CN107578778A - A kind of method of spoken scoring - Google Patents
A kind of method of spoken scoring Download PDFInfo
- Publication number
- CN107578778A CN107578778A CN201710705635.5A CN201710705635A CN107578778A CN 107578778 A CN107578778 A CN 107578778A CN 201710705635 A CN201710705635 A CN 201710705635A CN 107578778 A CN107578778 A CN 107578778A
- Authority
- CN
- China
- Prior art keywords
- learner
- text
- sample
- pronunciation
- audio file
- 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
Abstract
The invention discloses a kind of method of spoken scoring, this method comprises the following steps：1) teacher uploads or recorded the audio file of segment standard pronunciation；2) audio file of RP is identified as corresponding text by system, and this text is stored, as received text；3) learner's opening steps 1), 2) in RP audio file, listen to RP, voluntarily record the pronunciation of oneself, and upload to inside system；4) sample of learner is pronounced file identification into corresponding sample word by system, and is stored；5) otherness between system documents and sample text, the data of quantization is drawn, finally feed back to learner.The present invention provides a kind of pattern of oral test, and learner oneself can be allowed to pronounce, and the sample pronunciation then provided with teacher is contrasted, finally judge its order of accuarcy and standard degree, and corresponding fraction is given, allow learner to understand the pronunciation situation of oneself, so as to autonomous learning.
Description
Technical field
The present invention relates to a kind of method of spoken scoring.
Background technology
At present, whether standard mainly carries out artificial judgement to it to the pronunciation for verbal learning person by teacher, by
Learner reads passage, then by teacher come it is subjective judge its pronunciation whether accurately, standard.The workload ratio of this mode
It is huger, a teacher can be gone within the unit interval judge student be it is conditional, while learner also can not at any time with
Ground is judged that learner can not accomplish self-teaching, it is necessary to which both sides are pronounced and tested and assessed in real time.
The content of the invention
It is an object of the invention to provide a kind of method of spoken scoring, solves shortcoming existing for prior art.
The present invention adopts the following technical scheme that realization：
A kind of method of spoken scoring, it is characterised in that this method comprises the following steps：1) teacher uploads or recorded one
The audio file of segment standard pronunciation；2) audio file of RP is identified as corresponding text by system, and by this text
Stored, as received text；3) learner's opening steps 1), 2) in RP audio file, listen to standard hair
Sound, voluntarily records the pronunciation of oneself, and uploads to inside system；4) sample of learner is pronounced file identification into corresponding by system
Sample word, and stored；5) otherness between system documents and sample text, the data of quantization are drawn, most
Learner is fed back to eventually.
Further, in step 2), system is identified the audio file of RP by calling speech recognition algorithm
Into corresponding text.
Further, in step 4), system knows the sample pronunciation file of learner by calling speech recognition algorithm
Not into corresponding sample word, and stored.
Further, in step 5), system is by Text Clustering Algorithm, the difference between documents and sample text
Property, the data of quantization are drawn, finally feed back to learner.
The method have the benefit that：A kind of pattern of oral test is provided, learner oneself can be allowed to pronounce, so
The sample pronunciation provided afterwards with teacher is contrasted, and finally judges its order of accuarcy and standard degree, and gives corresponding fraction,
Learner is allowed to understand the pronunciation situation of oneself, so as to autonomous learning.
Embodiment
By the following description to embodiment, it will more contribute to public understanding of the invention, but can't should be by Shen
Given specific embodiment of asking someone is considered as the limitation to technical solution of the present invention, any definition to part or technical characteristic
Be changed and/or make form to overall structure and immaterial conversion is regarded as what technical scheme was limited
Protection domain.
A kind of method of spoken scoring, this method comprise the following steps：1) teacher uploads or recorded segment standard pronunciation
Audio file；2) audio file of RP is identified as corresponding text by system, and this text is stored, and is made
For received text；3) learner's opening steps 1), 2) in RP audio file, listen to RP, voluntarily record
The pronunciation of oneself, and upload to inside system；4) sample of learner is pronounced file identification into corresponding sample word by system,
And stored；5) otherness between system documents and sample text, draws the data of quantization, finally feeds back to study
Person.In the present embodiment, the audio file of RP is identified as corresponding text by step 2) by calling speech recognition algorithm
This；In step 4) by calling speech recognition algorithm, the sample of learner is pronounced file identification into corresponding sample word, and
Stored；By Text Clustering Algorithm in step 5), the otherness between documents and sample text, the number of quantization is drawn
According to finally feeding back to learner.
Using currently advanced speech recognition technology, (University of Science and Technology's news fly the present invention, Baidu both provides substantial amounts of speech recognition
Technology API), the pronunciation of learner is identified as corresponding word (can be identified as Chinese, English etc.), while teacher is provided
RP be also identified as corresponding word.Using the identification word of RP as reference hierarchy, learner is pronounced institute
The word of identification sample as a comparison, using the computerized algorithm based on Clustering Analysis of Text, calculate grapholect and sample text
Similarity between word, so as to judge the pronunciation of learner whether standard, and give corresponding quantization.In current speech recognition
In technology, if pronunciation is identical, its word identified is also identical.The difference of received text and sample text word,
Also it is exactly the difference between RP and learner's pronunciation, so as to quantify the standard of learner's pronunciation.Standard is sent out
The process that the audio file of sound is identified as corresponding text is：Phonetic characters string is obtained, grammer point is created according to phonetic characters string
Analysis tree, syntactic analysis tree is for judging whether phonetic characters string can be identified and parsed for the first time in the phonetic characters string
The lemma attribute information of at least one lemma, semantic-parse tree is created according to the result identified for the first time, speech analysis tree root is according to solution
The lemma attribute information of analysis obtains pre-stored attribute information to create voice identification result.The present embodiment by speech recognition and
Text cluster contrast algorithm is combined to calculate pronunciation standard quantized data；Spoken learn can be calculated by the way that computer is large batch of
The pronunciation standard degree of habit person, the artificial treatment of teacher is reduced, improve study and work efficiency.
Certainly, the present invention can also have other various embodiments, in the case of without departing substantially from spirit of the invention and its essence,
Those skilled in the art can be made according to the present invention it is various it is corresponding change and deformation, but these it is corresponding change and
Deformation should all belong to the protection domain of appended claims of the invention.
Claims (4)
- A kind of 1. method of spoken scoring, it is characterised in that this method comprises the following steps：1) teacher uploads or recorded one section The audio file of RP；2) audio file of RP is identified as corresponding text by system, and this text is entered Row storage, as received text；3) learner's opening steps 1), 2) in RP audio file, listen to RP, The pronunciation of oneself is voluntarily recorded, and is uploaded to inside system；4) sample of learner is pronounced file identification into corresponding by system Sample word, and stored；5) otherness between system documents and sample text, the data of quantization are drawn, finally Feed back to learner.
- 2. the method for spoken scoring according to claim 1, it is characterised in that in step 2), system is by calling language Sound recognizer, the audio file of RP is identified as corresponding text.
- 3. the method for spoken scoring according to claim 1, it is characterised in that in step 4), system is by calling language Sound recognizer, the sample of learner is pronounced file identification into corresponding sample word, and stored.
- 4. the method for spoken scoring according to claim 1, it is characterised in that in step 5), system is gathered by text Class algorithm, the otherness between documents and sample text, the data of quantization are drawn, finally feed back to learner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710705635.5A CN107578778A (en) | 2017-08-16 | 2017-08-16 | A kind of method of spoken scoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710705635.5A CN107578778A (en) | 2017-08-16 | 2017-08-16 | A kind of method of spoken scoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107578778A true CN107578778A (en) | 2018-01-12 |
Family
ID=61034243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710705635.5A Pending CN107578778A (en) | 2017-08-16 | 2017-08-16 | A kind of method of spoken scoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107578778A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108538126A (en) * | 2018-04-18 | 2018-09-14 | 上海本荣信息技术有限公司 | Compare the security knowledge learning detection method and its detecting system of the re-reading voice of word |
| CN108682437A (en) * | 2018-05-18 | 2018-10-19 | 网易乐得科技有限公司 | Information processing method, device, medium and computing device |
| CN108922289A (en) * | 2018-07-25 | 2018-11-30 | 深圳市异度信息产业有限公司 | A kind of scoring method, device and equipment for Oral English Practice |
| 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 |
| CN109086387A (en) * | 2018-07-26 | 2018-12-25 | 上海慧子视听科技有限公司 | A kind of audio stream methods of marking, device, equipment and storage medium |
| CN110136721A (en) * | 2019-04-09 | 2019-08-16 | 北京大米科技有限公司 | A kind of scoring generation method, device, storage medium and electronic equipment |
| CN110148413A (en) * | 2019-05-21 | 2019-08-20 | 科大讯飞股份有限公司 | Speech evaluating method and relevant apparatus |
| CN112259083A (en) * | 2020-10-16 | 2021-01-22 | 北京猿力未来科技有限公司 | Audio processing method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101197084A (en) * | 2007-11-06 | 2008-06-11 | 安徽科大讯飞信息科技股份有限公司 | Automatic spoken English evaluating and learning system |
| 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 |
| CN103198726A (en) * | 2013-04-23 | 2013-07-10 | 李华 | English learning equipment |
| CN103928023A (en) * | 2014-04-29 | 2014-07-16 | 广东外语外贸大学 | Voice scoring method and system |
| CN104347071A (en) * | 2013-08-02 | 2015-02-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for generating oral test reference answer |
| 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 |
| CN106205634A (en) * | 2016-07-14 | 2016-12-07 | 东北电力大学 | A kind of spoken English in college level study and test system and method |
| CN106710587A (en) * | 2016-12-20 | 2017-05-24 | 广东东田数码科技有限公司 | Speech recognition data pre-processing method |
-
2017
- 2017-08-16 CN CN201710705635.5A patent/CN107578778A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101197084A (en) * | 2007-11-06 | 2008-06-11 | 安徽科大讯飞信息科技股份有限公司 | Automatic spoken English evaluating and learning system |
| 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 |
| CN103198726A (en) * | 2013-04-23 | 2013-07-10 | 李华 | English learning equipment |
| CN104347071A (en) * | 2013-08-02 | 2015-02-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for generating oral test reference answer |
| 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 |
| CN103928023A (en) * | 2014-04-29 | 2014-07-16 | 广东外语外贸大学 | Voice scoring method and system |
| CN106205634A (en) * | 2016-07-14 | 2016-12-07 | 东北电力大学 | A kind of spoken English in college level study and test system and method |
| CN106710587A (en) * | 2016-12-20 | 2017-05-24 | 广东东田数码科技有限公司 | Speech recognition data pre-processing method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108538126A (en) * | 2018-04-18 | 2018-09-14 | 上海本荣信息技术有限公司 | Compare the security knowledge learning detection method and its detecting system of the re-reading voice of word |
| CN108682437A (en) * | 2018-05-18 | 2018-10-19 | 网易乐得科技有限公司 | Information processing method, device, medium and computing device |
| CN108682437B (en) * | 2018-05-18 | 2020-12-11 | 网易乐得科技有限公司 | Information processing method, device, medium and computing equipment |
| CN108922289A (en) * | 2018-07-25 | 2018-11-30 | 深圳市异度信息产业有限公司 | A kind of scoring method, device and equipment for Oral English Practice |
| CN109086387A (en) * | 2018-07-26 | 2018-12-25 | 上海慧子视听科技有限公司 | A kind of audio stream methods of marking, device, equipment and storage medium |
| 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 |
| 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 |
| CN110136721A (en) * | 2019-04-09 | 2019-08-16 | 北京大米科技有限公司 | A kind of scoring generation method, device, storage medium and electronic equipment |
| CN110148413A (en) * | 2019-05-21 | 2019-08-20 | 科大讯飞股份有限公司 | Speech evaluating method and relevant apparatus |
| CN110148413B (en) * | 2019-05-21 | 2021-10-08 | 科大讯飞股份有限公司 | Voice evaluation method and related device |
| CN112259083A (en) * | 2020-10-16 | 2021-01-22 | 北京猿力未来科技有限公司 | Audio processing method and device |
| CN112259083B (en) * | 2020-10-16 | 2024-02-13 | 北京猿力未来科技有限公司 | Audio processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107578778A (en) | A kind of method of spoken scoring | |
| CN101105939B (en) | Sonification guiding method | |
| CN102034475B (en) | Method for interactively scoring open short conversation by using computer | |
| US9087519B2 (en) | Computer-implemented systems and methods for evaluating prosodic features of speech | |
| Gao et al. | A study on robust detection of pronunciation erroneous tendency based on deep neural network. | |
| US9652991B2 (en) | Systems and methods for content scoring of spoken responses | |
| Blanchard et al. | A study of automatic speech recognition in noisy classroom environments for automated dialog analysis | |
| CN104217713A (en) | Tibetan-Chinese speech synthesis method and device | |
| CN102253976B (en) | Metadata processing method and system for spoken language learning | |
| Bogach et al. | Speech processing for language learning: A practical approach to computer-assisted pronunciation teaching | |
| US20110213610A1 (en) | Processor Implemented Systems and Methods for Measuring Syntactic Complexity on Spontaneous Non-Native Speech Data by Using Structural Event Detection | |
| CN109949799B (en) | Semantic parsing method and system | |
| WO2021074721A2 (en) | System for automatic assessment of fluency in spoken language and a method thereof | |
| CN111192659A (en) | Pre-training method for depression detection and depression detection method and device | |
| Duan et al. | A Preliminary study on ASR-based detection of Chinese mispronunciation by Japanese learners | |
| Kostuchenko et al. | The evaluation process automation of phrase and word intelligibility using speech recognition systems | |
| Koudounas et al. | Italic: An italian intent classification dataset | |
| Tsiakoulis et al. | Dialogue context sensitive HMM-based speech synthesis | |
| CN110010123A (en) | English phonetic word pronunciation learning evaluation system and method | |
| Gutkin et al. | FonBund: A library for combining cross-lingual phonological segment data | |
| Liu et al. | A maximum entropy based hierarchical model for automatic prosodic boundary labeling in mandarin | |
| Michaux et al. | The production and perception of L1 and L2 Dutch stress | |
| CN114241835A (en) | Student spoken language quality evaluation method and device | |
| Díez et al. | Non-native speech corpora for the development of computer assisted pronunciation training systems | |
| Iriondo et al. | Objective and subjective evaluation of an expressive speech corpus |
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: 20180112 |