Automatic spoken English evaluating and learning system

A learning system and spoken language technology, applied in the fields of pattern recognition, digital signal processing and voice signal processing, can solve the problems of insufficient teacher resources and a large number of manpower

Inactive Publication Date: 2008-06-11
IFLYTEK CO LTD
View PDF0 Cites 61 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the existing oral English teaching and evaluation, the present invention designs and develops an automatic oral English evaluation that has good interactivity, is not limited by location, can avoid shortage of teacher resources, and solve practical limitations such as requiring a large amount of manpower. learning system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic spoken English evaluating and learning system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] The automatic oral English evaluation and learning system includes a detection part, a scoring part and a guiding part. Detection part: According to the scoring parameters of the students' speech under the standard speech model, and on the basis of fully considering the relevant prior knowledge of linguistics, the machine learning method is used to judge the mistakes of the learners for the manual marking of typical speech errors. location and its error type.

[0043] Scoring part: Combining with the assessment standard of oral English level, using digital signal theory and computer voice processing technology to calculate various scoring parameters of students' voices relative to standard voices, and transforming these scoring parameters into voices according to the pre-trained mapping model The scoring of the machine makes the scoring results of the machine as close as possible to the scoring results of human experts.

[0044] Guidance section: Give corrective and po...

Embodiment 2

[0072] The automatic oral English evaluation and learning system includes a detection part, and the detection of the oral pronunciation part includes the following steps:

[0073] 〔1〕Establishment of standard speaker corpus:

[0074] 1) Find a standard speaker;

[0075] 2) Design the recording text according to the requirements of oral English learning and the principle of phoneme balance;

[0076] 3) Ask the standard speaker to record against the recorded text;

[0077] 4) The recording files after recording are stored in a form associated with the text, so that the corresponding text can be quickly found according to the name of each recording file.

[0078] 〔2〕Collection of oral evaluation corpus: Record students' oral pronunciation, save the recorded text, and associate the recorded file name with the recorded text.

[0079] 〔3〕Annotation of the oral evaluation corpus: the correctness of the pronunciation of the phonemes in each word is marked in detail.

[0080] 〔4〕Es...

Embodiment 3

[0089] The automatic oral English evaluation and learning system includes a detection part and a scoring part, and the detection part and the scoring part include the following steps:

[0090] 〔1〕Establishment of standard speaker corpus:

[0091] 1) Find a standard speaker;

[0092] 2) Design the recording text according to the requirements of oral English learning and the principle of phoneme balance;

[0093] 3) Ask the standard speaker to record against the recorded text;

[0094] 4) The recording files after recording are stored in a form associated with the text, so that the corresponding text can be quickly found according to the name of each recording file.

[0095] 〔2〕Collection of oral evaluation corpus: Record students' oral pronunciation, save the recorded text, and associate the recorded file name with the recorded text.

[0096] 〔3〕Annotation of the oral evaluation corpus: Three experts are invited to independently score each oral evaluation recording, and mark...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an automation oral English evaluation and learning system, comprising a testing part, an grading part and a guiding part; the invention is realized by the following procedures that: (1) a standard pronunciation people corpus is set up; (2) an oral English evaluation corpus is collected; (3) the oral English evaluation corpus is labeled; (4) a standard sound acoustic model is built; (5) the error detection parameter of the sound is calculated; (6) an error detection mapping model for error detection parameter-toward pronunciation error labeled by experts is created; (7) an evaluation parameter-toward expert grading mapping model is created; (8) the oral error is guided to be corrected. The invention has the advantages of good interactivity and no limit on place, and overcomes the shortage of the teacher resource and resolves the limitation problem in the practicability aspect that more teachers are needed for teaching.

Description

technical field [0001] The invention relates to the fields of pattern recognition, digital signal processing and voice signal processing. Specifically, it is a system that uses computers to analyze and process the speech signals of English oral test or learners, and then automatically scores, points out wrong pronunciations, and guides learning for wrong pronunciations. Background technique [0002] With the development of global economic integration, English, as an international common language, is showing its important role more and more. The demand for comprehensive English ability of talents in various industries is increasingly urgent. However, the current English teaching in China cannot well meet the needs of the development of the situation, especially the students' English listening and speaking ability needs to be further improved. Due to the lack of oral English teachers, it is difficult for English learners to obtain a one-to-one English learning environment, s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G09B5/00G09B7/00G09B19/06
Inventor 姚志强胡国平刘庆升胡郁刘庆峰吴晓如陈涛陈燕王仁华
Owner IFLYTEK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap