CN110164422A - A kind of the various dimensions appraisal procedure and device of speaking test - Google Patents
A kind of the various dimensions appraisal procedure and device of speaking test Download PDFInfo
- Publication number
- CN110164422A CN110164422A CN201910266709.9A CN201910266709A CN110164422A CN 110164422 A CN110164422 A CN 110164422A CN 201910266709 A CN201910266709 A CN 201910266709A CN 110164422 A CN110164422 A CN 110164422A
- Authority
- CN
- China
- Prior art keywords
- dimension
- dimensions
- content
- score value
- spoken
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012360 testing method Methods 0.000 title claims abstract description 17
- 230000000875 corresponding effect Effects 0.000 description 42
- 230000007812 deficiency Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- 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
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
-
- 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
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention relates to the various dimensions appraisal procedures and device of a kind of speaking test, which comprises obtains the spoken of examinee and answers result;Determine that, to the spoken dimensions for answering result, the dimensions include at least content dimension, pronunciation dimension, grammer dimension and fluency;Based on the dimensions, dimension score value corresponding with the dimensions is obtained;Based on each dimension score value, the spoken comprehensive grading value for answering result is determined;Based on the comprehensive grading value and each dimension score value, the assessment result to the examinee is determined.The present invention simultaneously can assess spoken answer of examinee based on multiple and different dimensions, can also be further formed comprehensive grading value and assess on the whole.
Description
Technical field
The present invention relates to field of computer technology, more particularly to the various dimensions appraisal procedure and dress of a kind of speaking test
It sets.
Background technique
As the important medium of interpersonal communication, conversational language occupies extremely important status in real life.With society
The progress of continuous development and economical globalization tendency that can be economic, people are objective to the efficiency of language learning and language assessment
Property, fairness and scale test propose increasingly higher demands.For example oral composition of Open-ended Question type in speaking test, story
Repetition and picture talk etc. are to reflect an important topic type of the ability to express of examinee's spoken language.The expression content of examinee can be investigated
Integrality, smooth degree, pronounce accuracy and the correctness of grammer etc..
Traditional speaking test points-scoring system is directly to learn Rating Model according to the total score labeled data of teacher's marking, is given
A total score output out.And be weak in terms of which in oral expression of student and do not provide, such as pronounce whether accurate, grammer
It is whether problematic, whether content complete etc., therefore, the level of aggregation of examinee cannot be all presented in individual total score.
Summary of the invention
Based on this, it is necessary to for traditional scheme scoring feedback unstructured problem, provide a kind of various dimensions of speaking test
Appraisal procedure and device
A kind of various dimensions appraisal procedure of speaking test, which comprises
It obtains the spoken of examinee and answers result;
Determine that, to the spoken dimensions for answering result, the dimensions include at least content dimension, pronunciation dimension
Degree, grammer dimension and fluency;
Based on the dimensions, dimension score value corresponding with the dimensions is obtained;
Based on each dimension score value, the spoken comprehensive grading value for answering result is determined;
Based on the comprehensive grading value and each dimension score value, the assessment result to the examinee is determined.
Preferably, described to be based on the dimensions if the dimensions include content dimension, obtain with it is described
The corresponding dimension score value of dimensions, comprising:
Obtain the spoken content of text for answering result;
Determine the integrity degree coefficient between the content of text and preset reference answer;
Corresponding content dimension score value is determined based on the integrity degree coefficient.
Preferably, described to be based on the dimensions if the dimensions include pronunciation dimension, obtain with it is described
The corresponding dimension score value of dimensions, comprising:
The spoken pronunciation character answered in result is extracted based on the acoustic model that standard pronunciation is formed;
Based on the standard pronunciation, accuracy of the pronunciation character relative to the standard pronunciation is determined;
Corresponding pronunciation dimension score value is determined based on the accuracy.
Preferably, described to be based on the dimensions if the dimensions include grammer dimension, obtain with it is described
The corresponding dimension score value of dimensions, comprising:
Obtain the spoken content of text for answering result;
Punctuate is carried out to the content of text and obtains target sentences text;
Obtain the grammar property in the target sentences text;
Preset prediction model will be input to as parameter to each grammar property, and exported by the prediction model
Corresponding grammer dimension score value.
Preferably, described to be based on the dimensions if the dimensions include fluency, it obtains and institute's commentary
The corresponding dimension score value of fractional dimension, comprising:
Obtain the spoken content of text for answering result;
Determine the time serial message of respective word in the content of text;
Characteristic value corresponding with each time serial message is generated based on the time serial message;
Characteristic value corresponding with each time serial message is input to preset fluency model, and by described
Fluency model exports corresponding fluency score value.
A kind of various dimensions assessment device of speaking test, described device include:
First obtains module, answers result for obtaining the spoken of examinee;
First determining module, for determining that, to the spoken dimensions for answering result, the dimensions at least wrap
Include content dimension, pronunciation dimension, grammer dimension and fluency;
Second obtains module, for being based on the dimensions, obtains dimension scoring corresponding with the dimensions
Value;
Second determining module determines that the spoken synthesis for answering result is commented for being based on each dimension score value
Score value;
Third determining module, for being based on the comprehensive grading value and each dimension score value, determination is examined described
Raw assessment result.
Preferably, if the dimensions include content dimension, the second acquisition module is used for:
Obtain the spoken content of text for answering result;
Determine the integrity degree coefficient between the content of text and preset reference answer;
Corresponding content dimension score value is determined based on the integrity degree coefficient.
Preferably, if the dimensions include pronunciation dimension, the second acquisition module is used for:
The spoken pronunciation character answered in result is extracted based on the acoustic model that standard pronunciation is formed;
Based on the standard pronunciation, accuracy of the pronunciation character relative to the standard pronunciation is determined;
Corresponding pronunciation dimension score value is determined based on the accuracy.
Preferably, if the dimensions include grammer dimension, the second acquisition module is used for:
Obtain the spoken content of text for answering result;
Punctuate is carried out to the content of text and obtains target sentences text;
Obtain the grammar property in the target sentences text;
Preset prediction model will be input to as parameter to each grammar property, and exported by the prediction model
Corresponding grammer dimension score value.
Preferably, if the dimensions include fluency, the second acquisition module is used for:
Obtain the spoken content of text for answering result;
Determine the time serial message of respective word in the content of text;
Characteristic value corresponding with each time serial message is generated based on the time serial message;
Characteristic value corresponding with each time serial message is input to preset fluency model, and by described
Fluency model exports corresponding fluency score value.
In the present invention, obtains the spoken of examinee and answer result;It determines to the spoken dimensions for answering result, it is described
Dimensions include at least content dimension, pronunciation dimension, grammer dimension and fluency;Based on the dimensions, acquisition and institute
The corresponding dimension score value of commentary fractional dimension;Based on each dimension score value, the comprehensive of the spoken answer result is determined
Close score value;Based on the comprehensive grading value and each dimension score value, the assessment result to the examinee is determined.By
This, the present invention simultaneously can assess spoken answer of examinee based on multiple and different dimensions, can also be further formed comprehensive
Score value is closed to assess on the whole;In this way, the advantages of each student can directly know oneself and deficiency, timely improve oneself
Study plan;The relatively direct scheme for providing total score, it is explanatory stronger, relatively more objective to score.
Detailed description of the invention
Fig. 1 is the flow chart of the various dimensions appraisal procedure of the speaking test of an embodiment;
Fig. 2 is that the various dimensions of the speaking test of an embodiment assess the structure chart of device.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the flow chart of the various dimensions appraisal procedure of the speaking test of an embodiment.As shown in Figure 1, this method comprises:
Step 110, it obtains the spoken of examinee and answers result;
Step 120, it determines to the spoken dimensions for answering result, dimensions include at least content dimension, pronunciation dimension
Degree, grammer dimension and fluency;
Step 130, dimensions are based on, dimension score value corresponding with dimensions is obtained;
Step 140, it is based on each dimension score value, determines the spoken comprehensive grading value for answering result;
Step 150, it is based on comprehensive grading value and each dimension score value, determines the assessment result to examinee.
In the present invention, obtains the spoken of examinee and answer result;It determines to the spoken dimensions for answering result, it is described
Dimensions include at least content dimension, pronunciation dimension, grammer dimension and fluency;Based on the dimensions, acquisition and institute
The corresponding dimension score value of commentary fractional dimension;Based on each dimension score value, the comprehensive of the spoken answer result is determined
Close score value;Based on the comprehensive grading value and each dimension score value, the assessment result to the examinee is determined.By
This, the present invention simultaneously can assess spoken answer of examinee based on multiple and different dimensions, can also be further formed comprehensive
Score value is closed to assess on the whole;In this way, the advantages of each student can directly know oneself and deficiency, timely improve oneself
Study plan;The relatively direct scheme for providing total score, it is explanatory stronger, relatively more objective to score.
In the present embodiment, when examinee's spoken language is answered, knot can be answered using the spoken of voice storage system record examinee
Fruit can be stored in a manner of audio etc..
In one implementation of the present embodiment, if dimensions include content dimension, be based on dimensions, obtain with
The corresponding dimension score value of dimensions, comprising:
Obtain the spoken content of text for answering result;
Determine the integrity degree coefficient between content of text and preset reference answer;
Corresponding content dimension score value is determined based on integrity degree coefficient.
Pass through the available spoken content of text for answering result of speech recognition system.Determine content of text and preset reference
When integrity degree coefficient between answer, keyword can be extracted from Key for Reference, it is necessary that these keywords can be examinee
Want the spoken content answered.Then synonym extension is made to these keywords, and takes its union.Then by the union out of text
Search for whether content of text includes keyword therein in appearance, if so, then recording, identical or synonym keyword is only
Retain one.It is then based on the quantity for the keyword for including in content of text and the number of the keyword extracted from Key for Reference
Amount, the two are divided by, an available integrity degree coefficient.It is appreciated that the integrity degree coefficient is bigger, corresponding content dimension is commented
Score value is higher.
In one implementation of the present embodiment, if dimensions include pronunciation dimension, be based on dimensions, obtain with
The corresponding dimension score value of dimensions, comprising:
The spoken pronunciation character answered in result is extracted based on the acoustic model that standard pronunciation is formed;
Based on standard pronunciation, accuracy of the pronunciation character relative to standard pronunciation is determined;
Corresponding pronunciation dimension score value is determined based on accuracy.
In the present embodiment, it is related special to extract GOP marking by recognition result for the acoustic model that can be trained with standard pronunciation
Sign.Using standard pronunciation as reference frame, 0-1 model is evaluated in the pronunciation of training word level.The marking of last entire dimension is by correct
Rate provides.Acoustic model can be obtained by way of big data training.
Pronunciation character can be every spoken pronunciation for answering each word in result.Then, based on each word
The standard pronunciation of itself and each word can be compared, judge whether the pronunciation of the word is correct by pronunciation.Based on all lists
Word therefrom determines orthoepic word, and the quantity of orthoepic word and the quantity of all words are divided by, and can obtain
To accuracy.Accuracy is bigger, then dimension of pronouncing score value is higher.
In one implementation of the present embodiment, if dimensions include grammer dimension, be based on dimensions, obtain with
The corresponding dimension score value of dimensions, comprising:
Obtain the spoken content of text for answering result;
Punctuate is carried out to the content of text and obtains target sentences text;
Obtain the grammar property in the target sentences text;
Preset prediction model will be input to as parameter to each grammar property, and exported by the prediction model
Corresponding grammer dimension score value.
The present invention can, can first to content of text carry out subordinate sentence;Then grammer is carried out to misinterpretation by sentence pair content of text,
Come to sentence into grammer by link grammar scheme to misinterpretation;Finally, according to the correlated characteristic of test taker answers mistake and corresponding
Syntax error marking mark, is based on prediction model.A prediction model provides the marking of grammer dimension in this way.Prediction model can
It is generated by way of big data training by the spoken result of answering based on previous all examinees.
It is appreciated that prediction model can judge whether there is mistake to the grammar property of input, and marking mark is carried out,
With the marking of final output grammer dimension.
In one implementation of the present embodiment, if dimensions include fluency, dimensions is based on, obtains and comments
The corresponding dimension score value of fractional dimension, comprising:
Obtain the spoken content of text for answering result;
Determine the time serial message of respective word in content of text;
Characteristic value corresponding with each time serial message is generated based on time serial message;
Characteristic value corresponding with each time serial message is input to preset fluency model, and by fluency mould
Type exports corresponding fluency score value.
In the present embodiment, time serial message emphasis includes the distributed intelligence of the time number of length sil.Characteristic value can be with
It is temporal information itself, such as time span, interval time lengths, dead time length.
For time serial message, the time point of corresponding pronunciation of words itself can be understood as.If being appreciated that mouth
Language compares process, and the time interval between two words is inevitable smaller, on the contrary, then can be bigger.Therefore, if two time sequences
Time interval between column information is smaller, i.e., characteristic value is smaller, then marking value is higher, on the contrary, marking value is then smaller.
In the present embodiment, when dimensions include 4 dimensions such as content dimension, pronunciation dimension, grammer dimension and fluency
When, the spoken comprehensive grading value for answering result can be calculated using following formula.Specific formula is as follows:
R=Scontent*0.05
X1=SContent;SContent∈ [0,10]
X2=SFluency/3*10;SFluency∈ [0,3]
X3=SGrummar;SGrammar∈ [0,3]
X4=SPronunciationSPronunciation∈ [0,4]
Overall=(1-r) * x1+r* (0.25*x2+0.25*x3+0.5*x4)
Overall ∈ [0,10]
Wherein, x1 indicates content dimension marking value, and x2 indicates fluency marking value, and x3 indicates grammer dimension marking value, x4
Indicate pronunciation dimension marking value, r indicates coefficient associated with spoken language answer result.
Fig. 2 is that the various dimensions of the speaking test of an embodiment assess the structure chart of device.As shown in Fig. 2, the device includes:
First obtains module 210, answers result for obtaining the spoken of examinee;
First determining module 220, for determining that, to the spoken dimensions for answering result, dimensions include at least content
Dimension, pronunciation dimension, grammer dimension and fluency;
Second obtains module 230, for being based on dimensions, obtains dimension score value corresponding with dimensions;
Second determining module 240 determines the spoken comprehensive grading value for answering result for being based on each dimension score value;
Third determining module 250 determines the assessment knot to examinee for being based on comprehensive grading value and each dimension score value
Fruit.
In the present invention, obtains the spoken of examinee and answer result;It determines to the spoken dimensions for answering result, it is described
Dimensions include at least content dimension, pronunciation dimension, grammer dimension and fluency;Based on the dimensions, acquisition and institute
The corresponding dimension score value of commentary fractional dimension;Based on each dimension score value, the comprehensive of the spoken answer result is determined
Close score value;Based on the comprehensive grading value and each dimension score value, the assessment result to the examinee is determined.By
This, the present invention simultaneously can assess spoken answer of examinee based on multiple and different dimensions, can also be further formed comprehensive
Score value is closed to assess on the whole;In this way, the advantages of each student can directly know oneself and deficiency, timely improve oneself
Study plan;The relatively direct scheme for providing total score, it is explanatory stronger, relatively more objective to score.
In one implementation of the present embodiment, if dimensions include content dimension, the second acquisition module is used for:
Obtain the spoken content of text for answering result;
Determine the integrity degree coefficient between content of text and preset reference answer;
Corresponding content dimension score value is determined based on integrity degree coefficient.
In one implementation of the present embodiment, if dimensions include pronunciation dimension, the second acquisition module is used for:
The spoken pronunciation character answered in result is extracted based on the acoustic model that standard pronunciation is formed;
Based on standard pronunciation, accuracy of the pronunciation character relative to standard pronunciation is determined;
Corresponding pronunciation dimension score value is determined based on accuracy.
In one implementation of the present embodiment, if dimensions include grammer dimension, the second acquisition module is used for:
Obtain the spoken content of text for answering result;
Punctuate is carried out to the content of text and obtains target sentences text;
Obtain the grammar property in the target sentences text;
Preset prediction model will be input to as parameter to each grammar property, and exported by the prediction model
Corresponding grammer dimension score value.
In one implementation of the present embodiment, if dimensions include fluency, the second acquisition module is used for:
Obtain the spoken content of text for answering result;
Determine the time serial message of respective word in content of text;
Characteristic value corresponding with each time serial message is generated based on time serial message;
Characteristic value corresponding with each time serial message is input to preset fluency model, and by fluency mould
Type exports corresponding fluency score value.
In the present embodiment, the realization process of apparatus above is identical as the content of above method, is specifically referred to top
The content of embodiment in method, the present embodiment are no longer specifically described in detail device.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of various dimensions appraisal procedure of speaking test, which is characterized in that the described method includes:
It obtains the spoken of examinee and answers result;
Determine that, to the spoken dimensions for answering result, the dimensions include at least content dimension, pronunciation dimension, language
Method dimension and fluency;
Based on the dimensions, dimension score value corresponding with the dimensions is obtained;
Based on each dimension score value, the spoken comprehensive grading value for answering result is determined;
Based on the comprehensive grading value and each dimension score value, the assessment result to the examinee is determined.
2. described the method according to claim 1, wherein if the dimensions include content dimension
Based on the dimensions, dimension score value corresponding with the dimensions is obtained, comprising:
Obtain the spoken content of text for answering result;
Determine the integrity degree coefficient between the content of text and preset reference answer;
Corresponding content dimension score value is determined based on the integrity degree coefficient.
3. described the method according to claim 1, wherein if the dimensions include pronunciation dimension
Based on the dimensions, dimension score value corresponding with the dimensions is obtained, comprising:
The spoken pronunciation character answered in result is extracted based on the acoustic model that standard pronunciation is formed;
Based on the standard pronunciation, accuracy of the pronunciation character relative to the standard pronunciation is determined;
Corresponding pronunciation dimension score value is determined based on the accuracy.
4. described the method according to claim 1, wherein if the dimensions include grammer dimension
Based on the dimensions, dimension score value corresponding with the dimensions is obtained, comprising:
Obtain the spoken content of text for answering result;
Punctuate is carried out to the content of text and obtains target sentences text;
Obtain the grammar property in the target sentences text;
Preset prediction model will be input to as parameter to each grammar property, and exported and corresponded to by the prediction model
Grammer dimension score value.
5. the method according to claim 1, wherein if the dimensions include fluency, the base
In the dimensions, dimension score value corresponding with the dimensions is obtained, comprising:
Obtain the spoken content of text for answering result;
Determine the time serial message of respective word in the content of text;
Characteristic value corresponding with each time serial message is generated based on the time serial message;
Characteristic value corresponding with each time serial message is input to preset fluency model, and by described fluent
It spends model and exports corresponding fluency score value.
6. the various dimensions of speaking test a kind of assess device, which is characterized in that described device includes:
First obtains module, answers result for obtaining the spoken of examinee;
First determining module, for determining that the dimensions include at least interior to the spoken dimensions for answering result
Hold dimension, pronunciation dimension, grammer dimension and fluency;
Second obtains module, for being based on the dimensions, obtains dimension score value corresponding with the dimensions;
Second determining module determines the spoken comprehensive grading value for answering result for being based on each dimension score value;
Third determining module is determined for being based on the comprehensive grading value and each dimension score value to the examinee's
Assessment result.
7. device according to claim 6, which is characterized in that described if the dimensions include content dimension
Second acquisition module is used for:
Obtain the spoken content of text for answering result;
Determine the integrity degree coefficient between the content of text and preset reference answer;
Corresponding content dimension score value is determined based on the integrity degree coefficient.
8. device according to claim 6, which is characterized in that described if the dimensions include pronunciation dimension
Second acquisition module is used for:
The spoken pronunciation character answered in result is extracted based on the acoustic model that standard pronunciation is formed;
Based on the standard pronunciation, accuracy of the pronunciation character relative to the standard pronunciation is determined;
Corresponding pronunciation dimension score value is determined based on the accuracy.
9. device according to claim 6, which is characterized in that described if the dimensions include grammer dimension
Second acquisition module is used for:
Obtain the spoken content of text for answering result;
Punctuate is carried out to the content of text and obtains target sentences text;
Obtain the grammar property in the target sentences text;
It is input to preset prediction model using each grammar property as parameter, and corresponding by prediction model output
Grammer dimension score value.
10. device according to claim 6, which is characterized in that if the dimensions include fluency, described
Two acquisition modules are used for:
Obtain the spoken content of text for answering result;
Determine the time serial message of respective word in the content of text;
Characteristic value corresponding with each time serial message is generated based on the time serial message;
Characteristic value corresponding with each time serial message is input to preset fluency model, and by described fluent
It spends model and exports corresponding fluency score value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910266709.9A CN110164422A (en) | 2019-04-03 | 2019-04-03 | A kind of the various dimensions appraisal procedure and device of speaking test |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910266709.9A CN110164422A (en) | 2019-04-03 | 2019-04-03 | A kind of the various dimensions appraisal procedure and device of speaking test |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110164422A true CN110164422A (en) | 2019-08-23 |
Family
ID=67638354
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910266709.9A Pending CN110164422A (en) | 2019-04-03 | 2019-04-03 | A kind of the various dimensions appraisal procedure and device of speaking test |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110164422A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110797010A (en) * | 2019-10-31 | 2020-02-14 | 腾讯科技(深圳)有限公司 | Question-answer scoring method, device, equipment and storage medium based on artificial intelligence |
CN111415101A (en) * | 2020-04-16 | 2020-07-14 | 成都爱维译科技有限公司 | Automatic evaluation method and system for civil aviation English-Chinese bilingual radio communication capability grade |
CN111612324A (en) * | 2020-05-15 | 2020-09-01 | 深圳看齐信息有限公司 | Multi-dimensional assessment method based on oral English examination |
CN115798513A (en) * | 2023-01-31 | 2023-03-14 | 新励成教育科技股份有限公司 | Talent expression management method, system and computer readable storage medium |
CN116343824A (en) * | 2023-05-29 | 2023-06-27 | 新励成教育科技股份有限公司 | Comprehensive evaluation and solution method, system, device and medium for talent expression capability |
Citations (21)
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 |
CN101740024A (en) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | Method for automatic evaluation based on generalized fluent spoken language fluency |
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 |
CN102354495A (en) * | 2011-08-31 | 2012-02-15 | 中国科学院自动化研究所 | Testing method and system of semi-opened spoken language examination questions |
CN102509483A (en) * | 2011-10-31 | 2012-06-20 | 苏州思必驰信息科技有限公司 | Distributive automatic grading system for spoken language test and method thereof |
CN102789504A (en) * | 2012-07-19 | 2012-11-21 | 姜赢 | Chinese grammar correcting method and system on basis of XLM (Extensible Markup Language) rule |
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 |
CN103151042A (en) * | 2013-01-23 | 2013-06-12 | 中国科学院深圳先进技术研究院 | Full-automatic oral language evaluating management and scoring system and scoring method thereof |
CN103365838A (en) * | 2013-07-24 | 2013-10-23 | 桂林电子科技大学 | Method for automatically correcting syntax errors in English composition based on multivariate features |
CN103493041A (en) * | 2011-11-29 | 2014-01-01 | Sk电信有限公司 | Automatic sentence evaluation device using shallow parser to automatically evaluate sentence, and error detection apparatus and method for same |
CN104464423A (en) * | 2014-12-19 | 2015-03-25 | 科大讯飞股份有限公司 | Calibration optimization method and system for speaking test evaluation |
CN104464757A (en) * | 2014-10-28 | 2015-03-25 | 科大讯飞股份有限公司 | Voice evaluation method and device |
CN105632488A (en) * | 2016-02-23 | 2016-06-01 | 深圳市海云天教育测评有限公司 | Voice evaluation method and device |
CN105741831A (en) * | 2016-01-27 | 2016-07-06 | 广东外语外贸大学 | Spoken language evaluation method based on grammatical analysis and spoken language evaluation system |
CN105845134A (en) * | 2016-06-14 | 2016-08-10 | 科大讯飞股份有限公司 | Spoken language evaluation method through freely read topics and spoken language evaluation system thereof |
CN106776549A (en) * | 2016-12-06 | 2017-05-31 | 桂林电子科技大学 | A kind of rule-based english composition syntax error correcting method |
CN108255934A (en) * | 2017-12-07 | 2018-07-06 | 北京奇艺世纪科技有限公司 | A kind of sound control method and device |
CN108509474A (en) * | 2017-09-15 | 2018-09-07 | 腾讯科技(深圳)有限公司 | Search for the synonym extended method and device of information |
CN108519974A (en) * | 2018-03-31 | 2018-09-11 | 华南理工大学 | English composition automatic detection of syntax error and analysis method |
CN108960944A (en) * | 2017-05-17 | 2018-12-07 | 北京京东尚科信息技术有限公司 | User's evaluation processing method and processing device, computer-readable medium, electronic equipment |
CN109545243A (en) * | 2019-01-23 | 2019-03-29 | 北京猎户星空科技有限公司 | Pronunciation quality evaluating method, device, electronic equipment and storage medium |
-
2019
- 2019-04-03 CN CN201910266709.9A patent/CN110164422A/en active Pending
Patent Citations (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101740024A (en) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | Method for automatic evaluation based on generalized fluent spoken language fluency |
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 |
CN102354495A (en) * | 2011-08-31 | 2012-02-15 | 中国科学院自动化研究所 | Testing method and system of semi-opened spoken language examination questions |
CN102509483A (en) * | 2011-10-31 | 2012-06-20 | 苏州思必驰信息科技有限公司 | Distributive automatic grading system for spoken language test and method thereof |
CN103493041A (en) * | 2011-11-29 | 2014-01-01 | Sk电信有限公司 | Automatic sentence evaluation device using shallow parser to automatically evaluate sentence, and error detection apparatus and method for same |
CN102789504A (en) * | 2012-07-19 | 2012-11-21 | 姜赢 | Chinese grammar correcting method and system on basis of XLM (Extensible Markup Language) rule |
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 |
CN103151042A (en) * | 2013-01-23 | 2013-06-12 | 中国科学院深圳先进技术研究院 | Full-automatic oral language evaluating management and scoring system and scoring method thereof |
CN103365838A (en) * | 2013-07-24 | 2013-10-23 | 桂林电子科技大学 | Method for automatically correcting syntax errors in English composition based on multivariate features |
CN104464757A (en) * | 2014-10-28 | 2015-03-25 | 科大讯飞股份有限公司 | Voice evaluation method and device |
CN104464423A (en) * | 2014-12-19 | 2015-03-25 | 科大讯飞股份有限公司 | Calibration optimization method and system for speaking test evaluation |
CN105741831A (en) * | 2016-01-27 | 2016-07-06 | 广东外语外贸大学 | Spoken language evaluation method based on grammatical analysis and spoken language evaluation system |
CN105632488A (en) * | 2016-02-23 | 2016-06-01 | 深圳市海云天教育测评有限公司 | Voice evaluation method and device |
CN105845134A (en) * | 2016-06-14 | 2016-08-10 | 科大讯飞股份有限公司 | Spoken language evaluation method through freely read topics and spoken language evaluation system thereof |
CN106776549A (en) * | 2016-12-06 | 2017-05-31 | 桂林电子科技大学 | A kind of rule-based english composition syntax error correcting method |
CN108960944A (en) * | 2017-05-17 | 2018-12-07 | 北京京东尚科信息技术有限公司 | User's evaluation processing method and processing device, computer-readable medium, electronic equipment |
CN108509474A (en) * | 2017-09-15 | 2018-09-07 | 腾讯科技(深圳)有限公司 | Search for the synonym extended method and device of information |
CN108255934A (en) * | 2017-12-07 | 2018-07-06 | 北京奇艺世纪科技有限公司 | A kind of sound control method and device |
CN108519974A (en) * | 2018-03-31 | 2018-09-11 | 华南理工大学 | English composition automatic detection of syntax error and analysis method |
CN109545243A (en) * | 2019-01-23 | 2019-03-29 | 北京猎户星空科技有限公司 | Pronunciation quality evaluating method, device, electronic equipment and storage medium |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110797010A (en) * | 2019-10-31 | 2020-02-14 | 腾讯科技(深圳)有限公司 | Question-answer scoring method, device, equipment and storage medium based on artificial intelligence |
CN111415101A (en) * | 2020-04-16 | 2020-07-14 | 成都爱维译科技有限公司 | Automatic evaluation method and system for civil aviation English-Chinese bilingual radio communication capability grade |
CN111612324A (en) * | 2020-05-15 | 2020-09-01 | 深圳看齐信息有限公司 | Multi-dimensional assessment method based on oral English examination |
CN111612324B (en) * | 2020-05-15 | 2021-02-19 | 深圳看齐信息有限公司 | Multi-dimensional assessment method based on oral English examination |
CN115798513A (en) * | 2023-01-31 | 2023-03-14 | 新励成教育科技股份有限公司 | Talent expression management method, system and computer readable storage medium |
CN116343824A (en) * | 2023-05-29 | 2023-06-27 | 新励成教育科技股份有限公司 | Comprehensive evaluation and solution method, system, device and medium for talent expression capability |
CN116343824B (en) * | 2023-05-29 | 2023-08-15 | 新励成教育科技股份有限公司 | Comprehensive evaluation and solution method, system, device and medium for talent expression capability |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110164422A (en) | A kind of the various dimensions appraisal procedure and device of speaking test | |
Lynch et al. | Listening | |
CN103065626B (en) | Automatic grading method and automatic grading equipment for read questions in test of spoken English | |
CN101740024B (en) | Method for automatic evaluation of spoken language fluency based on generalized fluency | |
CN103761975B (en) | Method and device for oral evaluation | |
Gretter et al. | TLT-school: a corpus of non native children speech | |
Spring et al. | Assessing the practicality of using an automatic speech recognition tool to teach English pronunciation online | |
Kowtko | The function of intonation in task-oriented dialogue | |
Baur et al. | A shared task for spoken CALL? | |
KR20100114702A (en) | Learner centered foreign language education system and its teaching method | |
Leonisa | The Effectiveness Of Shadowing Technique On Students' Pronunciation At The Tenth Grade Students Of SMAN 1 Jetis Ponorogo | |
CN112668883A (en) | Small speech practice system for integrating Chinese speech and speech piece evaluation | |
Bernstein et al. | Design and development parameters for a rapid automatic screening test for prospective simultaneous interpreters | |
Rahmawati et al. | The Improvement of StudentsEnglish Pronunciation by Using Animation (3d) Video for the Second Years Students of Junior High School 1 Payakumbuh | |
Luo et al. | Investigation of the effects of automatic scoring technology on human raters' performances in L2 speech proficiency assessment | |
Elsayed Ahmed Ibrahim | Using E-portfolio to Develop EFL Fluency Skills among Secondary School Students | |
Prahaladaiah et al. | Effect of Phonological and Phonetic Interventions on Proficiency in English Pronunciation and Oral Reading | |
PRATIWI | AN ANALYSIS OF THE DIFFICULTIES ENCOUNTERED BY NON-ENGLISH DEPARTMENT STUDENT’S IN TOEFL TEST OF LISTENING SECTION (A Case Study at Arabic Education Department IAIN SMH Banten) | |
Rerung | Spoken fluency practices in increasing language learners performance | |
Shackleton | Planning for positive washback: The case of a listening proficiency test | |
Havrylenko | ESP Listening in Online Learning to University Students | |
KR102658252B1 (en) | Video education content providing method and apparatus based on artificial intelligence natural language processing using characters | |
Castro et al. | Teachers’ and Students’ Prosodic Knowledge and Skills: Aid to Reading Comprehension | |
Zhang et al. | Multi‐Feature Intelligent Oral English Error Correction Based on Few‐Shot Learning Technology | |
Yamauchi et al. | Investigation of teacher-selected sentences and machine-suggested sentences in terms of correlation between human ratings and GOP-based machine scores. |
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: 20190823 |