CN106653055A - On-line oral English evaluating system - Google Patents
On-line oral English evaluating system Download PDFInfo
- Publication number
- CN106653055A CN106653055A CN201610912307.8A CN201610912307A CN106653055A CN 106653055 A CN106653055 A CN 106653055A CN 201610912307 A CN201610912307 A CN 201610912307A CN 106653055 A CN106653055 A CN 106653055A
- Authority
- CN
- China
- Prior art keywords
- module
- audio frequency
- time
- section
- frequency
- 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
- 238000010801 machine learning Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 34
- 238000013507 mapping Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000006116 polymerization reaction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract 2
- 238000007781 pre-processing Methods 0.000 abstract 2
- 238000012935 Averaging Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- 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
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (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 the field of education automation, and in particular relates to an on-line oral English evaluating system. The on-line oral English evaluating system comprises a voice preprocessing module, a convolution neural network analyzing module, and an assessment and feedback module, wherein the voice preprocessing module is used for randomly segmenting an oral English audio file to be evaluated into slices with equal length; the convolution neural network analyzing module is used for carrying out the short-time Fourier transform on the obtained audio slices so that corresponding two-dimensional time-frequency graphs are generated, and then carrying out high-level abstraction on the two-dimensional time-frequency graphs one by one so that the high-level abstraction characteristics of the audio slices are obtained; the assessment and feedback module is used for analyzing the high-level abstraction characteristics of the audio slices one by one through a machine learning model so that the score of each audio slice is obtained, and then averaging all the scores so that the final oral English evaluating score is obtained.
Description
Technical field
The present invention relates to education automation field, and in particular to a kind of online English speaking assessment system.
Background technology
The product of spoken on-line testing has been occurred in that in the market, but the employing at present of these products is all such as lower section
Method：Student's spoken audio is identified as into text first with speech recognition technology, then the text to recognizing carries out signature analysis, most
Provide student's spoken language assessment result with machine learning algorithm afterwards.The method greatest problem is from speech recognition period and follow-up
The signature analysis stage.First, high-precision English Phonetics identification engine R＆D costs are expensive, at present only similar Google, IBM it
The large-scale scientific ＆ technical corporation of class or research unit just possess.Secondly, the result of speech recognition determine it is follow-up all, but current English
Language speech recognition technology simply has enough accuracys rate in the speech recognition of pronunciation standard, and in the not accurate enough English that pronounces
It is also undesirable in beginner's (such as Chinese learners) speech recognition.Finally, the signature analysis stage need Oral English Practice to teach
The expert for learning examination field carrys out design feature, and this can also consume many manpower and materials, and effect is bad.
The content of the invention
Goal of the invention：The present invention makes improvement for the problem that above-mentioned prior art is present, i.e., the invention discloses online
English speaking assessment system, it is not using English Phonetics technology of identification and is being independent of Oral English Practice field teaching examination expert's
In the case of, the assessment to learner's Oral English Practice and marking are realized, reach accurate with the assessment of existing method same level even more high
True property and robustness.
Technical scheme：Online English speaking assessment system, including with lower module：
Voice pretreatment module, for by Oral English Practice audio file random division to be evaluated be equal length section；
Convolutional neural networks analysis module, the audio frequency section to obtaining carries out Short Time Fourier Transform and generates corresponding two dimension
Time-frequency figure, then one by one high-level abstractions are carried out to two-dimentional time-frequency figure, obtain the high-level abstractions feature of audio frequency section；
Assessment and feedback module, are analyzed one by one by machine learning model to the high-level abstractions feature of audio frequency section
To the fraction of each audio frequency section, then all scores are taken the mean obtain final English speaking assessment fraction.
Further, random audio section when a length of 5 seconds.
Further, voice pretreatment module includes with lower module,
Speech analysis module is then right for being equal length section by Oral English Practice audio file random division to be evaluated
All of audio frequency section carries out preemphasis, voice framing, adding window and end-point detection；
Voice signal processing module, for the section of all audio frequency, is sequentially completed time-domain analysis, frequency-domain analysis and cepstrum domain point
Analysis；
Parameters,acoustic analysis module, is analyzed and calculates to the parameters,acoustic of audio frequency section, and parameters,acoustic includes MEL frequencies
Rate cepstrum coefficient, linear prediction residue error and Line Spectral Pair coefficients；
Further, voice signal processing module is included with lower module：
Time-domain analysis module, the time domain charactreristic parameter in analysis and extraction audio frequency section；
Frequency-domain analysis module, by bandpass filter group method, Short Time Fourier Transform method, frequency domain Pitch detection, when-frequency
Method for expressing, extracts frequency spectrum, power spectrum, cepstrum, the spectrum envelope of audio frequency section；
Cepstrum domain analyzing module, analyzes and extracts the cepstral domain feature parameter of audio frequency section, further by Homomorphic Processing
Glottal excitation information and sound channel response message are effectively separated：Glottal excitation information be used for judge pure and impure sound, seek pitch period,
Sound channel response message is used to seek formant, for the coding of voice, synthesis, identification.
Further, time domain charactreristic parameter includes short-time energy and short-time average magnitude, short-time average zero-crossing rate, in short-term
Auto-correlation coefficient and short-time average magnitade difference function.
Further, convolutional neural networks analysis module includes with lower module,
Input module, by audio frequency section the two-dimentional time-frequency figure of some same scales is changed into；
Convolutional layer C1, the two-dimentional time-frequency figure that input module is obtained is rolled up by trainable wave filter and Ke Jia biasings
Product, has obtained the local feature of two-dimentional time-frequency figure；
Feature Mapping figure S2, the local feature of the two-dimentional time-frequency figure extracted to convolutional layer C1 is sampled, weighted value, plus
Bias to calculate image-region special characteristic maximum, characteristics of image is polymerized and is mapped；
Convolutional layer C3, the convolutional calculation for carrying out again by the characteristics of image that Feature Mapping figure S2 is obtained, obtains image
Low-dimensional local feature；
Feature Mapping figure S4, samples to the characteristics of image that convolutional layer C3 is extracted, weighted value, plus biases to calculate image
Region special characteristic mean value, completes the final polymerization to characteristics of image and mapping；
Output module, by the parameters,acoustic of each audio frequency section and the characteristics of image after Feature Mapping figure S4 process
After combination, exported as the global feature of audio frequency section.
Beneficial effect：Online English speaking assessment system disclosed by the invention has the advantages that：
1st, low cost, without the need for relying on speech recognition technology, without the need for organizing Oral English Teaching examination in terms of expert carry out
Characteristic Design；
2nd, strong robustness, without the need for relying on voice identification result, the spoken assessment to non-native English speaker personage also has high precision
Rate；
3rd, extensibility is strong, as the accumulation of data can constantly carry out self-teaching, effect in the case of mass data
It is splendid.
Description of the drawings
Fig. 1 is the schematic diagram of convolutional neural networks analysis module.
Specific embodiment：
The specific embodiment of the present invention is described in detail below.
Online English speaking assessment system, including with lower module：
Voice pretreatment module, for by Oral English Practice audio file random division to be evaluated be equal length section；
Convolutional neural networks analysis module, the audio frequency section to obtaining carries out Short Time Fourier Transform and generates corresponding two dimension
Time-frequency figure, then one by one high-level abstractions are carried out to two-dimentional time-frequency figure, obtain the high-level abstractions feature of audio frequency section；
Assessment and feedback module, are analyzed one by one by machine learning model to the high-level abstractions feature of audio frequency section
To the fraction of each audio frequency section, then all scores are taken the mean obtain final English speaking assessment fraction.
Further, random audio section when a length of 5 seconds.
Further, voice pretreatment module includes with lower module,
Speech analysis module is then right for being equal length section by Oral English Practice audio file random division to be evaluated
All of audio frequency section carries out preemphasis, voice framing, adding window and end-point detection；
Voice signal processing module, for the section of all audio frequency, is sequentially completed time-domain analysis, frequency-domain analysis and cepstrum domain point
Analysis；
Parameters,acoustic analysis module, is analyzed and calculates to the parameters,acoustic of audio frequency section, and parameters,acoustic includes MEL frequencies
Rate cepstrum coefficient, linear prediction residue error and Line Spectral Pair coefficients；
Further, voice signal processing module is included with lower module：
Time-domain analysis module, the time domain charactreristic parameter in analysis and extraction audio frequency section；
Frequency-domain analysis module, by bandpass filter group method, Short Time Fourier Transform method, frequency domain Pitch detection, when-frequency
Method for expressing, extracts frequency spectrum, power spectrum, cepstrum, the spectrum envelope of audio frequency section；
Cepstrum domain analyzing module, analyzes and extracts the cepstral domain feature parameter of audio frequency section, further by Homomorphic Processing
Glottal excitation information and sound channel response message are effectively separated：Glottal excitation information be used for judge pure and impure sound, seek pitch period,
Sound channel response message is used to seek formant, for the coding of voice, synthesis, identification.
Further, time domain charactreristic parameter includes short-time energy and short-time average magnitude, short-time average zero-crossing rate, in short-term
Auto-correlation coefficient and short-time average magnitade difference function.
Further, as shown in figure 1, convolutional neural networks analysis module is included with lower module,
Input module, by audio frequency section the two-dimentional time-frequency figure of some same scales is changed into；
Convolutional layer C1, the two-dimentional time-frequency figure that input module is obtained is rolled up by trainable wave filter and Ke Jia biasings
Product, has obtained the local feature of two-dimentional time-frequency figure；
Feature Mapping figure S2, the local feature of the two-dimentional time-frequency figure extracted to convolutional layer C1 is sampled, weighted value, plus
Bias to calculate image-region special characteristic maximum, characteristics of image is polymerized and is mapped；
Convolutional layer C3, the convolutional calculation for carrying out again by the characteristics of image that Feature Mapping figure S2 is obtained, obtains image
Low-dimensional local feature；
Feature Mapping figure S4, samples to the characteristics of image that convolutional layer C3 is extracted, weighted value, plus biases to calculate image
Region special characteristic mean value, completes the final polymerization to characteristics of image and mapping；
Output module, by the parameters,acoustic of each audio frequency section and the characteristics of image after Feature Mapping figure S4 process
After combination, exported as the global feature of audio frequency section.
Embodiments of the present invention are elaborated above.But the present invention is not limited to above-mentioned embodiment,
In the ken that art those of ordinary skill possesses, can be doing on the premise of without departing from present inventive concept
Go out various change.
Claims (6)
1. online English speaking assessment system, it is characterised in that include with lower module：
Voice pretreatment module, for by Oral English Practice audio file random division to be evaluated be equal length section；
Convolutional neural networks analysis module, the audio frequency section to obtaining carries out Short Time Fourier Transform and generates corresponding two-dimentional time-frequency
Figure, then one by one high-level abstractions are carried out to two-dimentional time-frequency figure, obtain the high-level abstractions feature of audio frequency section；
Assessment and feedback module, are analyzed one by one to the high-level abstractions feature of audio frequency section by machine learning model and obtain every
The fraction of individual audio frequency section, then all scores are taken the mean obtain final English speaking assessment fraction.
2. online English speaking assessment system according to claim 1, it is characterised in that random audio section when it is a length of
5 seconds.
3. online English speaking assessment system according to claim 1, it is characterised in that voice pretreatment module include with
Lower module,
Speech analysis module, for being equal length section by Oral English Practice audio file random division to be evaluated, then to all
Audio frequency section carry out preemphasis, voice framing, adding window and end-point detection；
Voice signal processing module, for the section of all audio frequency, is sequentially completed time-domain analysis, frequency-domain analysis and cepstrum domain analysis；
Parameters,acoustic analysis module, is analyzed and calculates to the parameters,acoustic of audio frequency section, and parameters,acoustic falls including MEL frequencies
Spectral coefficient, linear prediction residue error and Line Spectral Pair coefficients.
4. online English speaking assessment system according to claim 3, it is characterised in that voice signal processing module includes
With lower module：
Time-domain analysis module, the time domain charactreristic parameter in analysis and extraction audio frequency section；
Frequency-domain analysis module, by bandpass filter group method, Short Time Fourier Transform method, frequency domain Pitch detection, when-frequency represent
Method, extracts frequency spectrum, power spectrum, cepstrum, the spectrum envelope of audio frequency section；
Cepstrum domain analyzing module, analyzes and extracts the cepstral domain feature parameter of audio frequency section, further by sound by Homomorphic Processing
Door excitation information and sound channel response message effectively separate：Glottal excitation information be used for judge pure and impure sound, seek pitch period, sound channel
Response message is used to seek formant, for the coding of voice, synthesis, identification.
5. online English speaking assessment system according to claim 4, it is characterised in that time domain charactreristic parameter is included in short-term
Energy and short-time average magnitude, in short-term short-time average zero-crossing rate, auto-correlation coefficient and short-time average magnitade difference function.
6. online English speaking assessment system according to claim 1, it is characterised in that convolutional neural networks analysis module
Including with lower module,
Input module, by audio frequency section the two-dimentional time-frequency figure of some same scales is changed into；
Convolutional layer C1, the two-dimentional time-frequency figure that input module is obtained carries out convolution by trainable wave filter and Ke Jia biasings,
The local feature of two-dimentional time-frequency figure is obtained；
Feature Mapping figure S2, the local feature of the two-dimentional time-frequency figure extracted to convolutional layer C1 is sampled, weighted value, plus biasing
To calculate image-region special characteristic maximum, characteristics of image is polymerized and is mapped；
Convolutional layer C3, the convolutional calculation for carrying out again by the characteristics of image that Feature Mapping figure S2 is obtained, obtains the low-dimensional of image
Local feature；
Feature Mapping figure S4, samples to the characteristics of image that convolutional layer C3 is extracted, weighted value, plus biases to calculate image district
Domain special characteristic mean value, completes the final polymerization to characteristics of image and mapping；
Output module, by the parameters,acoustic of each audio frequency section and the image characteristic combination after Feature Mapping figure S4 process
Afterwards, exported as the global feature of audio frequency section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610912307.8A CN106653055A (en) | 2016-10-20 | 2016-10-20 | On-line oral English evaluating system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610912307.8A CN106653055A (en) | 2016-10-20 | 2016-10-20 | On-line oral English evaluating system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106653055A true CN106653055A (en) | 2017-05-10 |
Family
ID=58856223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610912307.8A Pending CN106653055A (en) | 2016-10-20 | 2016-10-20 | On-line oral English evaluating system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106653055A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107039049A (en) * | 2017-05-27 | 2017-08-11 | 郑州仁峰软件开发有限公司 | A kind of data assessment educational system |
| CN107886968A (en) * | 2017-12-28 | 2018-04-06 | 广州讯飞易听说网络科技有限公司 | Speech evaluating method and system |
| CN108364661A (en) * | 2017-12-15 | 2018-08-03 | 海尔优家智能科技（北京）有限公司 | Visualize speech performance appraisal procedure, device, computer equipment and storage medium |
| CN112133312A (en) * | 2020-09-24 | 2020-12-25 | 上海松鼠课堂人工智能科技有限公司 | Spoken language training method and system based on deep learning |
| CN113112990A (en) * | 2021-03-04 | 2021-07-13 | 昆明理工大学 | Language identification method of variable-duration voice based on spectrum envelope diagram |
| CN114571472A (en) * | 2020-12-01 | 2022-06-03 | 北京小米移动软件有限公司 | Ground attribute detection method and driving method for foot type robot and device thereof |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101494049A (en) * | 2009-03-11 | 2009-07-29 | 北京邮电大学 | Method for extracting audio characteristic parameter of audio monitoring system |
| CN101739868A (en) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | Automatic evaluation and diagnosis method of text reading level for oral test |
| CN101826263A (en) * | 2009-03-04 | 2010-09-08 | 中国科学院自动化研究所 | Objective standard based automatic oral evaluation system |
| CN103065626A (en) * | 2012-12-20 | 2013-04-24 | 中国科学院声学研究所 | Automatic grading method and automatic grading equipment for read questions in test of spoken English |
| CN103617799A (en) * | 2013-11-28 | 2014-03-05 | 广东外语外贸大学 | Method for detecting English statement pronunciation quality suitable for mobile device |
| CN104732977A (en) * | 2015-03-09 | 2015-06-24 | 广东外语外贸大学 | On-line spoken language pronunciation quality evaluation method and system |
| CN104992705A (en) * | 2015-05-20 | 2015-10-21 | 普强信息技术（北京）有限公司 | English oral automatic grading method and system |
| CN105825852A (en) * | 2016-05-23 | 2016-08-03 | 渤海大学 | Oral English reading test scoring method |
-
2016
- 2016-10-20 CN CN201610912307.8A patent/CN106653055A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739868A (en) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | Automatic evaluation and diagnosis method of text reading level for oral test |
| CN101826263A (en) * | 2009-03-04 | 2010-09-08 | 中国科学院自动化研究所 | Objective standard based automatic oral evaluation system |
| CN101494049A (en) * | 2009-03-11 | 2009-07-29 | 北京邮电大学 | Method for extracting audio characteristic parameter of audio monitoring system |
| CN103065626A (en) * | 2012-12-20 | 2013-04-24 | 中国科学院声学研究所 | Automatic grading method and automatic grading equipment for read questions in test of spoken English |
| CN103617799A (en) * | 2013-11-28 | 2014-03-05 | 广东外语外贸大学 | Method for detecting English statement pronunciation quality suitable for mobile device |
| CN104732977A (en) * | 2015-03-09 | 2015-06-24 | 广东外语外贸大学 | On-line spoken language pronunciation quality evaluation method and system |
| CN104992705A (en) * | 2015-05-20 | 2015-10-21 | 普强信息技术（北京）有限公司 | English oral automatic grading method and system |
| CN105825852A (en) * | 2016-05-23 | 2016-08-03 | 渤海大学 | Oral English reading test scoring method |
Non-Patent Citations (2)
| Title |
|---|
| 王乃峰: ""基于深层神经网络的音频特征提取及场景识别研究"", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 王玉林: ""英语口语评分系统的研究与设计"", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107039049A (en) * | 2017-05-27 | 2017-08-11 | 郑州仁峰软件开发有限公司 | A kind of data assessment educational system |
| CN108364661A (en) * | 2017-12-15 | 2018-08-03 | 海尔优家智能科技（北京）有限公司 | Visualize speech performance appraisal procedure, device, computer equipment and storage medium |
| CN107886968A (en) * | 2017-12-28 | 2018-04-06 | 广州讯飞易听说网络科技有限公司 | Speech evaluating method and system |
| CN112133312A (en) * | 2020-09-24 | 2020-12-25 | 上海松鼠课堂人工智能科技有限公司 | Spoken language training method and system based on deep learning |
| CN114571472A (en) * | 2020-12-01 | 2022-06-03 | 北京小米移动软件有限公司 | Ground attribute detection method and driving method for foot type robot and device thereof |
| CN114571472B (en) * | 2020-12-01 | 2024-01-23 | 北京小米机器人技术有限公司 | Ground attribute detection method and driving method for foot robot and device thereof |
| CN113112990A (en) * | 2021-03-04 | 2021-07-13 | 昆明理工大学 | Language identification method of variable-duration voice based on spectrum envelope diagram |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106653055A (en) | On-line oral English evaluating system | |
| CN103559892B (en) | Oral evaluation method and system | |
| US9489864B2 (en) | Systems and methods for an automated pronunciation assessment system for similar vowel pairs | |
| CN104732977A (en) | On-line spoken language pronunciation quality evaluation method and system | |
| CN114373447A (en) | A method and system for scoring Chinese-English translation questions | |
| CN105608960A (en) | Spoken language formative teaching method and system based on multi-parameter analysis | |
| Liu et al. | AI recognition method of pronunciation errors in oral English speech with the help of big data for personalized learning | |
| Ibrahim et al. | Quranic verse recitation feature extraction using Mel-frequency cepstral coefficients (MFCC) | |
| Shufang | Design of an automatic English pronunciation error correction system based on radio magnetic pronunciation recording devices | |
| Dave et al. | Speech recognition: A review | |
| Yousfi et al. | Holy Qur'an speech recognition system Imaalah checking rule for warsh recitation | |
| CN111341346A (en) | Language expression capability evaluation method and system for fusion depth language generation model | |
| Alkhatib et al. | Building an assistant mobile application for teaching arabic pronunciation using a new approach for arabic speech recognition | |
| KR20080018658A (en) | Voice comparison system for user selection section | |
| Yousfi et al. | Isolated Iqlab checking rules based on speech recognition system | |
| CN116543760A (en) | Oral English teaching evaluation method based on artificial intelligence | |
| Adam et al. | Analysis of Momentous Fragmentary Formants in Talaqi-like Neoteric Assessment of Quran Recitation using MFCC Miniature Features of Quranic Syllables | |
| Jing et al. | The speech evaluation method of English phoneme mobile learning system | |
| Li et al. | English sentence pronunciation evaluation using rhythm and intonation | |
| Bhadra et al. | Study on feature extraction of speech emotion recognition | |
| CN117423260B (en) | Auxiliary teaching method based on classroom speech recognition and related equipment | |
| Bansod et al. | Speaker Recognition using Marathi (Varhadi) Language | |
| RU2589851C2 (en) | System and method of converting voice signal into transcript presentation with metadata | |
| Hassan et al. | Pattern Classification in Recognising Idgham Maal Ghunnah Pronunciation Using Multilayer Perceptrons | |
| Ma et al. | Optimization of Computer Aided English Pronunciation Teaching System Based on Speech Signal Processing Technology. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |