CN104778865A - Method for conducting spoken language correction through speech recognition technology and language learning machine - Google Patents
Method for conducting spoken language correction through speech recognition technology and language learning machine Download PDFInfo
- Publication number
- CN104778865A CN104778865A CN201410023709.3A CN201410023709A CN104778865A CN 104778865 A CN104778865 A CN 104778865A CN 201410023709 A CN201410023709 A CN 201410023709A CN 104778865 A CN104778865 A CN 104778865A
- Authority
- CN
- China
- Prior art keywords
- speech recognition
- module
- output module
- central processing
- processing unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/065—Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to a method for conducting spoken language correction through the speech recognition technology. Spoken language pronunciation of a user is identified through the speech recognition technology so as to correct spoken language pronunciation. The invention further relates to a language learning machine; an audio input and output module is connected with a speech recognition module and a central processing unit, and the speech recognition module, a storage unit and a display module are each connected with the central processing unit; a speech recognition database is stored in the storage unit, and the speech recognition module calls the speech recognition database to analyze and process speech signals input through the audio input and output module; and processed data are transmitted to the central processing unit, and the data transmitted through the speech recognition module is transmitted to the display module through the central processing unit so as to be output through the display module in an image mode. Image and speed comparison is carried out on pronunciations of the user and original standard pronunciations through the speech recognition technology, the pronunciation accuracy is accurately judged, correction is carried out in time, the spoken language pronunciation level is rapidly improved, and the listening level of the user can be rapidly improved.
Description
Technical field
The invention belongs to aided education field, be specifically related to a kind of speech recognition technology of applying and carry out the method for spoken rectification and a kind of language learner.
Background technology
Current, the domestic language environment lacking foreign language learning, exercise, foreign language listening and spoken language are the difficult points of foreign language teaching, most School English Teaching remains and lays particular emphasis on foreign language knowwhy, the foreign language of Students ' Learning remains " Dumb English " mostly, knowwhy level is relatively high, and listening and speaking ability is very poor, does not also have a kind of method and the instrument that carry out foreign language listening-speaking study preferably at present.
Summary of the invention
The object of this invention is to provide can improve foreign language learning hearing fast, a kind of speech recognition technology of applying of oracy carries out spoken method of correcting, the step of the method is:
Step one: user carries out spoken language pronunciation according to source information facing to microphone;
Step 2: by the spoken language pronunciation of speech recognition technology identification user;
Step 3: the spoken language pronunciation information after identification is shown by textual form;
Step 4: user by the text after relative discern and source information multilevel iudge spoken language pronunciation whether standard, accurately, if recognition result and source information inconsistent, then correct spoken language pronunciation, repeat above process, if unanimously, then carry out the next one and circulate.
In order to reach listening and speaking effect better, said method is also included in user and carries out before step one carries out spoken language pronunciation, and carry out Received Pronunciation by speech play, user carries out with reading.
Above-mentioned source information comprises received text or Received Pronunciation etc.
The present invention also comprises and can improve foreign language learning hearing fast, a kind of language learner of oracy, this equipment comprises housing, power supply, also comprise microphone, audio frequency input/output module, sound identification module, CPU (central processing unit), display module and storage unit etc., audio frequency input/output module is connected with sound identification module and CPU (central processing unit), sound identification module, storage unit, display module, be connected with CPU (central processing unit) respectively, cell stores has speech recognition database, sound identification module calls speech recognition database and is analyzed by the voice signal that audio frequency input/output module inputs, process, the data processed are transferred to CPU (central processing unit), the data transmitted by sound identification module are transferred to display module and are exported with image format by display module by CPU (central processing unit).
Display module comprises LCDs, and LCDs carries out image output.
This equipment also comprises loudspeaker, and loudspeaker is connected with audio frequency input/output module, is exported in the form of sound by the signal that the transmission of audio frequency input/output module comes.
Microphone and audio frequency input/output module or loudspeaker and audio frequency input/output module pass through wireless signal transmission.
Also comprise data input/output module, data input/output module is connected with CPU (central processing unit), data input/output module comprises card reader, USB interface or bluetooth etc., be connected with external unit by data input/output module, by data input/output module by the storage information transmission of storage unit to external unit, or by the storage information transmission of external unit to language learner, show by the display module of language learner or play by loudspeaker.
This equipment also comprises mixed-media network modules mixed-media, mixed-media network modules mixed-media comprises wifi, GPRS, 3G, 4G radio communication unit or wire communication unit etc., mixed-media network modules mixed-media carries out network connection by wireless or wire communication, utilizes Internet resources to carry out signal transacting, data upload and download.
The CPU (central processing unit) of language learner is accepted instruction and the language message of cell stores is transferred to display module and is shown by display module and be transferred to audio frequency input/output module and be converted to form of sound by loudspeaker and export, user sees display information and hears the voice that language learner is play, undertaken with reading by microphone, microphone by transmitting voice signal to audio frequency input/output module, the simulating signal of microphone is converted to voice digital signal by audio frequency input/output module, and the voice digital signal after process is transferred to sound identification module and CPU (central processing unit), sound identification module is by the speech recognition database of storage unit or carry out voice recognition processing by network data base, by the Signal transmissions of identification to CPU (central processing unit), the voice digital signal inputted by audio frequency input/output module is transferred to storer storage or the voice digital signal inputted by audio frequency input/output module is transferred to audio frequency input/output module and is converted to form of sound output by loudspeaker by CPU (central processing unit), the Signal transmissions inputted by sound identification module stores to storer or is exported with image format by display module to display module by the Signal transmissions inputted by sound identification module by CPU (central processing unit), user to be compared with original content by the identification content of display and passes through to compare with reading sound and original sound the pronunciation whether standard judging oneself, by continuous rectification, reach the raising of spoken language pronunciation.
The pronunciation of user and primary standard are pronounced to carry out the contrast of image and sound by utilizing speech recognition technology by this equipment, accurately can judge the accuracy of pronouncing, timely correction, reaches and improves spoken language pronunciation level fast, and can improve the hearing level of user fast.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of embodiment 1;
Fig. 2 is the process flow diagram of embodiment 2;
Fig. 3 is the general frame figure of embodiment 3;
Fig. 4 is the general frame figure of embodiment 4;
Fig. 5 is the microphone in embodiment 4;
Fig. 6 is the loudspeaker in embodiment 4;
Fig. 7 is the general frame figure of embodiment 5.
Wherein: 1-housing, 2-power supply, 3-microphone, 4-loudspeaker, 5-audio frequency input/output module, 6-sound identification module, 7-CPU (central processing unit), 8-display module, 8.1-liquid crystal display, 9-storage unit, 10-data input/output module, 11-mixed-media network modules mixed-media.
Embodiment
Embodiment 1
As shown in Figure 1, a kind of speech recognition technology of applying carries out spoken method of correcting, and the step of the method is:
Step one: user carries out spoken language pronunciation according to source information facing to microphone;
Step 2: by the spoken language pronunciation of speech recognition technology identification user;
Step 3: the spoken language pronunciation information after identification is shown by textual form;
Step 4: user by the text after relative discern and source information multilevel iudge spoken language pronunciation whether standard, accurately, if recognition result and source information inconsistent, then correct spoken language pronunciation, repeat above process, if unanimously, then carry out the next one and circulate.
Embodiment 2
As shown in Figure 2, a kind of speech recognition technology of applying carries out spoken method of correcting, and the step of the method is:
Step one: carry out Received Pronunciation by speech play.
Step 2: user carries out spoken language pronunciation according to source information facing to microphone;
Step 3: by the spoken language pronunciation of speech recognition technology identification user;
Step 4: the spoken language pronunciation information after identification is shown by textual form;
Step 5: user by the text after relative discern and source information multilevel iudge spoken language pronunciation whether standard, accurately, if recognition result and source information inconsistent, then correct spoken language pronunciation, repeat above process, if unanimously, then carry out the next one and circulate.
Embodiment 3
As shown in Figure 3, language learner comprises housing 1, power supply 2, microphone 3, loudspeaker 4, audio frequency input/output module 5, sound identification module 6, CPU (central processing unit) 7, display module 8 and storage unit 9, audio frequency input/output module 5 is connected with sound identification module 6 and CPU (central processing unit) 7, sound identification module 6, storage unit 9, display module 8 is connected with CPU (central processing unit) 7 respectively, storage unit 9 stores speech recognition database, sound identification module 6 calls speech recognition database and is analyzed by the voice signal that audio frequency input/output module 5 inputs, process, the data processed are transferred to CPU (central processing unit) 7, the data transmitted by sound identification module 6 are transferred to display module 8 and are exported with image format by display module 8 by CPU (central processing unit) 7.
Display module 8 comprises LCDs 8.1, and LCDs 8.1 carries out image output.
Loudspeaker 4 is connected with audio frequency input/output module 5, audio frequency input/output module 5 is transmitted the signal come and exports in the form of sound.
Microphone 3 passes through wire transmission signal with audio frequency input/output module 5 and loudspeaker 4 with audio frequency input/output module 5.
Embodiment 4
As shown in Figures 4 to 6, language learner comprises housing 1, power supply 2, microphone 3, loudspeaker 4, audio frequency input/output module 5, sound identification module 6, CPU (central processing unit) 7, display module 8 and storage unit 9, audio frequency input/output module 5 is connected with sound identification module 6 and CPU (central processing unit) 7, sound identification module 6, storage unit 9, display module 8 is connected with CPU (central processing unit) 7 respectively, storage unit 9 stores speech recognition database, sound identification module 6 calls speech recognition database and is analyzed by the voice signal that audio frequency input/output module 5 inputs, process, the data processed are transferred to CPU (central processing unit) 7, the data transmitted by sound identification module 6 are transferred to display module 8 and are exported with image format by display module 8 by CPU (central processing unit) 7.
Loudspeaker 4 is connected with audio frequency input/output module 5, audio frequency input/output module 5 is transmitted the signal come and exports in the form of sound.
Microphone 3 passes through wireless signal transmission with audio frequency input/output module 5 and loudspeaker 4 with audio frequency input/output module 5.
This equipment also comprises data input/output module 10, data input/output module 10 is connected with CPU (central processing unit) 7, data input/output module 10 comprises card reader, USB interface, bluetooth etc., be connected with external unit by data input/output module, by data input/output module by the storage information transmission of storage unit to external unit, or by the storage information transmission of external unit to language learner, show by the display module of language learner or play by loudspeaker.
Embodiment 5
As shown in Figure 7, this equipment also comprises mixed-media network modules mixed-media 11, mixed-media network modules mixed-media 11 comprises wifi, GPRS, 3G, 4G radio communication unit or wire communication unit, and mixed-media network modules mixed-media 11 carries out network connection by wireless or wire communication, utilizes Internet resources to carry out signal transacting, data upload and download.
All the other are with embodiment 4.
Claims (10)
1. apply speech recognition technology and carry out a spoken method of correcting, the step of the method is:
Step one: user carries out spoken language pronunciation according to source information facing to microphone;
Step 2: by the spoken language pronunciation of speech recognition technology identification user;
Step 3: the spoken language pronunciation information after identification is shown by textual form;
Step 4: user by the text after relative discern and source information multilevel iudge spoken language pronunciation whether standard, accurately, if recognition result and source information inconsistent, then correct spoken language pronunciation, repeat above process, if unanimously, then carry out the next one and circulate.
2. a kind of speech recognition technology of applying according to claim 1 carries out spoken method of correcting, and its step also comprises: carry out before step one carries out spoken language pronunciation user, carry out Received Pronunciation by speech play, user carries out with reading.
3. a foreign language learning machine, comprise housing, power supply, it is characterized in that: also comprise microphone, audio frequency input/output module, sound identification module, CPU (central processing unit), display module, storage unit, audio frequency input/output module is connected with sound identification module and CPU (central processing unit), sound identification module, storage unit, display module, be connected with CPU (central processing unit) respectively, cell stores has speech recognition database, sound identification module calls speech recognition database and is analyzed by the voice signal that audio frequency input/output module inputs, process, the data processed are transferred to CPU (central processing unit), the data transmitted by sound identification module are transferred to display module and are exported with image format by display module by CPU (central processing unit).
4. a kind of foreign language learning machine according to claim 3, is characterized in that: display module comprises LCDs, and LCDs carries out image output.
5. a kind of foreign language learning machine according to claim 3, is characterized in that: also comprise loudspeaker, and loudspeaker is connected with audio frequency input/output module, is exported in the form of sound by the signal that the transmission of audio frequency input/output module comes.
6. a kind of foreign language learning machine according to claim 3, is characterized in that: microphone and audio frequency input/output module pass through wireless signal transmission.
7. a kind of foreign language learning machine according to claim 6, is characterized in that: loudspeaker and audio frequency input/output module pass through wireless signal transmission.
8. a kind of foreign language learning machine according to claim 3, it is characterized in that: also comprise data input/output module, data input/output module is connected with CPU (central processing unit).
9. a kind of foreign language learning machine according to claim 3, is characterized in that: also comprise mixed-media network modules mixed-media, carries out network connection by mixed-media network modules mixed-media.
10. a kind of foreign language learning machine according to claim 3, is characterized in that: sound identification module accessible site audio frequency input/output module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410023709.3A CN104778865A (en) | 2014-01-14 | 2014-01-14 | Method for conducting spoken language correction through speech recognition technology and language learning machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410023709.3A CN104778865A (en) | 2014-01-14 | 2014-01-14 | Method for conducting spoken language correction through speech recognition technology and language learning machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104778865A true CN104778865A (en) | 2015-07-15 |
Family
ID=53620302
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410023709.3A Pending CN104778865A (en) | 2014-01-14 | 2014-01-14 | Method for conducting spoken language correction through speech recognition technology and language learning machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104778865A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106023682A (en) * | 2016-07-27 | 2016-10-12 | 新乡学院 | English teaching system based on intelligent terminal |
CN106454491A (en) * | 2016-09-30 | 2017-02-22 | 天脉聚源(北京)传媒科技有限公司 | Method and device for playing voice information in video smartly |
CN106530867A (en) * | 2016-11-02 | 2017-03-22 | 天津福威科技发展有限公司 | Intelligent online education training system |
CN107507467A (en) * | 2017-09-18 | 2017-12-22 | 滨州学院 | A kind of Multimedia EFL teaching system |
CN108091182A (en) * | 2016-11-22 | 2018-05-29 | 罗敬业 | The english teaching device of smart machine |
CN108831212A (en) * | 2018-06-28 | 2018-11-16 | 深圳语易教育科技有限公司 | A kind of oral English teaching auxiliary device and method |
CN109003475A (en) * | 2018-09-03 | 2018-12-14 | 安徽声讯信息技术有限公司 | A kind of control system and method based on mobile phone speech children's early learning machine |
CN109147419A (en) * | 2018-07-11 | 2019-01-04 | 北京美高森教育科技有限公司 | Language learner system based on incorrect pronunciations detection |
CN109859536A (en) * | 2019-01-14 | 2019-06-07 | 九江学院 | A kind of Foreigh-language oral-speech correction system |
CN112289089A (en) * | 2020-10-26 | 2021-01-29 | 烟台职业学院 | Multi-functional exercise device of oral english ability |
-
2014
- 2014-01-14 CN CN201410023709.3A patent/CN104778865A/en active Pending
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106023682A (en) * | 2016-07-27 | 2016-10-12 | 新乡学院 | English teaching system based on intelligent terminal |
CN106454491A (en) * | 2016-09-30 | 2017-02-22 | 天脉聚源(北京)传媒科技有限公司 | Method and device for playing voice information in video smartly |
CN106530867A (en) * | 2016-11-02 | 2017-03-22 | 天津福威科技发展有限公司 | Intelligent online education training system |
CN108091182A (en) * | 2016-11-22 | 2018-05-29 | 罗敬业 | The english teaching device of smart machine |
CN107507467A (en) * | 2017-09-18 | 2017-12-22 | 滨州学院 | A kind of Multimedia EFL teaching system |
CN108831212A (en) * | 2018-06-28 | 2018-11-16 | 深圳语易教育科技有限公司 | A kind of oral English teaching auxiliary device and method |
CN109147419A (en) * | 2018-07-11 | 2019-01-04 | 北京美高森教育科技有限公司 | Language learner system based on incorrect pronunciations detection |
CN109003475A (en) * | 2018-09-03 | 2018-12-14 | 安徽声讯信息技术有限公司 | A kind of control system and method based on mobile phone speech children's early learning machine |
CN109859536A (en) * | 2019-01-14 | 2019-06-07 | 九江学院 | A kind of Foreigh-language oral-speech correction system |
CN112289089A (en) * | 2020-10-26 | 2021-01-29 | 烟台职业学院 | Multi-functional exercise device of oral english ability |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104778865A (en) | Method for conducting spoken language correction through speech recognition technology and language learning machine | |
CN110136691B (en) | Speech synthesis model training method and device, electronic equipment and storage medium | |
CN110600033B (en) | Learning condition evaluation method and device, storage medium and electronic equipment | |
US10783884B2 (en) | Electronic device-awakening method and apparatus, device and computer-readable storage medium | |
JP6925469B2 (en) | Smart microphone control server and system | |
CN110111778B (en) | Voice processing method and device, storage medium and electronic equipment | |
CN104602136A (en) | Subtitle display method and system for foreign language learning | |
CN113498536A (en) | Electronic device and control method thereof | |
CN111522971A (en) | Method and device for assisting user in attending lessons in live broadcast teaching | |
CN109255130A (en) | A kind of method, system and the equipment of language translation and study based on artificial intelligence | |
CN103413469A (en) | Social type language learning system | |
CN104978875A (en) | Multi-functional intelligent teaching system | |
US9087512B2 (en) | Speech synthesis method and apparatus for electronic system | |
CN203562105U (en) | English listening comprehension training device | |
KR100997255B1 (en) | Language learning system of simultaneous interpretation type using voice recognition | |
CN113012683A (en) | Speech recognition method and device, equipment and computer readable storage medium | |
KR102233155B1 (en) | Apparatus for Learning Service Using Speech Recorgnition and Driving Method Thereof | |
CN112185186B (en) | Pronunciation correction method and device, electronic equipment and storage medium | |
CN204903990U (en) | Smart box | |
CN203909165U (en) | A PS/2 computer input equipment tester with a voice function | |
CN112052358A (en) | Method, apparatus, electronic device and computer readable medium for displaying image | |
CN110728992A (en) | Audio data processing method and device, server and storage medium | |
CN110277104B (en) | Word voice training system | |
TWI768412B (en) | Pronunciation teaching method | |
CN103794229A (en) | Audio control device and method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150715 |