in APP application programs.
The former voice document of typing can be stored in voice storage module.
Then step S2 is executed, text file conversion is carried out to the original voice document using speech recognition technology, is obtained former
Text file.
Speech recognition technology can be existing speech recognition technology.
Being converted into text file, first to occupy memory space small, is second conducive to subsequently compare error correction in big data.
Followed by step S3 is executed, to original text this document error correction, wrong point list is obtained.
Error correction can be there are two types of method.First, the study voice for being directed to learner is originated from and is answered with reference to the APP on intelligent terminal
The case where with the learning Content presented in program, can be compared with the representative normative text data in pre stored data.
Second, for the study voice of learner content be based at that time, it is local, mood is extemporaneously played instantly the case where, using artificial
Intellectual technology error correction.The use of artificial intelligence technology error correction refer to capturing to compare in big data on the internet.Earphone can lead to
It crosses bluetooth to connect with mobile terminal, big data is obtained using mobile terminal as hot spot.Earphone can also with mobile terminal and
Router forms LAN, and big data is obtained using the communication of router.
Mistake point list includes the correspondence of the position and wrong content of each mistake.
Step S4 is executed later, and feedback error point list simultaneously replaces with each erroneous point in the original text this document correctly
Machine language text forms and corrects version text file.
This feedback step forms a kind of feedback mechanism so that learner has practiced spoken language not only through saying, and knows mistake
Accidentally place, targetedly to repeat.
About correct machine language text when replacing, acquisition modes can have：A) error correction step S3 is not only obtained
The position of erroneous point and erroneous point content can also compare according to data packet or big data and obtain correct machine language text；It should
Correct machine language text can be together listed in position, wrong content in wrong point list；Or b) earphone is called to prestore
Machine language.
Step S5 is executed, voice document conversion is carried out to correcting version text file using speech synthesis technique, is corrected
Version voice document.
Speech synthesis technique is referred to existing speech synthesis technique.
Then step S6 is executed, which is played by earphone.
Play-back technology is referred to existing play-back technology.
Intelligent earphone in the present embodiment can be translation earphone.In other words, which is based on existing translation ear
Machine carries out functions expanding, in this way：Speech recognition steps S2, phonetic synthesis step S5 and broadcasting step S6 can be by translation earphones
Sound identification module, voice synthetic module and playing module complete.
Another embodiment of the present invention also provides a kind of Foreigh-language oral-speech practice intelligent earphone.Compared with previous embodiment, this
Intelligent earphone in embodiment difference lies in：1) wrong point list of the text processing module 15 based on feedback also forms revision text
This document；The revised text file is the type of error text file of each erroneous point and corresponding correct machine language text text
Part；2) voice synthetic module 16 also carries out voice document conversion using speech synthesis technique to the revised text file, obtains
The type of error voice document of each erroneous point and corresponding machine talk file；3) playing module 17 passes through earphone also playback error
Type voice file and machine talk file.
Revised text file can be interspersed in and correct in version text file by text processing module 15 as needed, or put
Before or after correcting version text file.
The type of error of each erroneous point may include：Word or byte pronunciation mistake, tone or stress mistake and pause or
Not familiar mistake.In text file, different type mistake can be distinguished by different code, can also be distinguished by different storage addresses.
Word or byte pronunciation mistake, tone or stress mistake can be placed on not familiar mistake before or after correction version text file.For
Pause mistake can be interspersed in and correct in version text file, so that follow-up earphone plays " should not have pause herein " to prompt to use
Family.The certain value of full section, such as 80% or more can be accounted for mistake of statistics for the criterion of not familiar mistake, plays " this section life
Dredge " to prompt learner.
Fig. 3 is the flow chart of the man-machine interaction method of the intelligent earphone in another embodiment of the present invention.It, can be with reference to Fig. 3
Find out, it is roughly the same with the flow in Fig. 2, difference lies in：
1) in step S4 ', feedback error point list also forms revised text file；Revised text file is each erroneous point
Type of error text file and corresponding correct machine language text file；
2) in step S5 ', voice document conversion also is carried out to revised text file using speech synthesis technique, obtains each mistake
Overdue type of error voice document and corresponding machine talk file；
3) in step S6 ', pass through earphone also playback error type voice file and machine talk file.
In revised text file, the type of error of each erroneous point may include：Word or byte pronunciation mistake, tone or again
Sound mistake and pause or not familiar mistake.In text file, different type mistake can be distinguished by different code, can also be by not
It is distinguished with storage address.Word or byte pronunciation mistake, can be placed on not familiar mistake and correct version text tone or stress mistake
Before or after file.For pause mistake, it can be interspersed in and correct in version text file, so that the broadcasting of follow-up earphone " is not answered herein
Have pause " to prompt user.Can account for the certain value of full section with mistake of statistics for the criterion of not familiar mistake, for example, 80% with
On, " this section is not familiar " is played to prompt learner.
The type of error voice document of each erroneous point and corresponding machine talk file are played, it can also be by each erroneous point
Type of error voice document and corresponding machine talk file preserve, so that learner calls.Learner can be by earphone
Button up and down turn over the type of error voice document for calling each erroneous point and corresponding machine talk file, intelligence can also be passed through
The APP of terminal is called.
Intelligent earphone in the present embodiment can also be translation earphone.New phonetic synthesis step S5 ' and broadcasting step
S6 ' can be completed by the voice synthetic module and playing module of translation earphone.
Although present disclosure is as above, present invention is not limited to this.Any those skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (18)
1. a kind of language learning intelligent earphone, which is characterized in that including：Recording module, sound identification module, correction module,
Feedback module, text processing module, voice synthetic module and playing module；
Wherein, the recording module is used for the study phonetic acquisition original voice document of typing learner；
The sound identification module is used to carry out text file conversion to the former voice document using speech recognition technology, obtains
Original text this document；
The correction module is used to, to original text this document error correction, obtain wrong point list；
The feedback module is for feeding back the wrong point list；
The wrong point list of the text processing module based on feedback, each erroneous point in described original text this document is replaced
For correct machine language text, is formed and correct version text file；
The voice synthetic module is used to carry out voice document conversion to the correction version text file using speech synthesis technique,
It obtains and corrects version voice document；
The playing module plays the correction version voice document by earphone.
2. language learning intelligent earphone according to claim 1, which is characterized in that the correction module uses artificial intelligence
Energy technology is to original text this document error correction.
3. language learning intelligent earphone according to claim 1, which is characterized in that the text processing module is based on anti-
The wrong point list of feedback, also forms revised text file；The revised text file is the type of error text of each erroneous point
This document and corresponding correct machine language text file；The voice synthetic module is using speech synthesis technique also to described
Revised text file carries out voice document conversion, obtains the type of error voice document and corresponding machine talk text of each erroneous point
Part；The playing module also plays the type of error voice document and machine talk file by earphone.
4. language learning intelligent earphone according to claim 3, which is characterized in that the text processing module will be described
Revised text file is interspersed in the correction version text file, or is put in before or after the correction version text file.
5. language learning intelligent earphone according to claim 1, which is characterized in that further include voice storage module, use
Version voice is corrected in storage.
6. language learning intelligent earphone according to claim 3, which is characterized in that further include voice storage module, use
In the type of error voice and corresponding correct machine language voice that store each erroneous point.
7. language learning intelligent earphone according to any one of claims 1 to 6, which is characterized in that the intelligent earphone
To translate earphone, the sound identification module, voice synthetic module and playing module are by the speech recognition for translating earphone
Module, voice synthetic module and playing module serve as.
8. a kind of language learning intelligent interactive system, which is characterized in that including：
Intelligent earphone described in any one of claim 1 to 7 and mobile terminal；
Wherein, the mobile terminal and the intelligent earphone interactive communication, the APP on the mobile terminal, which is synchronized, obtains the original
Voice document and the correction version voice document.
9. a kind of man-machine interaction method of intelligent earphone, which is characterized in that including：
The study phonetic acquisition original voice document of typing learner；
Text file conversion is carried out to the former voice document using speech recognition technology, obtains original text this document；
To original text this document error correction, wrong point list is obtained；
It feeds back the wrong point list and each erroneous point in described original text this document is replaced with into correct machine language text,
It is formed and corrects version text file；
Voice document conversion is carried out to the correction version text file using speech synthesis technique, obtains and corrects version voice document；
The correction version voice document is played by earphone.
10. man-machine interaction method according to claim 9, which is characterized in that using artificial intelligence technology to the original text
This document error correction.
11. man-machine interaction method according to claim 9, which is characterized in that the feedback wrong point list is also formed and repaiied
Order text file；The revised text file is the type of error text file of each erroneous point and corresponding correct machine language
Text file；Voice document conversion also is carried out to the revised text file using speech synthesis technique, obtains each erroneous point
Type of error voice document and corresponding machine talk file；The type of error voice document and machine language are played by earphone
Sound file.
12. man-machine interaction method according to claim 11, which is characterized in that when broadcasting, the type of error voice text
Part and machine talk file are interspersed in the correction version voice, or are put in before or after the correction version voice.
13. man-machine interaction method according to claim 9, which is characterized in that the correction version voice is also stored, with
Study is called repeatedly.
14. man-machine interaction method according to claim 11, which is characterized in that the type of error voice document and machine
Voice document is also stored, to call study repeatedly.
15. man-machine interaction method according to claim 11, which is characterized in that the different type of error texts of each erroneous point
File is distinguished using different code.
16. the man-machine interaction method according to claim 11 or 15, which is characterized in that the type of error of each erroneous point
Including：Word or byte pronunciation mistake, tone or stress mistake and pause or not familiar mistake.
17. man-machine interaction method according to claim 9, which is characterized in that further include entangling former voice document with described
Legal voice document is synchronized to the APP on mobile phone.
18. man-machine interaction method according to claim 11, which is characterized in that further include by former voice document, described entangle
On the type of error voice document and corresponding machine talk file synchronization to mobile phone of legal voice document and each erroneous point
APP。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810319502.9A CN108735220A (en) | 2018-04-11 | 2018-04-11 | A kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810319502.9A CN108735220A (en) | 2018-04-11 | 2018-04-11 | A kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108735220A true CN108735220A (en) | 2018-11-02 |
Family
ID=63940747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810319502.9A Pending CN108735220A (en) | 2018-04-11 | 2018-04-11 | A kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108735220A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109462790A (en) * | 2018-11-14 | 2019-03-12 | 王美金 | A kind of artificial intelligence wears mill ear financial payment translation earphone cloud system and method |
| CN114974221A (en) * | 2022-04-29 | 2022-08-30 | 中移互联网有限公司 | Speech recognition model training method and device and computer readable storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739870A (en) * | 2009-12-03 | 2010-06-16 | 深圳先进技术研究院 | Interactive language learning system and method |
| CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
| CN203761458U (en) * | 2014-02-24 | 2014-08-06 | 汉诚信息技术（上海）有限公司 | Interactive type automatic voice response system |
| CN104123858A (en) * | 2014-07-30 | 2014-10-29 | 广东小天才科技有限公司 | Method and device for error detection and correction during back-reading lesson text |
| CN105025178A (en) * | 2014-04-18 | 2015-11-04 | 北京艾沃信通讯技术有限公司 | Method and system for converting interactive voice response into interactive text response |
| CN105304080A (en) * | 2015-09-22 | 2016-02-03 | 科大讯飞股份有限公司 | Speech synthesis device and speech synthesis method |
| CN106528616A (en) * | 2016-09-30 | 2017-03-22 | 厦门快商通科技股份有限公司 | Language error correcting method and system for use in human-computer interaction process |
| CN106847288A (en) * | 2017-02-17 | 2017-06-13 | 上海创米科技有限公司 | The error correction method and device of speech recognition text |
| CN107133222A (en) * | 2017-04-17 | 2017-09-05 | 中译语通科技（北京）有限公司 | A kind of real-time language conversion equipment and conversion method based on heterogeneous framework |
| CN107293284A (en) * | 2017-07-27 | 2017-10-24 | 上海传英信息技术有限公司 | A kind of phoneme synthesizing method and speech synthesis system based on intelligent terminal |
| CN107622054A (en) * | 2017-09-26 | 2018-01-23 | 科大讯飞股份有限公司 | The error correction method and device of text data |
| CN107644637A (en) * | 2017-03-13 | 2018-01-30 | 平安科技（深圳）有限公司 | Phoneme synthesizing method and device |
| CN107798931A (en) * | 2017-12-05 | 2018-03-13 | 上海电机学院 | A kind of intelligent children education learning system and method |
-
2018
- 2018-04-11 CN CN201810319502.9A patent/CN108735220A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739870A (en) * | 2009-12-03 | 2010-06-16 | 深圳先进技术研究院 | Interactive language learning system and method |
| CN103000052A (en) * | 2011-09-16 | 2013-03-27 | 上海先先信息科技有限公司 | Man-machine interactive spoken dialogue system and realizing method thereof |
| CN203761458U (en) * | 2014-02-24 | 2014-08-06 | 汉诚信息技术（上海）有限公司 | Interactive type automatic voice response system |
| CN105025178A (en) * | 2014-04-18 | 2015-11-04 | 北京艾沃信通讯技术有限公司 | Method and system for converting interactive voice response into interactive text response |
| CN104123858A (en) * | 2014-07-30 | 2014-10-29 | 广东小天才科技有限公司 | Method and device for error detection and correction during back-reading lesson text |
| CN105304080A (en) * | 2015-09-22 | 2016-02-03 | 科大讯飞股份有限公司 | Speech synthesis device and speech synthesis method |
| CN106528616A (en) * | 2016-09-30 | 2017-03-22 | 厦门快商通科技股份有限公司 | Language error correcting method and system for use in human-computer interaction process |
| CN106847288A (en) * | 2017-02-17 | 2017-06-13 | 上海创米科技有限公司 | The error correction method and device of speech recognition text |
| CN107644637A (en) * | 2017-03-13 | 2018-01-30 | 平安科技（深圳）有限公司 | Phoneme synthesizing method and device |
| CN107133222A (en) * | 2017-04-17 | 2017-09-05 | 中译语通科技（北京）有限公司 | A kind of real-time language conversion equipment and conversion method based on heterogeneous framework |
| CN107293284A (en) * | 2017-07-27 | 2017-10-24 | 上海传英信息技术有限公司 | A kind of phoneme synthesizing method and speech synthesis system based on intelligent terminal |
| CN107622054A (en) * | 2017-09-26 | 2018-01-23 | 科大讯飞股份有限公司 | The error correction method and device of text data |
| CN107798931A (en) * | 2017-12-05 | 2018-03-13 | 上海电机学院 | A kind of intelligent children education learning system and method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109462790A (en) * | 2018-11-14 | 2019-03-12 | 王美金 | A kind of artificial intelligence wears mill ear financial payment translation earphone cloud system and method |
| CN114974221A (en) * | 2022-04-29 | 2022-08-30 | 中移互联网有限公司 | Speech recognition model training method and device and computer readable storage medium |
| CN114974221B (en) * | 2022-04-29 | 2024-01-19 | 中移互联网有限公司 | Speech recognition model training method and device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11627221B2 (en) | Semiautomated relay method and apparatus | |
| US10255918B2 (en) | Command and control of devices and applications by voice using a communication base system | |
| CN105869626B (en) | A kind of method and terminal of word speed automatic adjustment | |
| US9547642B2 (en) | Voice to text to voice processing | |
| US10217466B2 (en) | Voice data compensation with machine learning | |
| US9924012B2 (en) | Apparatus for answering a phone call when a recipient of the phone call decides that it is inappropriate to talk, and related method | |
| US20110270601A1 (en) | Universal translator | |
| US20190130176A1 (en) | Performing artificial intelligence sign language translation services in a video relay service environment | |
| US11528568B1 (en) | Assisted hearing aid with synthetic substitution | |
| KR102044689B1 (en) | System and method for creating broadcast subtitle | |
| CN108093653B (en) | Voice prompt method, recording medium and voice prompt system | |
| KR101819459B1 (en) | Voice recognition system and apparatus supporting voice recognition error correction | |
| CN110166729A (en) | Cloud video-meeting method, device, system, medium and calculating equipment | |
| US20150287332A1 (en) | Distance Education Method and Server Device for Providing Distance Education | |
| CN106981289A (en) | A kind of identification model training method and system and intelligent terminal | |
| CN108735220A (en) | A kind of language learning intelligent earphone, intelligent interactive system and man-machine interaction method | |
| Liao et al. | Formosa speech recognition challenge 2020 and Taiwanese across Taiwan corpus | |
| CN107766333A (en) | A kind of intelligent translation apparatus, system and method | |
| CN103646645A (en) | Method based on voice translation text output | |
| CN110915239A (en) | On-line automatic audio transcription for hearing aid users | |
| US20200075000A1 (en) | System and method for broadcasting from a group of speakers to a group of listeners | |
| CN102104657A (en) | Alarm clock reminding method, device and mobile terminal | |
| CN114154636A (en) | Data processing method, electronic device and computer program product | |
| CN115171645A (en) | Dubbing method and device, electronic equipment and storage medium | |
| JP2019159099A (en) | Music reproduction system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181102 |
|
| WD01 | Invention patent application deemed withdrawn after publication |