CN108154735A - Oral English Practice assessment method and device - Google Patents
Oral English Practice assessment method and device Download PDFInfo
- Publication number
- CN108154735A CN108154735A CN201611110307.2A CN201611110307A CN108154735A CN 108154735 A CN108154735 A CN 108154735A CN 201611110307 A CN201611110307 A CN 201611110307A CN 108154735 A CN108154735 A CN 108154735A
- Authority
- CN
- China
- Prior art keywords
- answer
- result
- text
- test
- match
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
This disclosure relates to a kind of Oral English Practice Level Evaluation method and apparatus, this method include:After test problem is exported, the voice signal of tester's input is received;Speech recognition is carried out to the voice signal, obtains corresponding text message;Answer in text message answer set corresponding with the test problem is subjected to text matches, wherein, the derivative answer that the answer set includes the model answer of the test problem and expanded according to the model answer;According at least to text matches as a result, obtaining evaluating result;Export the evaluating result.Thus, it is possible to which the semanteme and logicality to spoken language text make effective test and appraisal, comprehensive and accuracy rate and the evaluating result feedback speed for improving test and appraisal are fast.Suggest in addition, tester can obtain being promoted accordingly, it is with strong points.
Description
Technical field
A kind of this disclosure relates to Oral English Practice automation evaluation technology field, and in particular, to Oral English Practice assessment method
And device.
Background technology
The efficiency that learns with the continuous social and economic development with the aggravation of the trend of globalization, people to Oral English Practice and
Objectivity, fairness and the scale test of spoken assessment test propose increasingly higher demands.Due to spoken test and appraisal side
The particularity of formula and content, the at present scoring of Oral English Practice are mainly still solved by way of manually scoring.Due to artificial
The subjectivity of judging panel accounts for great role in scoring process, and therefore, this kind scoring lacks fairness, and accuracy rate is also difficult to ensure that, and
And compare time and effort consuming, inefficiency.
To solve the above problems, in the prior art by the way of computer automatic scoring, that is, using area of computer aided or
Person's full-automation carries out the scoring of spoken language exercise, speaking test process, using the efficient operation of computer and objectivity, improves
The efficiency and fairness of scoring.But existing automatic scoring mode is commented roughly for spoken speech intonation mostly
Valency but seldom makes logicality, the accuracy of spoken content in itself the evaluation of science, evaluates sufficiently complete, comprehensive, accuracy rate
Also it is corresponding to reduce.In addition, most of spoken language points-scoring system can only provide scoring, can not provide effectively, with specific aim
Carry point and to suggest.
Invention content
The purpose of the disclosure is to be directed to comment caused by it cannot make scientific evaluation to spoken content in the prior art
The problem of valency is sufficiently complete, accuracy rate is not high provides a kind of Oral English Practice assessment method and device.
To achieve these goals, the disclosure provides a kind of Oral English Practice assessment method, and this method includes:It is tested in output
After problem, the voice signal of tester's input is received;Speech recognition is carried out to the voice signal, obtains corresponding text envelope
Breath;Answer in text message answer set corresponding with the test problem is subjected to text matches, wherein, it is described to answer
The derivative answer that case set includes the model answer of the test problem and expanded according to the model answer;According to text
This matching result obtains evaluating result;Export the evaluating result.
Optionally, it is described according at least to text matches as a result, obtain evaluating result, including:In the text matches result
When representing that the answer set includes the answer to match with the text message, obtain opposite with the answer to match
The semantic test and appraisal score answered, and the semantic score of testing and assessing is included in the evaluating result.
Optionally, it is described according at least to text matches as a result, obtain evaluating result, further include:It is described match answer
When case and the inconsistent model answer, the deviation between the answer to match and the model answer is determined;According to institute
Deviation is stated, prompt message is suggested in generation, and the deviation and the suggestion prompt message are included in the evaluating result.
Optionally, it is described according at least to text matches as a result, obtain evaluating result, further include:In the text matches knot
When fruit represents that the answer set includes the answer to match with the text message, intonation knowledge is carried out to the voice signal
Not;According to intonation recognition result, the pronunciation scoring of the tester is obtained, and the pronunciation scoring is included tying in the test and appraisal
In fruit.
Optionally, the evaluating result further includes the audio of model answer corresponding with the test problem.
Optionally, the method further includes:Do not include and institute in the text matches result represents the answer set
When stating the answer that text message matches, the text message is recorded;Reach pre- in the cumulative record number of the text message
If during number, the text message is exported to answer librarian, so that answer library management person decides whether to utilize the text
Information updates answer library.
The disclosure also provides a kind of Oral English Practice assessment device, which includes:Receiving module, for being asked in output test
After topic, the voice signal of tester's input is received;Acquisition module for carrying out speech recognition to the voice signal, obtains
Corresponding text message;Matching module, for by answering in text message answer set corresponding with the test problem
Case carries out text matches, wherein, the answer set includes the model answer of the test problem and is answered according to the standard
The derivative answer that case expands;Evaluating result acquisition module, for according at least to text matches as a result, obtain evaluating result;It is defeated
Go out module, for exporting the evaluating result.
Optionally, the evaluating result acquisition module includes:Evaluating result acquisition submodule, in the text matches
When as a result representing that the answer set includes the answer to match with the text message, obtain and the answer to match
Corresponding semantic test and appraisal score, and the semantic score of testing and assessing is included in the evaluating result.
Optionally, the evaluating result acquisition module further includes:First determination sub-module, for it is described match answer
When case and the inconsistent model answer, the deviation between the answer to match and the model answer is determined;Second really
Stator modules, for according to the deviation, prompt message to be suggested in generation, and the deviation and the suggestion prompt message are included
In the evaluating result.
Optionally, the evaluating result acquisition module further includes:Intonation identifies submodule, in the text matches knot
When fruit represents that the answer set includes the answer to match with the text message, intonation knowledge is carried out to the voice signal
Not;Third determination sub-module, for according to intonation recognition result, obtaining the pronunciation of tester scoring, and by the pronunciation
Scoring is included in the evaluating result.
The technical scheme provided by this disclosed embodiment can include the following benefits:Pass through the language inputted to tester
Sound signal carries out speech recognition and obtains corresponding text message, then answers text information with corresponding model answer and derivative
Case carries out text matches, finally obtains evaluating result according at least to text matches result and exports the evaluating result.Pass through the skill
Art scheme can make effective test and appraisal to the semanteme and logicality of spoken language text, improve test and appraisal comprehensive and accuracy rate,
And evaluating result feedback speed is fast.Suggest in addition, tester can obtain being promoted accordingly, it is with strong points.
Other feature and advantage of the disclosure will be described in detail in subsequent specific embodiment part.
Description of the drawings
Attached drawing is for providing further understanding of the disclosure, and a part for constitution instruction, with following tool
Body embodiment is used to explain the disclosure, but do not form the limitation to the disclosure together.In the accompanying drawings:
Figure 1A is the flow chart according to a kind of Oral English Practice assessment method shown in an exemplary embodiment.
Figure 1B is the flow chart of a kind of Oral English Practice assessment method shown according to another exemplary embodiment.
Fig. 2A is the block diagram according to a kind of Oral English Practice assessment device shown in an exemplary embodiment.
Fig. 2 B are the block diagrams of a kind of Oral English Practice assessment device shown according to another exemplary embodiment.
Fig. 3 A to Fig. 3 E are the runnable interface figures according to a kind of Oral English Practice evaluation system shown in an exemplary embodiment.
Specific embodiment
The specific embodiment of the disclosure is described in detail below in conjunction with attached drawing.It should be understood that this place is retouched
The specific embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
Figure 1A is according to a kind of flow chart of Oral English Practice assessment method shown in an exemplary embodiment, applied to English
Spoken evaluation system.As shown in Figure 1A, this method can include:
In a step 101, after test problem is exported, the voice signal of tester's input is received.
In a step 102, speech recognition is carried out to voice signal, obtains corresponding text message.
In the disclosure, the database which is relied on can include by words and phrases in speaking test over the years into
The comprehensive corpus of authority that row is collected comprehensively and arranges and formed.Further, it is also possible to language materials whole in the database
Carry out speech recognition and the orientation optimization of semantic processes.Can by increase the word that is difficult to the number of machine learning come
Phonetic recognization rate is promoted, so as to complete speech recognition optimization.Furthermore it is also possible to the word frequency by counting the high frequency vocabulary in taking an examination
Probability identifies homonym, and then improve phonetic recognization rate according to the word frequency probability of the word and the position occurred.Illustratively,
" pronunciation of these three words of to, two, too " is identical, it is difficult to accurately identify out by existing speech recognition.Such as:
The answer section head in the 3rd problem in the spoken 24th set of topic of TOEFL occurs one, and " word of to, two, too " pronunciation, leads to
It crosses and judges the position of the word to confirm that the word must be " two ", because this position of this problem is only possible to occur this
“two”.In this way, can by the speech recognition of high discrimination by the speech recognition of tester into text message.
In step 103, the answer in text message answer set corresponding with test problem is subjected to text matches.
In the disclosure, which can include the model answer of the test problem and be answered according to the standard
The derivative answer that case expands.The derivative answer can include obtaining the synonymous extension of model answer progress at least one
Answer, it can replace to expand the answer come or lead to by carrying out model answer synonym or near synonym
The answer that provides of the person that crosses statistical test to test problem, and correct option of the statistics number more than predetermined value is entered into answer
Answer in library.In text matches, in order to improve the efficiency of text matches, Oral English Practice evaluation system can be first by text
Information model answer corresponding with test problem carries out text matches, is carried out when the two mismatches, then by itself and derivative answer
Text matches.
In addition, the logical correctness of text message is also extremely important, therefore, in text matches, it is also contemplated that text envelope
Sequence in breath between word and word.In this way, in text matches, not only want whether to include in criterion answer or derivative answer
Alphabet in text information, also to judge character sequence in text information whether with model answer or derivative answer
In character sequence it is consistent.When some answer in answer set includes the alphabet in text information, and character is suitable
Sequence is also consistent, then the answer is determined as and the matched answer of text message.
Illustratively, phrase " live on campus " must be included in the corresponding answer of test problem, therefore, can be passed through
It is realized before and after the phrase plus comma.In this way, only when in the corresponding text message of voice signal of tester's input
When all continuously occurring comprising " live ", " on ", " campus " three words and these three words, it is believed that text information
Answer in answer set corresponding with the test problem matches.And when the corresponding text envelope of voice signal of tester's input
Do not occur continuously comprising " live ", " on ", " campus " three words but these three words in breath, at this time it is considered that answer
The answer with text information matches is not included in set.In this way, it is possible to ensure the correctness of logic of language sequence.
At step 104, according at least to text matches as a result, obtaining evaluating result.
In the disclosure, whether text matching result can be used to indicate that in answer set and includes and above-mentioned text envelope
The matched answer of manner of breathing.Further, it is also possible to semantic test and appraisal score corresponding to each answer matches in answer library.It can pass through
In the following manner is each answer matches semanteme test and appraisal score:
First, it is word and sentence difference in each answer in answer library according to the spoken standards of grading of official
Score value weight corresponding with the score value with science.
Next, the matched score value of word and sentence institute and weight in each answer, it is opposite to calculate this kind of answer
The semantic test and appraisal score answered.
In one embodiment, when text matches result represents that answer set includes matching with above-mentioned text message
Answer when, obtain and the corresponding semantic test and appraisal score of the answer that matches, and semanteme score of testing and assessing is added to test and appraisal
As a result in.
In another embodiment, when text matches result represents not include and above-mentioned text envelope manner of breathing in answer set
During matched answer, then score, i.e. semanteme do not test and assess score as zero.
Optionally, above-mentioned steps 104 can also include the following steps:
First, it when the answer to match is inconsistent with model answer, determines between the answer and model answer that match
Deviation.
Next, according to above-mentioned deviation, prompt message is suggested in generation, and by deviation and suggests that prompt message includes testing and assessing
As a result in.
In the disclosure, a point suggestion corresponding to each answer matches in answer library can also be proposed, this proposes a point suggestion can
To be formulated according to the gap between the answer and model answer to match.Represent that answer set includes in text matches result
During the answer to match with above-mentioned text message, Oral English Practice evaluation system can compare the answer with model answer,
And when the two is inconsistent, the deviation between the answer and model answer to match is found out, that is, finds out the answer to match and mark
Gap between quasi- answer.Then, according to the gap, prompt message is suggested in generation, which is used for tester
Feedback proposes a point suggestion accordingly.
Illustratively, when the answer of tester differs several words with the model answer in answer library, Oral English Practice test and appraisal system
System can be provided as why not missed suggestion and the method for these words, can also be provided more preferable relative to other of the answer
Ground expression way.
Illustratively, the following answer included in answer set in the corresponding answer set of a test problem:“school
bus should be canceled”、“school bus should be canceled”、“school should cancel
the bus”、“school bus should be eliminated”、“school is supposed to cancel the
Bus ", " school should eliminate the bus ", " school should stop the bus " etc..Wherein,
" school bus should be canceled " is the model answer of the test problem.If the voice letter of tester's input
Number correspondence text message gone out by speech recognition is " school should stop the bus ", can by text matches
To determine that text information is included in the corresponding answer set of the test problem.At this point, Oral English Practice evaluation system can incite somebody to action
The answer is compared with model answer, is understood that text information is inconsistent with model answer by comparison, is made in model answer
With " cancled " word, and tester has used " stop " word, and the two has certain semantic deviation.Then, Oral English Practice
Evaluation system can generate to carry point accordingly and suggest according to the deviation, for example, in this scenario, use " cancel " or
" eliminate " is proper, and using " stop ", there are certain semantic deviations.
In addition, other than the content of text to English is tested and assessed, Oral English Practice evaluation system can also be to English mouth
The intonation of language is tested and assessed.In this way, evaluating result can include the evaluating result of speech intonation and content of text so that test and appraisal knot
Fruit is more comprehensively, accurately.
When text matches result represents not include the answer to match with above-mentioned text message in answer set, semanteme is surveyed
Scoring number is zero, that is to say, that tester is completely incorrect for the answer of test problem, at this time It is not necessary to send out again it
Sound scores.Therefore, in order to promote the efficiency of test and appraisal and reduce time delay, Oral English Practice evaluation system can be in text matches
When as a result representing that answer set includes the answer to match with text message, intonation identification is carried out to voice signal;Then root
According to intonation recognition result, the pronunciation scoring (including pronunciation and fluency) of tester is obtained, and pronunciation scoring is included testing and assessing
As a result in.As shown in Figure 3A, Oral English Practice evaluation system can also provide the pronunciation mistake of tester's appearance in evaluating result
Vocabulary and corresponding phonetic symbol, and provide corresponding official's comment.In addition, in order to targetedly promote tester in pronunciation side
The scoring in face, Oral English Practice evaluation system can be set with reading mode, that is, provide one section with read content, by receive tester with
With reading the corresponding voice of content and being uploaded in corpus, the scoring with reading voice is provided.In addition, tester can also lead to
It crosses and rerecords voice progress repeatedly with reading.
Since intonation identifies and pronounces that scoring is well known to those skilled in the art, do not do excessive description here.
In addition, evaluating result can also include the audio of model answer corresponding with test problem, contribute to test in this way
Person improves to some extent in terms of Oral English Practice pronunciation.
In step 105, evaluating result is exported.
In the disclosure, which can include semantic test and appraisal score, pronunciation scoring, text message and model answer
Between deviation, suggest prompt message, audio of model answer corresponding with test problem, etc..When the acquisition evaluating result
Afterwards, it can be output on interface, so that tester has clear, intuitive understanding to the answer situation of oneself.
As shown in figs. 3 b and 3 c, in order to strengthen the practice of tester's weak link, after evaluating result is obtained, Oral English Practice
Evaluation system can also recommend similar test problem to be practiced according to the evaluating result to tester.In addition, Oral English Practice
Evaluation system can also preserve each evaluating result, and provide be made of each evaluating result test and appraisal list (for example, into
Achievement curve).
In addition, as shown in Figure 3B, Oral English Practice evaluation system can also be according to the evaluating result to the comprehensive real of tester
Power scores, and provides and corresponding encourage the language person that comes exciting test.
In addition, as shown in Fig. 3 D and Fig. 3 E, Oral English Practice evaluation system can also provide tester in vocabulary, grammer, thin
The performance analysis chart of section and fluency etc., and provide official's comment for performance analysis and propose a point suggestion.
The technical scheme provided by this disclosed embodiment can include the following benefits:Pass through the language inputted to tester
Sound signal carries out speech recognition and obtains corresponding text message, then answers text information with corresponding model answer and derivative
Case carries out text matches, finally obtains evaluating result according at least to text matches result and exports the evaluating result.Pass through the skill
Art scheme can make effective test and appraisal to the semanteme and logicality of spoken language text, improve test and appraisal comprehensive and accuracy rate,
And evaluating result feedback speed is fast.Suggest in addition, tester can obtain being promoted accordingly, it is with strong points.
Figure 1B is the flow chart of a kind of Oral English Practice assessment method shown according to another exemplary embodiment.Such as Figure 1B institutes
Show, above-mentioned steps can also include the following steps:
In step 106, do not include the answer to match with text message in text matches result represents answer set
When, record text information.
In step 107, it when the cumulative record number of text message reaches preset times, is exported to answer librarian
Text information, so that answer library management person decides whether to update answer library using text information.
In the disclosure, since answer library is unable to all answers of limit test problem, those can be recorded and do not existed
Text message in answer library, and when the cumulative record number of the text message in record reaches preset times, it can be by this article
This information is output in answer librarian, to determine whether to add it to corresponding answer library by answer library management person
In.In this way, the comprehensive of answer library can be promoted so that evaluating result is more accurate.
In addition, Oral English Practice evaluation system can also provide relevant examination information for tester, which can include
Experience shares and simulation test problem etc..
Fig. 2A is according to a kind of block diagram of Oral English Practice assessment device shown in an exemplary embodiment, which is applied to
Oral English Practice evaluation system.As shown in Figure 2 A, which can include:Receiving module 201, in output test problem
Later, the voice signal of tester's input is received;Acquisition module 202, for the institute's predicate received to the receiving module 201
Sound signal carries out speech recognition, obtains corresponding text message;Matching module 203, for the acquisition module 202 to be got
Text message answer set corresponding with the test problem in answer carry out text matches, wherein, the answer
Gather the derivative answer for including the model answer of the test problem and being expanded according to the model answer;Evaluating result
Acquisition module 204, for the text matches that are obtained according at least to the matching module 203 as a result, obtaining evaluating result;Export mould
Block 205, for exporting the evaluating result.
Optionally, the evaluating result acquisition module 204 includes:Evaluating result acquisition submodule, in the text
When matching result represents that the answer set includes the answer to match with the text message, obtain and described match
The corresponding semantic test and appraisal score of answer, and the semantic score of testing and assessing is included in the evaluating result.
Optionally, the evaluating result acquisition module 204 further includes:First determination sub-module, for matching described
Answer and the model answer it is inconsistent when, determine the deviation between the answer to match and the model answer;The
Two determination sub-modules, for according to the deviation, prompt message is suggested in generation, and by the deviation and the suggestion prompt message
It is included in the evaluating result.
Optionally, the evaluating result acquisition module 204 further includes:Intonation identifies submodule, in the text
When representing that the answer set includes the answer to match with the text message with result, language is carried out to the voice signal
Adjust identification;Third determination sub-module, for according to intonation recognition result, obtaining the pronunciation scoring of the tester, and by described in
Pronunciation scoring is included in the evaluating result.
Fig. 2 B are the block diagrams of a kind of Oral English Practice assessment device shown according to another exemplary embodiment.Such as Fig. 2 B institutes
Show, which can also include:Logging modle 206, in representing the answer set in the text matches result not
Including match with the text message answer when, record the text message;Update module 207, in the text
When the cumulative record number of information reaches preset times, the text message is exported to answer librarian, so as to answer depositary management
Reason person decides whether to update answer library using the text message.
The preferred embodiment of the disclosure is described in detail above in association with attached drawing, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection domain of the disclosure.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case of shield, can be combined by any suitable means, in order to avoid unnecessary repetition, the disclosure to it is various can
The combination of energy no longer separately illustrates.
In addition, arbitrary combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought should equally be considered as disclosure disclosure of that.
Claims (10)
1. a kind of Oral English Practice assessment method, which is characterized in that the method includes:
After test problem is exported, the voice signal of tester's input is received;
Speech recognition is carried out to the voice signal, obtains corresponding text message;
Answer in text message answer set corresponding with the test problem is subjected to text matches, wherein, it is described
The derivative answer that answer set includes the model answer of the test problem and expanded according to the model answer;
According at least to text matches as a result, obtaining evaluating result;
Export the evaluating result.
2. according to the method described in claim 1, it is characterized in that, described tie according at least to text matches as a result, obtaining test and appraisal
Fruit, including:
When the text matches result represents that the answer set includes the answer to match with the text message, obtain
With the corresponding semantic test and appraisal score of the answer to match, and the semantic score of testing and assessing is included in the evaluating result
In.
3. according to the method described in claim 2, it is characterized in that, described tie according at least to text matches as a result, obtaining test and appraisal
Fruit further includes:
When the answer to match and the model answer are inconsistent, determine that the answer to match is answered with the standard
Deviation between case;
According to the deviation, prompt message is suggested in generation, and the deviation and the suggestion prompt message are included in the survey
It comments in result.
4. according to the method in claim 2 or 3, which is characterized in that it is described according at least to text matches as a result, being tested and assessed
As a result, it further includes:
When the text matches result represents that the answer set includes the answer to match with the text message, to institute
Predicate sound signal carries out intonation identification;
According to intonation recognition result, the pronunciation scoring of the tester is obtained, and the pronunciation scoring is included in the test and appraisal
As a result in.
5. according to the method described in claim 4, it is characterized in that, the evaluating result further include it is corresponding with the test problem
Model answer audio.
6. according to the method described in claim 2, it is characterized in that, the method further includes:
When not including the answer to match with the text message during the text matches result represents the answer set, note
Record the text message;
When the cumulative record number of the text message reaches preset times, the text envelope is exported to answer librarian
Breath, so that answer library management person decides whether to update answer library using the text message.
7. a kind of Oral English Practice assessment device, which is characterized in that described device includes:
Receiving module, for after test problem is exported, receiving the voice signal of tester's input;
Acquisition module for carrying out speech recognition to the voice signal, obtains corresponding text message;
Matching module, for the answer in text message answer set corresponding with the test problem to be carried out text
Match, wherein, the answer set includes the model answer of the test problem and is spread out according to what the model answer expanded
Raw answer;
Evaluating result acquisition module, for according at least to text matches as a result, obtain evaluating result;
Output module, for exporting the evaluating result.
8. device according to claim 7, which is characterized in that the evaluating result acquisition module includes:
Evaluating result acquisition submodule, for representing that the answer set includes and the text in the text matches result
During the answer of information match, obtain with the corresponding semantic test and appraisal score of the answer that matches, and semantic surveyed described
Scoring number is included in the evaluating result.
9. device according to claim 8, which is characterized in that the evaluating result acquisition module further includes:
First determination sub-module, for when the answer to match and the model answer are inconsistent, determining the phase
Deviation between the answer and the model answer matched;
Second determination sub-module, for according to the deviation, prompt message to be suggested in generation, and the deviation and the suggestion are carried
Show that information is included in the evaluating result.
10. device according to claim 8 or claim 9, which is characterized in that the evaluating result acquisition module further includes:
Intonation identifies submodule, for representing that the answer set includes and the text message in the text matches result
During the answer to match, intonation identification is carried out to the voice signal;
Third determination sub-module, for according to intonation recognition result, obtaining the pronunciation of tester scoring, and by the pronunciation
Scoring is included in the evaluating result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611110307.2A CN108154735A (en) | 2016-12-06 | 2016-12-06 | Oral English Practice assessment method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611110307.2A CN108154735A (en) | 2016-12-06 | 2016-12-06 | Oral English Practice assessment method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108154735A true CN108154735A (en) | 2018-06-12 |
Family
ID=62468196
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611110307.2A Pending CN108154735A (en) | 2016-12-06 | 2016-12-06 | Oral English Practice assessment method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108154735A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109035896A (en) * | 2018-08-13 | 2018-12-18 | 广东小天才科技有限公司 | A kind of Oral Training method and facility for study |
CN109036438A (en) * | 2018-08-20 | 2018-12-18 | 平安科技(深圳)有限公司 | Storage cabinet control, device, computer equipment and storage medium |
CN109191968A (en) * | 2018-10-25 | 2019-01-11 | 重庆鲁班机器人技术研究院有限公司 | Language education robot and more educational robot langue leaning systems |
CN109213847A (en) * | 2018-09-14 | 2019-01-15 | 广州神马移动信息科技有限公司 | Layered approach and its device, electronic equipment, the computer-readable medium of answer |
CN109299250A (en) * | 2018-09-14 | 2019-02-01 | 广州神马移动信息科技有限公司 | Methods of exhibiting, device, storage medium and the electronic equipment of answer |
CN109460823A (en) * | 2018-09-14 | 2019-03-12 | 广州神马移动信息科技有限公司 | Construction method and its device, electronic equipment, the computer-readable medium of knowledge base |
CN109903618A (en) * | 2019-03-27 | 2019-06-18 | 广东小天才科技有限公司 | Listening Training method, apparatus, equipment and storage medium |
JP2020056982A (en) * | 2018-09-30 | 2020-04-09 | アイフライテック カンパニー,リミテッド | Speech evaluation method, device, apparatus and readable storage medium |
CN111047932A (en) * | 2020-01-02 | 2020-04-21 | 上海健坤教育科技有限公司 | Voice interactive teaching system |
CN111353066A (en) * | 2020-02-20 | 2020-06-30 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN111369998A (en) * | 2020-02-28 | 2020-07-03 | 联想(北京)有限公司 | Data processing method and electronic equipment |
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 |
CN111639219A (en) * | 2020-05-12 | 2020-09-08 | 广东小天才科技有限公司 | Method for acquiring spoken language evaluation sticker, terminal device and storage medium |
CN111951625A (en) * | 2020-09-04 | 2020-11-17 | 中原工学院信息商务学院 | College spoken English conversation interactive system |
CN112989012A (en) * | 2021-04-27 | 2021-06-18 | 武汉龙津科技有限公司 | Information updating method and device, electronic equipment and readable storage medium |
CN113053388A (en) * | 2021-03-09 | 2021-06-29 | 北京百度网讯科技有限公司 | Voice interaction method, device, equipment and storage medium |
JP7166696B1 (en) | 2022-07-07 | 2022-11-08 | 株式会社Ongli | Information processing method, program and information processing device |
CN115497455A (en) * | 2022-11-21 | 2022-12-20 | 山东山大鸥玛软件股份有限公司 | Intelligent voice evaluation method, system and device for oral English test |
CN116403604A (en) * | 2023-06-07 | 2023-07-07 | 北京奇趣万物科技有限公司 | Child reading ability evaluation method and system |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090070100A1 (en) * | 2007-09-11 | 2009-03-12 | International Business Machines Corporation | Methods, systems, and computer program products for spoken language grammar evaluation |
CN101551947A (en) * | 2008-06-11 | 2009-10-07 | 俞凯 | Computer system for assisting spoken language learning |
CN101739867A (en) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | Method for scoring interpretation quality by using computer |
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 |
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 |
CN103761975A (en) * | 2014-01-07 | 2014-04-30 | 苏州思必驰信息科技有限公司 | Method and device for oral evaluation |
JP2015011348A (en) * | 2013-06-26 | 2015-01-19 | 韓國電子通信研究院Electronics and Telecommunications Research Institute | Training and evaluation method for foreign language speaking ability using voice recognition and device for the same |
CN104599680A (en) * | 2013-10-30 | 2015-05-06 | 语冠信息技术(上海)有限公司 | Real-time spoken language evaluation system and real-time spoken language evaluation method on mobile equipment |
CN104681037A (en) * | 2015-03-19 | 2015-06-03 | 广东小天才科技有限公司 | Pronunciation guidance method and device as well as electronic reading machine |
CN104810017A (en) * | 2015-04-08 | 2015-07-29 | 广东外语外贸大学 | Semantic analysis-based oral language evaluating method and system |
CN104933084A (en) * | 2015-05-04 | 2015-09-23 | 上海智臻网络科技有限公司 | Method, apparatus and device for acquiring answer information |
CN104951456A (en) * | 2014-03-26 | 2015-09-30 | 上海智臻网络科技有限公司 | Method, device and equipment used for obtaining answer information |
CN105374356A (en) * | 2014-08-29 | 2016-03-02 | 株式会社理光 | Speech recognition method, speech assessment method, speech recognition system, and speech assessment system |
CN105654785A (en) * | 2016-03-18 | 2016-06-08 | 上海语知义信息技术有限公司 | Personalized spoken foreign language learning system and method |
CN105677783A (en) * | 2015-12-31 | 2016-06-15 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
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 |
-
2016
- 2016-12-06 CN CN201611110307.2A patent/CN108154735A/en active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090070100A1 (en) * | 2007-09-11 | 2009-03-12 | International Business Machines Corporation | Methods, systems, and computer program products for spoken language grammar evaluation |
CN101551947A (en) * | 2008-06-11 | 2009-10-07 | 俞凯 | Computer system for assisting spoken language learning |
CN101739867A (en) * | 2008-11-19 | 2010-06-16 | 中国科学院自动化研究所 | Method for scoring interpretation quality by using computer |
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 |
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 |
JP2015011348A (en) * | 2013-06-26 | 2015-01-19 | 韓國電子通信研究院Electronics and Telecommunications Research Institute | Training and evaluation method for foreign language speaking ability using voice recognition and device for the same |
CN104599680A (en) * | 2013-10-30 | 2015-05-06 | 语冠信息技术(上海)有限公司 | Real-time spoken language evaluation system and real-time spoken language evaluation method on mobile equipment |
CN103761975A (en) * | 2014-01-07 | 2014-04-30 | 苏州思必驰信息科技有限公司 | Method and device for oral evaluation |
CN104951456A (en) * | 2014-03-26 | 2015-09-30 | 上海智臻网络科技有限公司 | Method, device and equipment used for obtaining answer information |
CN105374356A (en) * | 2014-08-29 | 2016-03-02 | 株式会社理光 | Speech recognition method, speech assessment method, speech recognition system, and speech assessment system |
CN104681037A (en) * | 2015-03-19 | 2015-06-03 | 广东小天才科技有限公司 | Pronunciation guidance method and device as well as electronic reading machine |
CN104810017A (en) * | 2015-04-08 | 2015-07-29 | 广东外语外贸大学 | Semantic analysis-based oral language evaluating method and system |
CN104933084A (en) * | 2015-05-04 | 2015-09-23 | 上海智臻网络科技有限公司 | Method, apparatus and device for acquiring answer information |
CN105677783A (en) * | 2015-12-31 | 2016-06-15 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
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 |
CN105654785A (en) * | 2016-03-18 | 2016-06-08 | 上海语知义信息技术有限公司 | Personalized spoken foreign language learning system and method |
Non-Patent Citations (3)
Title |
---|
宋阳等: "一种自发性口语评测文本语义相似度评分特征提取方法", 《集成技术》 * |
汪文棣等: "英语口语机考评分系统研究与实现", 《电子器件》 * |
程蒙蒙: "Versant英语口语测试:特点分析及其启示", 《中国考试》 * |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109035896B (en) * | 2018-08-13 | 2021-11-05 | 广东小天才科技有限公司 | Oral training method and learning equipment |
CN109035896A (en) * | 2018-08-13 | 2018-12-18 | 广东小天才科技有限公司 | A kind of Oral Training method and facility for study |
CN109036438A (en) * | 2018-08-20 | 2018-12-18 | 平安科技(深圳)有限公司 | Storage cabinet control, device, computer equipment and storage medium |
CN109213847A (en) * | 2018-09-14 | 2019-01-15 | 广州神马移动信息科技有限公司 | Layered approach and its device, electronic equipment, the computer-readable medium of answer |
CN109299250A (en) * | 2018-09-14 | 2019-02-01 | 广州神马移动信息科技有限公司 | Methods of exhibiting, device, storage medium and the electronic equipment of answer |
CN109460823A (en) * | 2018-09-14 | 2019-03-12 | 广州神马移动信息科技有限公司 | Construction method and its device, electronic equipment, the computer-readable medium of knowledge base |
JP2020056982A (en) * | 2018-09-30 | 2020-04-09 | アイフライテック カンパニー,リミテッド | Speech evaluation method, device, apparatus and readable storage medium |
CN109191968A (en) * | 2018-10-25 | 2019-01-11 | 重庆鲁班机器人技术研究院有限公司 | Language education robot and more educational robot langue leaning systems |
CN109903618A (en) * | 2019-03-27 | 2019-06-18 | 广东小天才科技有限公司 | Listening Training method, apparatus, equipment and storage medium |
CN111047932A (en) * | 2020-01-02 | 2020-04-21 | 上海健坤教育科技有限公司 | Voice interactive teaching system |
CN111353066B (en) * | 2020-02-20 | 2023-11-21 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN111353066A (en) * | 2020-02-20 | 2020-06-30 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN111369998B (en) * | 2020-02-28 | 2023-07-21 | 联想(北京)有限公司 | Data processing method and electronic equipment |
CN111369998A (en) * | 2020-02-28 | 2020-07-03 | 联想(北京)有限公司 | Data processing method and electronic equipment |
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 |
CN111415101B (en) * | 2020-04-16 | 2021-04-23 | 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 |
CN111639219A (en) * | 2020-05-12 | 2020-09-08 | 广东小天才科技有限公司 | Method for acquiring spoken language evaluation sticker, terminal device and storage medium |
CN111951625A (en) * | 2020-09-04 | 2020-11-17 | 中原工学院信息商务学院 | College spoken English conversation interactive system |
CN113053388A (en) * | 2021-03-09 | 2021-06-29 | 北京百度网讯科技有限公司 | Voice interaction method, device, equipment and storage medium |
CN112989012B (en) * | 2021-04-27 | 2021-08-27 | 武汉龙津科技有限公司 | Information updating method and device, electronic equipment and readable storage medium |
CN112989012A (en) * | 2021-04-27 | 2021-06-18 | 武汉龙津科技有限公司 | Information updating method and device, electronic equipment and readable storage medium |
JP7166696B1 (en) | 2022-07-07 | 2022-11-08 | 株式会社Ongli | Information processing method, program and information processing device |
JP2024008232A (en) * | 2022-07-07 | 2024-01-19 | 株式会社Ongli | Information processing method, program and information processing device |
CN115497455A (en) * | 2022-11-21 | 2022-12-20 | 山东山大鸥玛软件股份有限公司 | Intelligent voice evaluation method, system and device for oral English test |
CN116403604A (en) * | 2023-06-07 | 2023-07-07 | 北京奇趣万物科技有限公司 | Child reading ability evaluation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108154735A (en) | Oral English Practice assessment method and device | |
CN101740024B (en) | Method for automatic evaluation of spoken language fluency based on generalized fluency | |
CN103594087B (en) | Improve the method and system of oral evaluation performance | |
CN103559894B (en) | Oral evaluation method and system | |
Neri et al. | Automatic Speech Recognition for second language learning: How and why it actually works. | |
CN103151042B (en) | Full-automatic oral evaluation management and points-scoring system and methods of marking thereof | |
CN101826263B (en) | Objective standard based automatic oral evaluation system | |
CN101751919B (en) | Spoken Chinese stress automatic detection method | |
CN103065626B (en) | Automatic grading method and automatic grading equipment for read questions in test of spoken English | |
US7062441B1 (en) | Automated language assessment using speech recognition modeling | |
CN103559892B (en) | Oral evaluation method and system | |
CN104464423A (en) | Calibration optimization method and system for speaking test evaluation | |
Chen et al. | Applying rhythm features to automatically assess non-native speech | |
US9262941B2 (en) | Systems and methods for assessment of non-native speech using vowel space characteristics | |
CN101739867A (en) | Method for scoring interpretation quality by using computer | |
CN105741831A (en) | Spoken language evaluation method based on grammatical analysis and spoken language evaluation system | |
CN106782603A (en) | Intelligent sound evaluating method and system | |
CN109545184A (en) | It is a kind of that detection method and electronic equipment are recited based on voice calibration | |
CN110415725B (en) | Method and system for evaluating pronunciation quality of second language using first language data | |
CN105608960A (en) | Spoken language formative teaching method and system based on multi-parameter analysis | |
JP2015011348A (en) | Training and evaluation method for foreign language speaking ability using voice recognition and device for the same | |
KR101992370B1 (en) | Method for learning speaking and system for learning | |
CN106548787B (en) | Optimize the evaluating method and evaluating system of new word | |
CN113205729A (en) | Foreign student-oriented speech evaluation method, device and system | |
WO2019075827A1 (en) | Voice evaluation method and device |
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: 20180612 |