CN101105894B - Multifunctional language learning machine - Google Patents
Multifunctional language learning machine Download PDFInfo
- Publication number
- CN101105894B CN101105894B CN2006100616771A CN200610061677A CN101105894B CN 101105894 B CN101105894 B CN 101105894B CN 2006100616771 A CN2006100616771 A CN 2006100616771A CN 200610061677 A CN200610061677 A CN 200610061677A CN 101105894 B CN101105894 B CN 101105894B
- Authority
- CN
- China
- Prior art keywords
- language
- unit
- voice
- information
- data
- 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.)
- Expired - Fee Related
Links
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000013519 translation Methods 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
Images
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to a multifunctional language learning machine, which includes: a voice receiving unit for receiving a first user voice information; a central processing unit for carrying out function control and data treatment; a storage unit for storing data; and a voice output unit and a display unit. The language learning machine further includes: A voice identification unit for identifying the first user voice information received by the voice receiving unit, a first language information that the central processing unit searches the similarity above the preset threshold value from the translation vocabulary stored in the storage unit according to the first user voice information identified by the voice identification unit, and a second language information corresponding with the first language information and displayed on the display unit according to the translation vocabulary. Through the structure, the learning machine can identify the source language entered by parents and transmit the source language into the target language for the reference of parents or learning of children.
Description
[technical field]
The present invention relates to a kind of multifunctional language learning machine, relate in particular to a kind of multifunctional language learning machine with speech recognition and interpretative function.
[background technology]
Along with science and technology and constant development of economy, foreign language has played more and more important effect in daily life and work.In order to improve child's L proficiency, the head of a family can buy various language learners usually and assist child's foreign language studying.But,, can't check child's learning outcome because a lot of head of a familys' L proficiency is limited.
[summary of the invention]
The technical matters of the function that child's learning outcome is checked is not provided for the limited head of a family of L proficiency for the language learner that solves prior art.The present invention proposes and a kind ofly can make the head of a family can check the multifunctional language learning machine of child's learning outcome by speech recognition and intertranslation mode.
The language learner that the present invention solves prior art for the limited head of a family of L proficiency provides the technical scheme that technical matters adopted of the function that child's learning outcome is checked is not: a kind of multifunctional language learning machine is provided, and this language learner comprises: the voice receiving unit that is used to receive the first user speech information; Be used to carry out the CPU (central processing unit) of function control and data processing; Be used to store the storage unit of data; Voice-output unit and display unit, language learner further comprises: the voice recognition unit that the first user speech information that voice receiving unit received is discerned, retrieve the first language information of similarity in the translation dictionary that the first user speech information that CPU (central processing unit) is discerned according to voice recognition unit is stored from storage unit, and on display unit, show the second language information corresponding with first language information according to the translation dictionary greater than predetermined threshold.
According to one preferred embodiment of the present invention, CPU (central processing unit) is selected at least two similarities according to the first user speech information and is shown greater than the first language information of predetermined threshold and at display unit from the translation dictionary, and according to user's confirmation needed first language information translation is become second language information.
According to one preferred embodiment of the present invention, storage unit is storage and the corresponding second language data of second language information further, language learner further comprises the speech conversion unit, and the speech conversion unit will become second language with the corresponding second language data-switching of second language information and export by voice-output unit.
According to one preferred embodiment of the present invention, the voice comparing unit that second user speech information that language learner further will receive through voice receiving unit and second language data compare, and CPU (central processing unit) shows corresponding scoring according to similarity on display unit.
According to one preferred embodiment of the present invention, store a plurality of alternate translation dictionaries in the storer.
According to one preferred embodiment of the present invention, language learner further comprises the data transmit-receive unit that carries out communication by wired or wireless mode.
According to one preferred embodiment of the present invention, voice recognition unit is the voice recognition unit at unspecified person.
The beneficial effect of technique scheme is: the mother tongue input of word or sentence can will investigate by to(for) the limited head of a family of L proficiency, then by language learner carry out speech recognition and by the translation dictionary translate into be presented at after other language messages on the display for the head of a family with reference to or child practise spelling.The mother tongue that language learner of the present invention is also further imported the head of a family is play to supply child to practise hearing or spoken language after converting other language to.In addition, the voice messaging and the standard language information of input can also be compared and marks by language learner of the present invention.
[description of drawings]
Fig. 1 is the schematic block diagram of language learner one embodiment of the present invention;
Fig. 2 is the workflow diagram of language learner shown in Figure 1.
[embodiment]
The present invention is further described below in conjunction with drawings and Examples.
Referring to Fig. 1 and Fig. 2, Fig. 1 is the schematic block diagram of language learner one embodiment of the present invention, and Fig. 2 is the workflow diagram of language learner shown in Figure 1.In the present embodiment, multifunctional language learning machine 1 of the present invention comprises: the voice receiving unit 11 that is used to the first user speech information that receives; Be used to carry out the CPU (central processing unit) 12 of function control and data processing; Be used to store the storage unit 13 of data; Voice-output unit 14 and display unit 15, language learner 1 further comprises: the voice recognition unit 16 that the first user speech information that voice receiving unit 11 is received is discerned.Retrieve the first language information of similarity in the translation dictionary that the first user speech information that CPU (central processing unit) 12 is discerned according to voice recognition unit 16 is stored from storage unit 13, and on display unit 15, show the second language information corresponding with first language information according to the translation dictionary greater than predetermined threshold.Further storage and the corresponding second language data of second language information of storage unit 13, language learner 1 further comprises speech conversion unit 17, and speech conversion unit 17 will become second language with the corresponding second language data-switching of second language information and export by voice-output unit 14.In addition, the voice comparing unit 18 that language learner 1 further will compare through the second user speech information and the second language data of voice receiving unit 11 receptions, and CPU (central processing unit) 12 shows corresponding scoring according to the two similarity on display unit 15.
To want English learning with Chinese user below is that example is carried out exemplary description to the workflow of language learner 1 of the present invention, but the present invention is equally applicable to other language.In use, the head of a family or other user not high for L proficiency can (for example use Chinese needed word of output or sentence by voice receiving unit 11 (Mike), apple), then the voice messaging of 16 pairs of user's inputs of voice recognition unit is discerned, CPU (central processing unit) 12 retrieves from the translation dictionary that storage unit 13 is stored like degree greater than the Chinese information of predetermined threshold and in display unit 15 demonstrations and wait user affirmation according to the recognition result of voice recognition unit 16, after receiving user's confirmation CPU (central processing unit) 12 according to dictionary for translation will be corresponding with Chinese information english information (for example, apple) be presented at display unit 15, practise spelling for the user.And can the speech data corresponding with english information be carried out D/A conversion, amplification etc. by speech conversion unit 17 and handle the back by voice-output unit 14 (loudspeaker or earphone) output, practise hearing or follow and read by the user.In addition, the user also can be English by voice receiving unit 11 outputs according to the displaying contents on the display unit 15, voice comparing unit 18 compares the standard English data of storing in the English of user input and the storage unit then, similarity according to the two shows scoring on display unit 15 then, and wherein comparative parameter can comprise interval and volume.The user can check whether the pronunciation of oneself is correct according to scoring.
In the above-described embodiments, the voice messaging that CPU (central processing unit) 12 is discerned according to voice recognition unit 16 is selected the text message of at least two similarities greater than predetermined threshold from storage unit 13, show on display unit 15 and wait for that the user confirms.The user selects own needed information by the key command at phonetic order or control interface.Can increase the accuracy of speech recognition by this alternate ways.In the storage unit 13 of language learner 1, can store multiple translation dictionary, for example travelling words and phrases storehouse, commercial term dictionary, engineering term dictionary etc.Translate dictionary even can refine to littler classification such as fruit, electrical equipment for the beginner.The user can carry out the most appropriate study by selecting suitable translation dictionary according to concrete language environment.And can comprise that various language translation dictionaries are so that the user carries out multilingual interactive learning.In addition, language learner 1 further comprises the data transmit-receive unit that carries out communication by wired or wireless mode, realizes renewal, the download of the interconnected and storage data between the different language learning machine 1 thus.
The voice recognition unit of language learner of the present invention can comprise: at the special speaker system or at the speech recognition system of unspecified person.In at the special speaker system, the user needs in advance each entry to be trained.In the training stage, each entry of user says successively that the voice recognition unit of language learner extracts the characteristic quantity of entry several times, and characteristic quantity is deposited in the storage unit by sequence.At cognitive phase, the characteristic quantity that voice recognition unit will be imported entry successively with storage unit in each characteristic quantity of storing carry out similarity relatively, similarity is exported as recognition result greater than the entry of predetermined threshold.At the entry number of specific people's recognition system identification generally below 100, recognition performance is along with the increase of entry number can significantly decrease, and for different user, in different noise circumstances, and under the different physiology of different time same subscriber, psychological condition, the performance of system all can be subjected to tangible influence.In the speech recognition system that adopts at unspecified person, adopt algorithm based on statistical model, system developer is gathered a large amount of speech datas in advance and is trained, and obtains acoustic model and is stored in the storage unit.At cognitive phase, voice recognition unit carries out matching and decoding with the characteristic quantity of user's input entry with the recognition network that makes up by acoustic model, exports this entry.CPU (central processing unit) can be carried out corresponding demonstration according to the recognition result of voice recognition unit output.The unspecified person speech recognition system does not need to introduce loaded down with trivial details training process for the user, and is convenient for users to use; It can use for different people simultaneously, has therefore widened range of application greatly.On the other hand, owing to the algorithm that has adopted based on statistical model, its robustness and recognition performance all improve greatly than the special person identification system.The entry number of unspecified person recognition system identification can reach 1000, and recognition performance can not significantly decrease along with the increase of identification entry number, and has certain anti-noise ability.
Pass through technique scheme.The mother tongue input of word or sentence can will investigate by to(for) the limited head of a family of L proficiency or other users, then by language learner carry out speech recognition and by the translation dictionary translate into be presented at after other language messages on the display for the head of a family with reference to or child practise spelling.The mother tongue that language learner of the present invention is also further imported the head of a family is play to supply child to practise hearing or spoken language after converting other language to.In addition, the voice messaging and the standard language data of input can also be compared and mark by language learner of the present invention.
Above-mentioned detailed description only is exemplary description, and those skilled in the art can design various embodiments according to different actual needs under the situation of the scope and spirit that do not break away from the present invention and protected.
Claims (6)
1. multifunctional language learning machine, described language learner comprises: the voice receiving unit that is used to receive the first user speech information; Be used to carry out the CPU (central processing unit) of function control and data processing; Be used to store the storage unit of data; Voice-output unit and display unit, it is characterized in that: described language learner further comprises: the voice recognition unit that the first user speech information that described voice receiving unit received is discerned, retrieval and select at least two similarities and show in the translation dictionary that described CPU (central processing unit) is stored from described storage unit according to the first user speech information of described voice recognition unit identification greater than the first language information of predetermined threshold and at described display unit, and needed first language information translation is become described second language information according to user's confirmation.
2. language learner according to claim 1, it is characterized in that: described storage unit is storage and the corresponding second language data of described second language information further, described language learner further comprises the speech conversion unit, and described speech conversion unit will become second language with the corresponding second language data-switching of described second language information and export by described voice-output unit.
3. language learner according to claim 2, it is characterized in that: the voice comparing unit that described language learner further will compare through the second user speech information and the described second language data of described voice receiving unit reception, and described CPU (central processing unit) shows corresponding scoring according to similarity on described display unit.
4. language learner according to claim 1 is characterized in that: store a plurality of alternate translation dictionaries in the described storer.
5. language learner according to claim 1 is characterized in that: described language learner further comprises the data transmit-receive unit that carries out communication by wired or wireless mode.
6. require any described language learner according to aforesaid right, it is characterized in that: described voice recognition unit is the voice recognition unit at unspecified person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2006100616771A CN101105894B (en) | 2006-07-12 | 2006-07-12 | Multifunctional language learning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2006100616771A CN101105894B (en) | 2006-07-12 | 2006-07-12 | Multifunctional language learning machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101105894A CN101105894A (en) | 2008-01-16 |
| CN101105894B true CN101105894B (en) | 2011-08-10 |
Family
ID=38999777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2006100616771A Expired - Fee Related CN101105894B (en) | 2006-07-12 | 2006-07-12 | Multifunctional language learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101105894B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101840640B (en) * | 2009-03-19 | 2012-08-29 | 财团法人工业技术研究院 | Voice Interaction System and Method |
| US9058751B2 (en) | 2011-11-21 | 2015-06-16 | Age Of Learning, Inc. | Language phoneme practice engine |
| US8740620B2 (en) * | 2011-11-21 | 2014-06-03 | Age Of Learning, Inc. | Language teaching system that facilitates mentor involvement |
| CN103179481A (en) * | 2013-01-12 | 2013-06-26 | 德州学院 | Headphones to improve English listening |
| CN103971550A (en) * | 2013-01-28 | 2014-08-06 | 黑龙江工程学院 | Intelligent specialized Japanese learning machine |
| CN105138663A (en) * | 2015-09-01 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Word bank query method and device |
| CN105678513B (en) * | 2015-12-31 | 2020-02-04 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
| CN106384589A (en) * | 2016-03-07 | 2017-02-08 | 陈勇 | Individual voice input device |
| CN106157711A (en) * | 2016-07-07 | 2016-11-23 | 燕丽 | A kind of intelligence system being applied to ideology and politics teaching |
| CN106228854A (en) * | 2016-07-28 | 2016-12-14 | 新乡医学院 | A kind of Language for English learning system |
| WO2018023506A1 (en) * | 2016-08-03 | 2018-02-08 | 李仁涛 | Smart toy for children |
| CN109272983A (en) * | 2018-10-12 | 2019-01-25 | 武汉辽疆科技有限公司 | Bilingual switching device for parent-child education |
| CN109448458A (en) * | 2018-11-29 | 2019-03-08 | 郑昕匀 | English oral training device, data processing method and storage medium |
| CN109637227A (en) * | 2018-12-28 | 2019-04-16 | 三河市简译软件开发有限公司 | A kind of shared learning machine of portable intelligent |
| CN110459081A (en) * | 2019-08-21 | 2019-11-15 | 河南工业职业技术学院 | A device for assisting English memory |
| CN111312220A (en) * | 2019-12-02 | 2020-06-19 | 西安冉科信息技术有限公司 | Learning method based on dialogue exchange of learning machine |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4611995A (en) * | 1979-10-16 | 1986-09-16 | Canon Kabushiki Kaisha | Electronic language learning machine |
| CN2147604Y (en) * | 1993-03-31 | 1993-11-24 | 上海荣川应用技术研究所 | Language learning machine |
| CN1178023A (en) * | 1995-03-07 | 1998-04-01 | 英国电讯公司 | Speech recognition device |
| CN1182259A (en) * | 1996-11-11 | 1998-05-20 | 李琳山 | Voice training system and training method |
| CN1399191A (en) * | 2002-09-09 | 2003-02-26 | 北京南山高科技有限公司 | Processing method for Chinese phonetic recognition word library |
| CN1763843A (en) * | 2005-11-18 | 2006-04-26 | 清华大学 | Pronunciation quality assessment method for language learning machine |
| CN1786943A (en) * | 2004-12-24 | 2006-06-14 | 卢国跃 | Apparatus for Chinese and English phonetic exchange |
-
2006
- 2006-07-12 CN CN2006100616771A patent/CN101105894B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4611995A (en) * | 1979-10-16 | 1986-09-16 | Canon Kabushiki Kaisha | Electronic language learning machine |
| CN2147604Y (en) * | 1993-03-31 | 1993-11-24 | 上海荣川应用技术研究所 | Language learning machine |
| CN1178023A (en) * | 1995-03-07 | 1998-04-01 | 英国电讯公司 | Speech recognition device |
| CN1182259A (en) * | 1996-11-11 | 1998-05-20 | 李琳山 | Voice training system and training method |
| CN1399191A (en) * | 2002-09-09 | 2003-02-26 | 北京南山高科技有限公司 | Processing method for Chinese phonetic recognition word library |
| CN1786943A (en) * | 2004-12-24 | 2006-06-14 | 卢国跃 | Apparatus for Chinese and English phonetic exchange |
| CN1763843A (en) * | 2005-11-18 | 2006-04-26 | 清华大学 | Pronunciation quality assessment method for language learning machine |
Non-Patent Citations (2)
| Title |
|---|
| JP特开2004-286834A 2004.10.14 |
| JP特开平8-50444A 1996.02.20 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101105894A (en) | 2008-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101105894B (en) | Multifunctional language learning machine | |
| US10217464B2 (en) | Vocabulary generation system | |
| CN108711420B (en) | Multilingual hybrid model establishing method, multilingual hybrid model establishing device, multilingual hybrid model data obtaining device and electronic equipment | |
| US10319250B2 (en) | Pronunciation guided by automatic speech recognition | |
| CN101414412A (en) | Interaction type acoustic control children education studying device | |
| WO2022078146A1 (en) | Speech recognition method and apparatus, device, and storage medium | |
| US8515764B2 (en) | Question and answer database expansion based on speech recognition using a specialized and a general language model | |
| CN105609107A (en) | Text processing method and device based on voice identification | |
| CN101115245A (en) | Mobile terminal with speech recognition and translating function | |
| CN110853422A (en) | Immersive language learning system and learning method thereof | |
| CN107909523A (en) | A kind of interactive learning methods and its learning system | |
| CN105575384A (en) | Method, device and equipment for automatically adjusting playing resources according to user level | |
| CN112463942A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
| US9805740B2 (en) | Language analysis based on word-selection, and language analysis apparatus | |
| CN111968646A (en) | Voice recognition method and device | |
| Obaido et al. | Talksql: A tool for the synthesis of sql queries from verbal specifications | |
| CN201054644Y (en) | Mobile terminal with voice recognition and translation function | |
| CN109473007B (en) | English natural spelling teaching method and system combining phonemes with sound side | |
| CN110148413B (en) | Voice evaluation method and related device | |
| CN201111735Y (en) | Interaction type acoustic control children education studying device | |
| CN104572617A (en) | Oral test answer deviation detection method and device | |
| CN101739852B (en) | Speech recognition-based method and device for realizing automatic oral interpretation training | |
| CN112086094B (en) | Method for correcting pronunciation, terminal equipment and computer readable storage medium | |
| CN111489742A (en) | Acoustic model training method, voice recognition method, device and electronic equipment | |
| KR102396833B1 (en) | System and method for studying korean pronunciation using voice analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160603 Address after: Panyu District Dalong street Guangzhou city Guangdong province 511450 Changsha Lu Chung Village No. 29 101 11 Patentee after: GUANGZHOU MEILU ELECTRONICS CO.,LTD. Address before: 518410 Guangdong city of Shenzhen province Nanshan District Shennan garden A Building Room 403 Patentee before: Chen Xiuzhi |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110810 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |