Automatic grading method and automatic grading equipment for read questions in test of spoken English
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An automatic scoring and spoken language technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of different evaluation, subjective evaluation, and high cost of manual evaluation
Active Publication Date: 2013-04-24
INST OF ACOUSTICS CHINESE ACAD OF SCI +1
View PDF2 Cites 50 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Manual scoring is a traditional scoring method, but there are many problems that are not easy to solve, such as the shortage of rater resources, the high cost of manual evaluation, and the subjective scoring. may also be scored differently for the impact of
Especially for ultra-large-scale evaluation, manual evaluation has been difficult to meet its needs
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
no. 4 example
[0094] In the fourth embodiment, the present invention provides a kind of spoken English reading aloud automatic scoring equipment, it is characterized in that, comprises:
[0095] A module for preprocessing the input speech, including framing processing;
[0096] A module for extracting speech features;
[0097] Using the linear grammatical network and acoustic model built by reading the text, the phonetic feature vector sequence is forced to be aligned to obtain the information of each phoneme segmentation point;
[0098] A module for calculating the posterior probability of each phoneme according to the information of each phoneme segmentation point;
[0099] A module for extracting multi-dimensional scoring features based on the posterior probability of phonemes;
[0100] According to the scoring features and manual scoring information, use the support vector regression method to train the nonlinear regression model, so as to use the nonlinear regression model to score t...
no. 5 example
[0101] In the fifth embodiment, the present invention provides a kind of spoken English reading automatic scoring equipment, it is characterized in that, comprises:
[0102] A module for preprocessing the input speech, including framing processing;
[0103] The extraction method extracts a module of speech features;
[0104] Using the linear grammatical network and acoustic model built by reading the text, the phonetic feature vector sequence is forced to be aligned, and the module for obtaining the information of each phoneme segmentation point;
[0105] A module for calculating the posterior probability of each phoneme according to the information of each phoneme segmentation point;
[0106] A module for extracting multi-dimensional scoring features based on the posterior probability of phonemes;
[0107] A module that uses this nonlinear regression model to score spoken English reading aloud based on scoring features.
[0108] Details of various aspects of the third, fou...
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
Login to view more
Abstract
The invention provides an automatic grading method and automatic grading equipment for read questions in a test of spoken English. According to the automatic grading method, preprocessing is carried out on input voice; the preprocessing comprises framing processing; phonetic feature is extracted from the preprocessed voice; by means of a linear grammar network and an acoustic model set up by reading texts, phonetic feature vector order is forcedly aligned to acquire information of the each break point of each phoneme; according to the information of the each break point of each phoneme, the posterior probability of each phoneme is calculated; based on the posterior probability of each phoneme, multi-dimensional grading characteristics are extracted; and based on the grading characteristics and manual grading information, a nonlinear regression model is trained by means of a support vector regression method, so that the nonlinear regression model is utilized to grade on reading of spoken English. The grading model is trained by means of expert scoring data, and therefore a result of machining grading is guaranteed not to deviate from a manual grading result in statistics, and the high simulation of a computer on the expert grading is achieved.
Description
technical field [0001] The invention belongs to the technical field of language test automatic scoring, in particular, the invention relates to a method for automatic evaluation of reading aloud questions in spoken English tests taken by non-native English test takers. Background technique [0002] As people pay more and more attention to oral English, at present, oral English test has become an important part of most English proficiency examinations. The increasing scale of the speaking test requires a large number of candidates' speaking data to be scored, which requires a lot of human resources. Manual scoring is a traditional scoring method, but there are many problems that are not easy to solve, such as the shortage of rater resources, the high cost of manual evaluation, and the subjective scoring. may also be scored differently. Especially for ultra-large-scale evaluation, manual evaluation has been difficult to meet its needs. Therefore, a machine scoring method th...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more