CN111710203A - English pronunciation correction system based on big data - Google Patents
English pronunciation correction system based on big data Download PDFInfo
- Publication number
- CN111710203A CN111710203A CN202010681307.8A CN202010681307A CN111710203A CN 111710203 A CN111710203 A CN 111710203A CN 202010681307 A CN202010681307 A CN 202010681307A CN 111710203 A CN111710203 A CN 111710203A
- Authority
- CN
- China
- Prior art keywords
- pronunciation
- target
- english word
- english
- standard
- 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.)
- Withdrawn
Links
Images
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
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to an English pronunciation correction system based on big data, which comprises a teacher end host and a student end host, wherein a student starts English pronunciation correction through the student end host, the teacher end host determines a target English word and corresponding target audio data after receiving an English pronunciation correction starting instruction and sends the target English word and the corresponding target audio data to the student end host, the student end host displays the target English word, then acquires an actual pronunciation signal, determines whether the pronunciation is standard or not by combining standard pronunciation, and realizes pronunciation correction, the student end host sends the actual pronunciation signal to the teacher end host, and the teacher end host processes the actual pronunciation signal, judges whether the pronunciation is standard or not, and sends a judgment result to the student end host. The student can carry out the reliable correction of english pronunciation through this english pronunciation correction system, promotes english learning efficiency and enthusiasm, moreover, reduces mr's work burden, promotes teaching efficiency.
Description
Technical Field
The invention relates to an English pronunciation correction system based on big data.
Background
In English learning, the pronunciation with correct standard of English words is the basis for learning good English, even if the more English vocabulary is mastered, if the pronunciation is wrong, the pronunciation still can not be communicated with other people normally, so the teaching of the pronunciation of the English words is very important. However, for learners of non-english native language, effective correction of pronunciation is a difficult point in english learning and a key point in english oral teaching. In the pronunciation teaching of present english, the teacher is according to the english pronunciation of oneself grasping, imparts knowledge to students, consequently, whether student's english pronunciation standard depends on teacher's english pronunciation level, and when teacher's english pronunciation standard, can seriously influence student's english pronunciation.
Disclosure of Invention
In order to solve the technical problem, the invention provides an English pronunciation correction system based on big data.
The invention adopts the following technical scheme:
an English pronunciation correction system based on big data comprises a teacher end host and a student end host;
the teacher end host includes: the system comprises an English pronunciation correction starting instruction receiving module, an English word database, a target English word database acquisition module, a target English word database display module, a target English word determination module, an English word standard pronunciation database, a target English word standard pronunciation acquisition module, a target English word sending module, an actual pronunciation signal receiving module, a noise filtering module, an actual pronunciation waveform generating module, an English standard pronunciation waveform database, a target standard pronunciation waveform acquisition module, a waveform comparison module, a pronunciation result judgment module and a judgment result sending module;
the student end host computer includes: the system comprises an English pronunciation correction starting instruction sending module, a target English word receiving module, a target English word display module, an actual pronunciation signal acquisition module, a target standard pronunciation external playing module, an actual pronunciation signal sending module and a judgment result display module;
the English pronunciation correction starting instruction sending module is used for sending an English pronunciation correction starting instruction to the teacher end host, and the English pronunciation correction starting instruction comprises grade information of a target student;
the English pronunciation correction starting instruction receiving module is used for receiving the English pronunciation correction starting instruction;
the target English word database acquisition module is used for acquiring an English word database corresponding to the grade information of the target student from the English word database according to the grade information of the target student to obtain a target English word database; the English word database comprises at least two English word databases, each English word database corresponds to the grade of a student one by one, and each English word database comprises at least two English words;
the target English word database display module is used for displaying each English word in the target English word database;
the target English word determining module is used for selecting a part of English words from the target English word database to obtain target English words;
the target English word standard pronunciation acquisition module is used for acquiring audio data of standard pronunciation corresponding to the target English word from the English word standard pronunciation database according to the target English word to obtain target audio data; the English word standard pronunciation database comprises each English word in the English word database and audio data of standard pronunciation of each English word;
the target English word sending module is used for sending the target English word and the target audio data to the student end host;
the target English word receiving module is used for receiving the target English word and the target audio data;
the target English word display module is used for displaying the target English word;
the actual pronunciation signal acquisition module is used for acquiring an actual pronunciation signal of the target English word sent by the student according to the target English word;
the target standard pronunciation external playing module is used for externally playing the target audio data through audio external playing equipment according to the target audio data and the actual pronunciation signal of the target English word;
the actual pronunciation signal sending module is used for sending the actual pronunciation signal of the target English word to the teacher-side host;
the actual pronunciation signal receiving module is used for receiving an actual pronunciation signal of the target English word;
the noise filtering module is used for performing noise filtering on the actual pronunciation signal of the target English word to obtain a target actual pronunciation signal;
the actual pronunciation waveform generating module is used for processing the target actual pronunciation signal and generating an actual pronunciation waveform corresponding to the target actual pronunciation signal;
the target standard pronunciation waveform acquisition module is used for acquiring a standard pronunciation waveform of a standard pronunciation corresponding to the target English word from the English standard pronunciation waveform database according to the target English word and the actual pronunciation waveform to obtain a target standard pronunciation waveform; the English standard pronunciation waveform database comprises English words in the English word database and standard pronunciation waveforms corresponding to the English words;
the waveform comparison module is used for comparing the actual pronunciation waveform with the target standard pronunciation waveform;
the pronunciation result judging module is used for acquiring a judgment result of whether the pronunciation of the target English word is standard or not by the student according to the comparison result of the actual pronunciation waveform and the target standard pronunciation waveform;
the judgment result sending module is used for sending the judgment result to the student end host;
and the judgment result display module is used for receiving and displaying the judgment result.
Optionally, the waveform comparison module is specifically configured to:
constructing the actual pronunciation waveform and the target standard pronunciation waveform in the same voice coordinate system;
extracting the voice key features of the actual pronunciation waveform according to a preset voice feature recognition algorithm to form a voice key feature vector and obtain an actual voice key feature vector; extracting the voice key features of the target standard pronunciation waveform to form a voice key feature vector to obtain a standard voice key feature vector;
and comparing the actual voice key feature vector with the standard voice key feature vector to obtain a comparison result.
Optionally, the comparing the actual speech key feature vector with the standard speech key feature vector to obtain a comparison result includes:
if the matching degree of the actual voice key feature vector and the standard voice key feature vector is greater than or equal to a preset threshold value, the comparison result is that the comparison is passed; if the matching degree of the actual voice key feature vector and the standard voice key feature vector is smaller than the preset threshold, the comparison result is that the comparison is not passed;
correspondingly, the pronunciation result judgment module is specifically configured to: if the comparison result is that the comparison is passed, the judgment result is the pronunciation standard of the student to the target English word; and if the comparison result is that the comparison is not passed, the judgment result is that the pronunciation of the target English word is not standard for the student.
The invention has the following technical effects: a student starts English pronunciation correction through a student end host, a teacher end host determines a target English word data sub-library after receiving an English pronunciation correction starting instruction, a teacher selects a part of English words needing English pronunciation correction according to each English word of the displayed target English word data sub-library to obtain target English words, and acquires target audio data corresponding to standard pronunciation of the target English words according to an English word standard pronunciation data library, the teacher end host sends the target English words and the target audio data to the student end host, the student end host displays the target English words and then acquires actual pronunciation signals of the target English words sent by the student, the student end host externally displays the target audio data according to the target audio data and the actual pronunciation signals of the target English words, and the student can determine whether the pronunciation is standard according to the standard pronunciation and the actual pronunciation of the student, the pronunciation of the student is effectively corrected according to the standard pronunciation, the efficiency and the reliability of English pronunciation correction are improved, a teacher is not required to correct the pronunciation, and the influence on the English pronunciation of the student when the English pronunciation of the teacher is not standard is avoided; the student end host sends an actual pronunciation signal to the teacher end host, the teacher end host generates a corresponding actual pronunciation waveform after noise filtering is carried out on the actual pronunciation signal, a standard pronunciation waveform of a standard pronunciation corresponding to a target English word is obtained from an English standard pronunciation waveform database, the teacher end host compares the two pronunciation waveforms, a judgment result of whether the pronunciation of the target English word is standard or not is obtained according to the comparison result, the judgment result is finally sent to the student end host, the student end host receives and displays the judgment result, automatic judgment of whether the pronunciation is standard or not is realized through a judgment program in the teacher end host, students can intuitively know whether the pronunciation is standard or not according to the judgment result, effective correction is carried out on the pronunciation of the students, and the efficiency and reliability of English pronunciation correction are improved; therefore, the judgment result of whether the pronunciation is standard is obtained through two modes of the student self judgment and the judgment of the teacher end host, and then the student can effectively correct the own English pronunciation. This system is corrected in pronunciation of english can realize the reliable correction of student's pronunciation of english, promotes student's english learning efficiency and enthusiasm, and student's english study no longer receives mr's english ability and the influence of teaching ability, avoids appearing influencing the condition of student's pronunciation of english when mr's pronunciation of english exists the nonstandard condition, can also reduce mr's work burden, promotes teaching efficiency.
Drawings
Fig. 1 is a schematic structural composition diagram of an english pronunciation correction system based on big data according to the present invention.
Detailed Description
The embodiment provides an english pronunciation correction system based on big data, as shown in fig. 1, including a teacher end host and a student end host. The hardware devices corresponding to the teacher-side host and the student-side host are not limited, and may be computer devices, such as desktop computers or notebook computers, or intelligent terminal devices, such as tablet computers or smart phones.
The teacher end host computer is in communication connection with the student end host computer, and can be in wired communication connection, namely, the teacher end host computer and the student end host computer are connected through related communication lines, such as RS485 communication; also can wireless communication, then, teacher end host computer and student end host computer all are provided with wireless communication module, carry out communication connection through wireless communication module, and wireless communication module's specific type is set up by actual need.
The number of the teacher end host and the student end host in the English pronunciation correction system is not limited, and under the ordinary condition, the teacher end host is set to be one, and the student end host can be set to be one or a plurality of. In this embodiment, for convenience of description, the english pronunciation correction system includes a teacher-side host and a student-side host.
The teacher end host computer includes: english pronunciation correct start instruction receiving module, english word database, target english word database acquisition module, target english word database display module, target english word is confirmed the module, english word standard pronunciation database, target english word standard pronunciation acquisition module, target english word sending module, actual pronunciation signal receiving module, the noise filter module, actual pronunciation waveform generation module, english standard pronunciation waveform database, target standard pronunciation waveform acquisition module, the waveform comparison module, pronunciation result judgment module and judgment result sending module.
Student end host computer includes: english pronunciation correct start instruction sending module, target English word receiving module, target English word display module, actual pronunciation signal acquisition module, target standard pronunciation outward put module, actual pronunciation signal sending module and judgement result display module.
It should be understood that each module in the teacher-side host and the student-side host may be a hardware module, and may also be a software module. In this embodiment, the software modules are taken as an example, and if the software modules are software modules, each software module is essentially a corresponding execution step.
The student operates the student end host to initiate english pronunciation correction. And the English pronunciation correction starting instruction sending module in the student end host is used for sending an English pronunciation correction starting instruction to the teacher end host. It should be understood that the english pronunciation correction initiation command can be input by the relevant information input device on the student end host, such as: and the student operates the touch screen or the keyboard to edit the English pronunciation correction starting instruction. And receiving and outputting the English pronunciation correction starting instruction obtained by editing to a teacher end host by an English pronunciation correction starting instruction sending module. The English pronunciation correction starting instruction comprises grade information of a target student, wherein the grade information of the target student is grade information of the target student, and the target student refers to a student operating the student end host. It should be understood that the english language pronunciation correction start instruction may include data information of the start instruction itself, such as a specific character string, in addition to the grade information of the target student.
And the English pronunciation correction starting instruction receiving module of the teacher end host is used for receiving an English pronunciation correction starting instruction.
The English word database in the teacher host comprises at least two English word databases, and the number of the English word databases is set according to actual needs. Each english word data sub-library corresponds to a student grade one to one, namely, each student grade corresponds to one english word data sub-library, for example: including three english word data sub-base, junior middle school grade corresponds first english word data sub-base, and junior middle school grade two corresponds second english word data sub-base, and junior middle school grade three corresponds third english word data sub-base. Each english word data sub-library includes two at least english words, and specific number is set up by actual need, and each english word that english word data sub-library includes should master for the student of corresponding grade english word.
And the target English word database acquisition module is used for acquiring an English word database corresponding to the grade information of the target student from the English word database according to the grade information of the target student, and the obtained English word database is the target English word database. Such as: and if the grade information of the target student is junior-middle-second grade, acquiring an English word database corresponding to junior-middle-second grade from the English word database.
The hardware device that target english word data sub-base display module corresponds can be touch-sensitive screen or display screen, and in this embodiment, the hardware device that target english word data sub-base display module corresponds is the touch-sensitive screen of teacher's end host computer. And the target English word database display module is used for displaying each English word in the target English word database through the touch screen. It should be understood that if the number of english words in the target english word database is large and one display page of the touch screen cannot be displayed completely, the touch screen supports paging display.
After the teacher sees each english word that shows through the touch-sensitive screen, through corresponding operation, select partial english word from target english word data sub-base, carry out the english word that the english pronunciation corrected as the student. Taking a touch screen as an example, a teacher may click on a selected english word on the touch screen. The touch screen can be provided with a selection determination virtual key, and when the selection is finished, the selection determination virtual key is clicked to finish the selection. As another embodiment, the selected english word may be tapped by another input device such as a keyboard, or the number label corresponding to the selected english word may be tapped, and the keyboard may be further provided with a selected and determined entity key, and when the selection is completed, the selected and determined entity key is clicked to complete the selection. Therefore, regardless of the operation employed by the teacher, the teacher selects a partial english word from the target english word database. Correspondingly, the target English word determining module is used for selecting a part of English words from the target English word database, wherein the selected English words are target English words. It should be understood that there may be only one or at least two english words selected, and for convenience of illustration, a target english word is taken as an example below. It should be understood that if at least two english words are selected, the pronunciation correction process for each english word is the same.
The standard pronunciation database of english words in the teacher host is a database storing audio data of standard pronunciations of english words, and specifically: including each english word in the english word database described above, and the audio data of the standard pronunciation of each english word. That is, the english word standard pronunciation database includes all english words in the english word database described above, as well as audio data of the standard pronunciation of each english word. For any English word, the audio data corresponding to the standard pronunciation of the English word is the voice signal of the standard pronunciation of the English word, and when the voice signal is played, the standard pronunciation of the English word can be heard.
And after the target English word is obtained, the target English word standard pronunciation acquisition module is used for acquiring audio data of standard pronunciation corresponding to the target English word from the English word standard pronunciation database according to the target English word, and the acquired audio data is the target audio data. Such as: and if the target English word is about, acquiring audio data of a standard pronunciation corresponding to about from the English word standard pronunciation database, and acquiring the target audio data about the audio data of the standard pronunciation of about.
And the target English word sending module is used for sending the target English word and the target audio data to the student end host.
And the target English word receiving module of the student end host is used for receiving the target English word and the target audio data.
The hardware device that target english word display module corresponds can be touch-sensitive screen or display screen, and in this embodiment, the hardware device that target english word display module corresponds is the touch-sensitive screen of student end host computer. And the target English word display module is used for displaying the target English word through the touch screen. Then, the touch screen of the student-side host displays the target english word.
Students can see the target English words displayed on the touch screen, and after seeing the target English words, according to the pronunciation mastering condition of the students for the target English words, the students read the target English words and give out the actual pronunciations of the target English words. It should be understood that the actual pronunciation by the student may or may not be a standard pronunciation.
The hardware equipment that actual pronunciation signal acquisition module corresponds can be pronunciation collection equipment such as the microphone of student end host computer, and then the actual pronunciation signal acquisition module of student end host computer is used for obtaining the actual pronunciation signal of the target english word that the student sent through the microphone according to target english word.
The hardware device corresponding to the target standard pronunciation external playing module is an audio external playing device, such as a loudspeaker of a student end host. After the actual pronunciation signal of the target English word is received by the actual pronunciation signal acquisition module of the student host, the target standard pronunciation external playing module is used for externally playing the target audio data through the audio external playing device according to the target audio data and the actual pronunciation signal of the target English word.
The student can hear the standard pronunciation of the target english word through the audio playback device. The student can compare with own actual pronunciation according to standard pronunciation by oneself, judges whether own pronunciation is standard to correct own pronunciation.
And the actual pronunciation signal sending module of the student end host is used for sending the actual pronunciation signal of the target English word to the teacher end host.
And the actual pronunciation signal receiving module of the teacher-side host is used for receiving the actual pronunciation signal of the target English word.
And the noise filtering module of the teacher-side host is used for performing noise filtering on the received actual pronunciation signal of the target English word to obtain a target actual pronunciation signal. The noise filtering algorithm corresponding to the noise filtering module belongs to the existing public noise filtering algorithm, and performs noise filtering on the received actual pronunciation signal of the target English word to filter noise in the actual pronunciation signal, so that the accuracy of subsequent waveform comparison can be improved.
The actual pronunciation waveform generation module is used for processing the target actual pronunciation signal and generating an actual pronunciation waveform corresponding to the target actual pronunciation signal. Since the generation of the corresponding waveform signal from the voice signal belongs to the conventional technology, it is not described in detail.
The standard pronunciation waveform database of english in teacher's host computer stores the standard pronunciation waveform that the english word corresponds, stores the pronunciation waveform that the standard pronunciation of english word corresponds promptly, specifically: the standard pronunciation waveform corresponding to the audio data of the standard pronunciation of each English word is obtained. That is, the english standard pronunciation waveform database includes all english words in the english word database and standard pronunciation waveforms corresponding to the audio data of the standard pronunciation of each english word. It should be understood that, when the english standard pronunciation waveform database is constructed, the audio data of the standard pronunciation of each english word is processed to obtain a corresponding standard pronunciation waveform, and then the corresponding relationship between each english word and the standard pronunciation waveform is established to obtain the english standard pronunciation waveform database.
And the target standard pronunciation waveform acquisition module is used for acquiring a standard pronunciation waveform corresponding to the standard pronunciation of the target English word from the English standard pronunciation waveform database according to the target English word and the actual pronunciation waveform to obtain a target standard pronunciation waveform. That is, after the teacher-side host obtains the actual pronunciation waveform, the target standard pronunciation waveform obtaining module obtains the target standard pronunciation waveform from the English standard pronunciation waveform database according to the target English word.
After the actual pronunciation waveform and the target standard pronunciation waveform are obtained, the waveform comparison module is used for comparing the actual pronunciation waveform with the target standard pronunciation waveform. Waveform comparison belongs to the conventional technology, and can adopt the related comparison algorithm disclosed in the prior art, such as: and generating the two waveforms in the same coordinate system, extracting voice characteristic curves of the two waveforms through a related voice characteristic recognition algorithm, and acquiring the area of an intersection region between the two curves, wherein if the area is greater than or equal to a preset area threshold value, the comparison is not passed, and if the area is less than the preset area threshold value, the comparison is passed. As a specific embodiment, a specific alignment procedure is given below: the method comprises the steps of constructing an actual pronunciation waveform and a target standard pronunciation waveform in the same voice coordinate system, then extracting voice key features of the actual pronunciation waveform according to a preset voice feature recognition algorithm to form a voice key feature vector, wherein the formed voice key feature vector is an actual voice key feature vector, extracting voice key features of the target standard pronunciation waveform to form a voice key feature vector, the formed voice key feature vector is a standard voice key feature vector, and finally comparing the actual voice key feature vector with the standard voice key feature vector to obtain a comparison result. In this embodiment, comparing the actual speech key feature vector with the standard speech key feature vector to obtain a comparison result, specifically including: if the matching degree of the actual voice key feature vector and the standard voice key feature vector is greater than or equal to a preset threshold value, the similarity of the actual voice key feature vector and the standard voice key feature vector is larger, and the comparison result is that the comparison is passed; and if the matching degree of the actual voice key feature vector and the standard voice key feature vector is smaller than a preset threshold value, the comparison result is that the comparison is failed.
The pronunciation result judging module is used for acquiring a judgment result of whether the pronunciation of the target English word is standard or not by the student according to a comparison result of the actual pronunciation waveform and the target standard pronunciation waveform, namely the comparison result output by the waveform comparison module. Specifically, the method comprises the following steps: if the comparison result is that the comparison is passed, judging that the result is the pronunciation standard of the student to the target English word; and if the comparison result is that the comparison is not passed, judging that the pronunciation of the student to the target English word is not standard.
And the judgment result sending module is used for sending the judgment result to the student host.
The judgment result display module of the student end host is used for receiving and displaying the judgment result, for example, displaying the judgment result on a touch screen. The student can know whether the pronunciation of the student is standard or not by seeing the judgment result displayed on the touch screen, and then corrects the pronunciation of the student according to the judgment result.
It should be understood that the above-mentioned embodiment is only a specific implementation procedure of the technical solution claimed in the present application, and the present application is not limited to the above-mentioned embodiment.
Claims (3)
1. An English pronunciation correction system based on big data is characterized by comprising a teacher end host and a student end host;
the teacher end host includes: the system comprises an English pronunciation correction starting instruction receiving module, an English word database, a target English word database acquisition module, a target English word database display module, a target English word determination module, an English word standard pronunciation database, a target English word standard pronunciation acquisition module, a target English word sending module, an actual pronunciation signal receiving module, a noise filtering module, an actual pronunciation waveform generating module, an English standard pronunciation waveform database, a target standard pronunciation waveform acquisition module, a waveform comparison module, a pronunciation result judgment module and a judgment result sending module;
the student end host computer includes: the system comprises an English pronunciation correction starting instruction sending module, a target English word receiving module, a target English word display module, an actual pronunciation signal acquisition module, a target standard pronunciation external playing module, an actual pronunciation signal sending module and a judgment result display module;
the English pronunciation correction starting instruction sending module is used for sending an English pronunciation correction starting instruction to the teacher end host, and the English pronunciation correction starting instruction comprises grade information of a target student;
the English pronunciation correction starting instruction receiving module is used for receiving the English pronunciation correction starting instruction;
the target English word database acquisition module is used for acquiring an English word database corresponding to the grade information of the target student from the English word database according to the grade information of the target student to obtain a target English word database; the English word database comprises at least two English word databases, each English word database corresponds to the grade of a student one by one, and each English word database comprises at least two English words;
the target English word database display module is used for displaying each English word in the target English word database;
the target English word determining module is used for selecting a part of English words from the target English word database to obtain target English words;
the target English word standard pronunciation acquisition module is used for acquiring audio data of standard pronunciation corresponding to the target English word from the English word standard pronunciation database according to the target English word to obtain target audio data; the English word standard pronunciation database comprises each English word in the English word database and audio data of standard pronunciation of each English word;
the target English word sending module is used for sending the target English word and the target audio data to the student end host;
the target English word receiving module is used for receiving the target English word and the target audio data;
the target English word display module is used for displaying the target English word;
the actual pronunciation signal acquisition module is used for acquiring an actual pronunciation signal of the target English word sent by the student according to the target English word;
the target standard pronunciation external playing module is used for externally playing the target audio data through audio external playing equipment according to the target audio data and the actual pronunciation signal of the target English word;
the actual pronunciation signal sending module is used for sending the actual pronunciation signal of the target English word to the teacher-side host;
the actual pronunciation signal receiving module is used for receiving an actual pronunciation signal of the target English word;
the noise filtering module is used for performing noise filtering on the actual pronunciation signal of the target English word to obtain a target actual pronunciation signal;
the actual pronunciation waveform generating module is used for processing the target actual pronunciation signal and generating an actual pronunciation waveform corresponding to the target actual pronunciation signal;
the target standard pronunciation waveform acquisition module is used for acquiring a standard pronunciation waveform of a standard pronunciation corresponding to the target English word from the English standard pronunciation waveform database according to the target English word and the actual pronunciation waveform to obtain a target standard pronunciation waveform; the English standard pronunciation waveform database comprises English words in the English word database and standard pronunciation waveforms corresponding to the English words;
the waveform comparison module is used for comparing the actual pronunciation waveform with the target standard pronunciation waveform;
the pronunciation result judging module is used for acquiring a judgment result of whether the pronunciation of the target English word is standard or not by the student according to the comparison result of the actual pronunciation waveform and the target standard pronunciation waveform;
the judgment result sending module is used for sending the judgment result to the student end host;
and the judgment result display module is used for receiving and displaying the judgment result.
2. The big-data-based english pronunciation correction system of claim 1, wherein the waveform matching module is specifically configured to:
constructing the actual pronunciation waveform and the target standard pronunciation waveform in the same voice coordinate system;
extracting the voice key features of the actual pronunciation waveform according to a preset voice feature recognition algorithm to form a voice key feature vector and obtain an actual voice key feature vector; extracting the voice key features of the target standard pronunciation waveform to form a voice key feature vector to obtain a standard voice key feature vector;
and comparing the actual voice key feature vector with the standard voice key feature vector to obtain a comparison result.
3. The big-data-based english pronunciation correction system according to claim 2, wherein said comparing said actual speech key feature vector with said standard speech key feature vector to obtain a comparison result comprises:
if the matching degree of the actual voice key feature vector and the standard voice key feature vector is greater than or equal to a preset threshold value, the comparison result is that the comparison is passed; if the matching degree of the actual voice key feature vector and the standard voice key feature vector is smaller than the preset threshold, the comparison result is that the comparison is not passed;
correspondingly, the pronunciation result judgment module is specifically configured to: if the comparison result is that the comparison is passed, the judgment result is the pronunciation standard of the student to the target English word; and if the comparison result is that the comparison is not passed, the judgment result is that the pronunciation of the target English word is not standard for the student.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010681307.8A CN111710203A (en) | 2020-07-15 | 2020-07-15 | English pronunciation correction system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010681307.8A CN111710203A (en) | 2020-07-15 | 2020-07-15 | English pronunciation correction system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111710203A true CN111710203A (en) | 2020-09-25 |
Family
ID=72546052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010681307.8A Withdrawn CN111710203A (en) | 2020-07-15 | 2020-07-15 | English pronunciation correction system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111710203A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116206496A (en) * | 2023-01-30 | 2023-06-02 | 齐齐哈尔大学 | Oral english practice analysis compares system based on artificial intelligence |
| CN116340489A (en) * | 2023-03-27 | 2023-06-27 | 齐齐哈尔大学 | Japanese teaching interaction method and device based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2007201394A1 (en) * | 2006-03-30 | 2007-10-18 | Helen Fraser | Method and system for online pronunciation learning |
| CN108109443A (en) * | 2017-12-05 | 2018-06-01 | 郑州大学西亚斯国际学院 | A kind of system for correcting Oral English Practice pronunciation |
| CN110246484A (en) * | 2019-07-19 | 2019-09-17 | 山东劳动职业技术学院 | A kind of intelligence pronunciation of English self-aid learning system |
| CN111078066A (en) * | 2019-05-15 | 2020-04-28 | 广东小天才科技有限公司 | Learning auxiliary method and learning equipment |
| CN111311991A (en) * | 2020-04-24 | 2020-06-19 | 郑州迈拓信息技术有限公司 | Teaching is with word pinyin tone pronunciation correction device based on speech recognition |
-
2020
- 2020-07-15 CN CN202010681307.8A patent/CN111710203A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2007201394A1 (en) * | 2006-03-30 | 2007-10-18 | Helen Fraser | Method and system for online pronunciation learning |
| CN108109443A (en) * | 2017-12-05 | 2018-06-01 | 郑州大学西亚斯国际学院 | A kind of system for correcting Oral English Practice pronunciation |
| CN111078066A (en) * | 2019-05-15 | 2020-04-28 | 广东小天才科技有限公司 | Learning auxiliary method and learning equipment |
| CN110246484A (en) * | 2019-07-19 | 2019-09-17 | 山东劳动职业技术学院 | A kind of intelligence pronunciation of English self-aid learning system |
| CN111311991A (en) * | 2020-04-24 | 2020-06-19 | 郑州迈拓信息技术有限公司 | Teaching is with word pinyin tone pronunciation correction device based on speech recognition |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116206496A (en) * | 2023-01-30 | 2023-06-02 | 齐齐哈尔大学 | Oral english practice analysis compares system based on artificial intelligence |
| CN116206496B (en) * | 2023-01-30 | 2023-08-18 | 齐齐哈尔大学 | Oral english practice analysis compares system based on artificial intelligence |
| CN116340489A (en) * | 2023-03-27 | 2023-06-27 | 齐齐哈尔大学 | Japanese teaching interaction method and device based on big data |
| CN116340489B (en) * | 2023-03-27 | 2023-08-22 | 齐齐哈尔大学 | Japanese teaching interaction method and device based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426362A (en) | Speech Translation Apparatus And Method | |
| KR20010054622A (en) | Method increasing recognition rate in voice recognition system | |
| JP2002116796A (en) | Voice processor and method for voice processing and storage medium | |
| KR101819457B1 (en) | Voice recognition apparatus and system | |
| CN111710203A (en) | English pronunciation correction system based on big data | |
| CN103730032A (en) | Method and system for controlling multimedia data | |
| CN111415537A (en) | Symbol-labeling-based word listening system for primary and secondary school students | |
| CN111311991A (en) | Teaching is with word pinyin tone pronunciation correction device based on speech recognition | |
| CN111312255A (en) | Pronunciation self-correcting device for word and pinyin tones based on voice recognition | |
| CN113591491B (en) | Speech translation text correction system, method, device and equipment | |
| CN111681470A (en) | Artificial intelligence english teaching system | |
| US20070250307A1 (en) | System, method, and computer readable medium thereof for language learning and displaying possible terms | |
| CN111710328A (en) | Method, device and medium for selecting training samples of voice recognition model | |
| CN110890095A (en) | Voice detection method, recommendation method, device, storage medium and electronic equipment | |
| CN105513612A (en) | Audio processing method and device for language vocabulary | |
| CN112434148A (en) | Intelligent robot response method and device based on artificial intelligence | |
| KR100319448B1 (en) | Interactive language tutoring system and method using speed control | |
| JPH1152984A (en) | Recognition object display system in speech recognition device | |
| CN114708125A (en) | Intelligent teaching auxiliary system based on artificial intelligence | |
| JP2022117805A (en) | Pronunciation training program and terminal device | |
| CN112560431A (en) | Method, apparatus, device, storage medium, and computer program product for generating test question tutoring information | |
| CN111353038A (en) | Data display method and device, computer equipment and storage medium | |
| CN111710199A (en) | English teaching system based on big data | |
| JP2014038140A (en) | Language learning assistant device, language learning assistant method and language learning assistant program | |
| JP2000181918A (en) | Multimedia english/japanese dictionary showing meaning/ pronunciation to english word inputted by handwriting |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200925 |
|
| WW01 | Invention patent application withdrawn after publication |