CN114327357A - Language learning auxiliary method, electronic equipment and storage medium - Google Patents
Language learning auxiliary method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114327357A CN114327357A CN202210005436.4A CN202210005436A CN114327357A CN 114327357 A CN114327357 A CN 114327357A CN 202210005436 A CN202210005436 A CN 202210005436A CN 114327357 A CN114327357 A CN 114327357A
- Authority
- CN
- China
- Prior art keywords
- student user
- phonemes
- pronunciation
- key word
- error
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000000463 material Substances 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 210000003928 nasal cavity Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000001260 vocal cord Anatomy 0.000 description 1
Images
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a language learning auxiliary method, electronic equipment and a storage medium. The method comprises the steps of acquiring an error between pronunciation of a key word in an electronic reading by a student user recorded on site and standard pronunciation of the key word; determining the feedback parameters of each student user, and adjusting the current playing speed of speech according to the feedback parameters and the normal speaking speed of the student user at the age stage, so that the intellectualization and the self-adaption of the playing speed of speech when the student user learns the electronic reading are realized, and the manual adjustment of the playing speed of speech and the repeated playing in the learning process are avoided.
Description
Technical Field
The invention belongs to the field of communication, and particularly relates to a language learning auxiliary method, electronic equipment and a storage medium.
Background
At present, in the process of learning according to the electronic reading materials, when the playing speed is too fast or when a student pronounces or pronounces abnormally along with the reading of the electronic reading materials, the playing speed needs to be manually adjusted or the electronic reading materials are continuously played repeatedly, so that a student user can hear clearly, and the user experience is poor. The adjustment of the playing speed in the playing process of the electronic reading is not intelligent, personalized and adaptive enough, and can not adapt to the personalized requirements of users.
Disclosure of Invention
The invention aims to solve the technical problem of providing a language learning auxiliary method, electronic equipment and a storage medium in order to overcome the defects of insufficient intellectualization, individuation and self-adaption in the adjustment of playing speed in the playing process of electronic reading materials in the prior art.
The invention solves the technical problems through the following technical scheme:
the invention provides a language learning auxiliary method, which comprises the following steps:
s1, acquiring the normal speaking speed of the student user at the age stage and the feedback parameters of the student user;
according to the recognized face information of each student user, searching the age stage, the normal speaking speed and the feedback parameters corresponding to the student user from a database; the database stores age and face information corresponding to each student user and a feedback parameter uniquely corresponding to the student, and stores the normal speaking speed of each age stage after training; s2, determining the pushed electronic reading according to the historical information and preference of the student user;
the historical information and the preference comprise completion rate and playing times of listening to the electronic reading materials in a period of time; the pushed electronic readings comprise electronic readings related to the electronic readings with the highest completion rate and the highest playing times;
s3, determining the playing speed of the electronic reading material pushed to the student user according to the normal speaking speed and the feedback parameter;
s4, playing the electronic reading according to the playing speed; judging whether the playing is finished, if so, executing S7;
s5, judging whether the electronic reading material is in the interaction stage of the student user and the electronic reading material, if so, executing S6; if not, returning to S4;
s6, acquiring errors between pronunciations of key words in the electronic reading material and standard pronunciations of the key words by the student user recorded on site after the current interaction stage is finished;
if the error is larger than the preset threshold, the error is used as the latest feedback parameter, and the step returns to S3; if the error is not greater than the preset threshold value, continuing to play the electronic readings, and returning to the step S4;
s7, counting the completion rate of the electronic readings of the student user and displaying the completion rate on the background; and the playing speech speed is equal to the normal speaking speech speed + a, wherein a is a preset coefficient, and the initial value of the feedback parameter is 0.
Preferably, the determining of the error between the pronunciation of the key term by the student user in the electronic reading and the standard pronunciation of the key term comprises: dividing the standard pronunciation of the key word into a plurality of phonemes, and dividing the pronunciation of the student user aiming at the key word into a plurality of phonemes; and comparing errors between the plurality of phonemes of the standard pronunciation of the key words and the plurality of phonemes of the pronunciation of the key words in the electronic reading by the student user, and taking the errors as feedback parameters.
Preferably, comparing the error between the phonemes of the standard pronunciation of the keyword and the phonemes of the pronunciation of the keyword in the electronic reading by the student user comprises: each phoneme uniquely corresponds to one feature vector, an error feature vector is formed according to the error between the feature vector of each phoneme in the multiple phonemes of the standard pronunciation of the key word and the feature vector of each phoneme in the multiple phonemes of the pronunciation of the key word by the student user, a phoneme error matrix of the key word is formed according to the error feature vector, the rank of the error matrix is calculated, and the rank is used as a feedback parameter.
Preferably, comparing the error between the plurality of phonemes of the standard pronunciation of the keyword and the plurality of phonemes of the pronunciation of the keyword by the student user comprises: each phoneme uniquely corresponds to one feature vector, Euclidean distances are obtained between the feature vector of each phoneme in a plurality of phonemes of the standard pronunciation of the key word and the feature vector of each phoneme in a plurality of phonemes of the pronunciation of the key word by a student user, and the average value or the sum value of a plurality of Euclidean distances corresponding to the plurality of phonemes divided by the key word is used as a feedback parameter.
Preferably, before step S1, an offline stage is further included:
dividing a plurality of students into a plurality of age stages according to ages, and collecting speech rate samples of normal speaking of the plurality of students in each age stage;
obtaining the normal speaking speed of each age stage by adopting a clustering algorithm according to the normal speaking speed samples of a plurality of students in each age stage; the clustering algorithm is a K-means algorithm.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the computer program.
The invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the method, the feedback parameters of each student user are determined according to the acquired errors between the pronunciation of the key words in the electronic reading and the standard pronunciation of the key words of the student user, and the playing speed of the electronic reading is adjusted in real time according to the feedback parameters, so that the automatic adjustment of the playing speed of the electronic reading is realized, and the self-adaption and individuation of the playing speed are realized.
Drawings
Fig. 1 is a flowchart of a language learning support method in embodiment 1.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
The present embodiment provides a language learning auxiliary method,
an off-line stage:
dividing a plurality of students into a plurality of age stages according to ages, and collecting speech rate samples of normal speaking of the plurality of students in each age stage;
obtaining the normal speaking speed of each age stage by adopting a clustering algorithm according to the normal speaking speed samples of a plurality of students in each age stage; the clustering algorithm is a K-means algorithm.
An online stage:
s1, acquiring the normal speaking speed of the student user at the age stage and the feedback parameters of the student user;
according to the recognized face information of each student user, searching the age stage, the normal speaking speed and the feedback parameters corresponding to the student user from a database; the database stores age and face information corresponding to each student user and a feedback parameter uniquely corresponding to the student, and stores the normal speaking speed of each age stage after training;
s2, determining the pushed electronic reading according to the historical information and preference of the student user;
the historical information and the preference comprise completion rate and playing times of listening to the electronic reading materials in a period of time; the pushed electronic readings comprise electronic readings related to the electronic readings with the highest completion rate and the highest playing times;
s3, determining the playing speed of the electronic reading material pushed to the student user according to the normal speaking speed and the feedback parameter;
s4, playing the electronic reading according to the playing speed; judging whether the playing is finished, if so, executing S7;
s5, judging whether the electronic reading material is in the interaction stage of the student user and the electronic reading material, if so, executing S6; if not, returning to S4;
s6, acquiring errors between pronunciations of key words in the electronic reading material and standard pronunciations of the key words by the student user recorded on site after the current interaction stage is finished;
phonemes are the smallest units of speech that are divided according to the natural properties of the speech. A phoneme is the smallest unit of speech divided from a timbre perspective. From the physiological point of view, a pronunciation action forms a phoneme. Phonemes are generally described in terms of pronunciation actions. The sounding action of the sound like m is that the upper lip and the lower lip are closed, the vocal cords vibrate, and airflow flows out from the nasal cavity to sound. If [ ma ] contains [ m ] a ] two pronunciation actions, which are two phonemes. The sounds uttered by the same pronunciation action are the same phoneme, and the sounds uttered by different pronunciation actions are different phonemes. For example, in [ ma-mi ], the two [ m ] pronunciations are identical and are identical phonemes, and [ a ] i is different and is different phoneme.
In the embodiment, the standard pronunciation of the key word is divided into a plurality of phonemes, and the pronunciation of the student user for the key word is divided into a plurality of phonemes; and comparing errors between the plurality of phonemes of the standard pronunciation of the key words and the plurality of phonemes of the pronunciation of the key words in the electronic reading by the student user, and taking the errors as feedback parameters.
In this embodiment, each phoneme uniquely corresponds to one feature vector, an error feature vector is formed according to an error between the feature vector of each of the multiple phonemes of the standard pronunciation of the keyword and the feature vector of each of the multiple phonemes of the pronunciation of the keyword by the student user, a phoneme error matrix of the keyword is formed according to the error feature vector, the rank of the error matrix is calculated, and the rank is used as a feedback parameter.
In this embodiment, comparing the errors between the phonemes of the standard pronunciation of the keyword and the phonemes of the pronunciation of the keyword by the student user includes: each phoneme uniquely corresponds to one feature vector, Euclidean distances are obtained between the feature vector of each phoneme in a plurality of phonemes of the standard pronunciation of the key word and the feature vector of each phoneme in a plurality of phonemes of the pronunciation of the key word by a student user, and the average value or the sum value of a plurality of Euclidean distances corresponding to the plurality of phonemes divided by the key word is used as a feedback parameter.
If the error is larger than the preset threshold, the error is used as the latest feedback parameter, and the step returns to S3; if the error is not greater than the preset threshold value, continuing to play the electronic readings, and returning to the step S4;
s7, counting the completion rate of the electronic readings of the student user and displaying the completion rate on the background; and the playing speech speed is equal to the normal speaking speech speed + a, wherein a is a preset coefficient, and the initial value of the feedback parameter is 0.
Example 2
A language learning aid comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method described in embodiment 1 when executing the computer program.
Example 3
The present invention also provides a computer-readable storage medium on which a computer program is stored, which, when being executed by a processor, carries out the steps of the language learning support method described in embodiment 1.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible embodiment, the invention can also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps of implementing the language learning aid described in embodiment 1, when said program product is run on said terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (7)
1. A language learning assistance method is characterized in that:
s1, acquiring the normal speaking speed of the student user at the age stage and the feedback parameters of the student user;
s2, determining the pushed electronic reading according to the historical information and preference of the student user;
s3, determining the playing speed of the electronic reading material pushed to the student user according to the normal speaking speed and the feedback parameter; the playing speech speed is equal to the normal speaking speech speed + a, wherein a is a preset coefficient, and the initial value of the feedback parameter is 0;
s4, playing the electronic reading according to the playing speed; judging whether the playing is finished, if so, executing S7;
s5, judging whether the interaction stage of the student user and the electronic reading material exists, if so, executing S6; if not, returning to S4;
s6, acquiring errors between pronunciations of key words in the electronic reading material and standard pronunciations of the key words by the student user recorded on site after the current interaction stage is finished;
if the error is larger than the preset threshold, the error is used as the latest feedback parameter, and the step returns to S3; if the error is not greater than the preset threshold value, continuing to play the electronic readings, and returning to the step S4;
and S7, counting the completion rate of the electronic readings of the student user and displaying the completion rate in the background.
2. A language learning assistance method according to claim 1 wherein the determination of the error between the pronunciation of a keyword in the electronic reading by the student user and the standard pronunciation of said keyword comprises the steps of: dividing the standard pronunciation of the key word into a plurality of phonemes, and dividing the pronunciation of the student user aiming at the key word into a plurality of phonemes; and comparing errors between the plurality of phonemes of the standard pronunciation of the key words and the plurality of phonemes of the pronunciation of the key words in the electronic reading by the student user, and taking the errors as feedback parameters.
3. The language learning support method of claim 2, wherein comparing errors between the phonemes of the standard pronunciation of the key word and the phonemes of the pronunciation of the key word by the student user in the electronic reading comprises the steps of: each phoneme uniquely corresponds to one feature vector, an error feature vector is formed according to the error between the feature vector of each phoneme in the multiple phonemes of the standard pronunciation of the key word and the feature vector of each phoneme in the multiple phonemes of the pronunciation of the key word by the student user, a phoneme error matrix of the key word is formed according to the error feature vector, the rank of the error matrix is calculated, and the rank is used as a feedback parameter.
4. The language learning support method of claim 2, wherein comparing errors between the phonemes of the standard pronunciation of the keyword and the phonemes of the pronunciation of the keyword by the student user comprises the steps of: each phoneme uniquely corresponds to one feature vector, Euclidean distances are obtained between the feature vector of each phoneme in a plurality of phonemes of the standard pronunciation of the key word and the feature vector of each phoneme in a plurality of phonemes of the pronunciation of the key word by a student user, and the average value or the sum value of a plurality of Euclidean distances corresponding to the plurality of phonemes divided by the key word is used as a feedback parameter.
5. The language learning support method according to claim 1, further comprising, before step S1, the steps of:
dividing a plurality of students into a plurality of age stages according to ages, and collecting speech rate samples of normal speaking of the plurality of students in each age stage;
obtaining the normal speaking speed of each age stage by adopting a clustering algorithm according to the normal speaking speed samples of a plurality of students in each age stage; the clustering algorithm is a K-means algorithm.
6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the language learning support method of any one of claims 1-5 when executing the computer program.
7. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the language learning support method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210005436.4A CN114327357B (en) | 2022-01-05 | 2022-01-05 | Language learning assisting method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210005436.4A CN114327357B (en) | 2022-01-05 | 2022-01-05 | Language learning assisting method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114327357A true CN114327357A (en) | 2022-04-12 |
| CN114327357B CN114327357B (en) | 2024-02-02 |
Family
ID=81025638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210005436.4A Active CN114327357B (en) | 2022-01-05 | 2022-01-05 | Language learning assisting method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114327357B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1787070A (en) * | 2005-12-09 | 2006-06-14 | 北京凌声芯语音科技有限公司 | Chip upper system for language learner |
| CN107945788A (en) * | 2017-11-27 | 2018-04-20 | 桂林电子科技大学 | A kind of relevant Oral English Practice pronunciation error detection of text and quality score method |
| CN108961868A (en) * | 2018-08-14 | 2018-12-07 | 徐州工业职业技术学院 | A kind of College English sound word auxiliary memory device |
| CN110085261A (en) * | 2019-05-16 | 2019-08-02 | 上海流利说信息技术有限公司 | A kind of pronunciation correction method, apparatus, equipment and computer readable storage medium |
| CN112233649A (en) * | 2020-10-15 | 2021-01-15 | 安徽听见科技有限公司 | Method, device and equipment for dynamically synthesizing machine simultaneous interpretation output audio |
-
2022
- 2022-01-05 CN CN202210005436.4A patent/CN114327357B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1787070A (en) * | 2005-12-09 | 2006-06-14 | 北京凌声芯语音科技有限公司 | Chip upper system for language learner |
| CN107945788A (en) * | 2017-11-27 | 2018-04-20 | 桂林电子科技大学 | A kind of relevant Oral English Practice pronunciation error detection of text and quality score method |
| CN108961868A (en) * | 2018-08-14 | 2018-12-07 | 徐州工业职业技术学院 | A kind of College English sound word auxiliary memory device |
| CN110085261A (en) * | 2019-05-16 | 2019-08-02 | 上海流利说信息技术有限公司 | A kind of pronunciation correction method, apparatus, equipment and computer readable storage medium |
| CN112233649A (en) * | 2020-10-15 | 2021-01-15 | 安徽听见科技有限公司 | Method, device and equipment for dynamically synthesizing machine simultaneous interpretation output audio |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114327357B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1557822B1 (en) | Automatic speech recognition adaptation using user corrections | |
| CN106531185B (en) | voice evaluation method and system based on voice similarity | |
| CN101105939B (en) | Sonification guiding method | |
| JP3520022B2 (en) | Foreign language learning device, foreign language learning method and medium | |
| CN106463113A (en) | Predicting pronunciation in speech recognition | |
| US20170076715A1 (en) | Training apparatus for speech synthesis, speech synthesis apparatus and training method for training apparatus | |
| US10832668B1 (en) | Dynamic speech processing | |
| JP2007249212A (en) | Method, computer program and processor for text speech synthesis | |
| JPH05341797A (en) | Device and method for contex-dependent type speech recognition | |
| CN111524534A (en) | Voice analysis method, system, device and storage medium | |
| US10515637B1 (en) | Dynamic speech processing | |
| US10930264B2 (en) | Voice quality preference learning device, voice quality preference learning method, and computer program product | |
| KR100362292B1 (en) | Method and system for english pronunciation study based on speech recognition technology | |
| JP7376071B2 (en) | Computer program, pronunciation learning support method, and pronunciation learning support device | |
| CN114327357B (en) | Language learning assisting method, electronic equipment and storage medium | |
| CN107910005A (en) | The target service localization method and device of interaction text | |
| JP5914119B2 (en) | Acoustic model performance evaluation apparatus, method and program | |
| Siegler | Measuring and compensating for the effects of speech rate in large vocabulary continuous speech recognition | |
| CN111078937B (en) | Voice information retrieval method, device, equipment and computer readable storage medium | |
| CN110164414B (en) | Voice processing method and device and intelligent equipment | |
| Mizera et al. | Impact of irregular pronunciation on phonetic segmentation of nijmegen corpus of casual czech | |
| CN114783412B (en) | Spanish spoken language pronunciation training correction method and system | |
| JP2005241767A (en) | Speech recognition device | |
| JP6903613B2 (en) | Speech recognition device, speech recognition method and program | |
| US20230260502A1 (en) | Voice adaptation using synthetic speech processing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |