Method for automatic evaluation based on generalized fluent spoken language fluency

A fluency and spoken language technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of poor correlation between manual scoring, single inspection index, and slow manual scoring.

Active Publication Date: 2010-06-16
IFLYTEK CO LTD
View PDF0 Cites 81 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems of slow manual scoring, poor comprehensiveness and non-uniform scale in the existing spoken language test, especially the spoken English test, as well as the single inspection index and poor correlation with manual s...

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
  • Method for automatic evaluation based on generalized fluent spoken language fluency
  • Method for automatic evaluation based on generalized fluent spoken language fluency
  • Method for automatic evaluation based on generalized fluent spoken language fluency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0120] Refer to attached Figure 1-6 Shown:

[0121] The specific implementation of the fluency automatic evaluation system is as follows: figure 1 As shown, the dotted line module labels correspond to steps 1-5 in the implementation manner, figure 2 It is a detailed description of steps 1 and 2, that is, the offline part of the system, including data preparation and various model training; image 3 It is a specific elaboration of the acceptability characteristics of the extracted pronunciation content in step 4-2; Figure 4 It is a specific elaboration of the posterior probability score of the neural network in step 4-3; Figure 5 It is a specific elaboration on the method of extracting heavy reading and weak reading in step 4-3; Figure 6 It is a specific elaboration on the establishment of language models in the repetitive and self-correcting feature extraction in steps 4-4.

[0122] 1. If figure 2 As shown, the pronunciation data collected for training the fluency ...

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 a method for automatic evaluation based on generalized fluent spoken language fluency, which comprises the following steps of: acquiring speech data according to different ages and spoken language levels by using a speech input device; adopting an evaluating model based on characteristics of the generalized fluency and the machine learning training fluency; configuring a speech recognition system with corresponding parameters according to scripts of different subjects and genders of enunciators in the speech data; performing quantification on speech speed coherence, content understanding, advanced skills and reconstruction standard characteristics in the speech data to comprehensively extract the characteristics of the fluency from the speech data from the angle of expert assessment and evaluation; and adopting a decision tree method in regression fitting analysis and data mining to detect faults of abnormal fluency and grade and diagnose the fluency. The acquired score of the machine fluency can reach the level close to that of grading experts, and the relativity index exceeds that of 2 to 3 of general 5 experts; besides, the method has a high speed, and can be embedded into a spoken language automatic evaluation system to serve as an important module to evaluate fluency indexes in pronunciation quality.

Description

technical field [0001] The invention belongs to the field of speech recognition, and relates to a method for merging multiple fluency features based on speech recognition to obtain scores and combining rules for diagnosis. Background technique [0002] A number of oral scoring studies have shown that fluency and accuracy are two important indicators for evaluating the quality of oral pronunciation. Taking English as an example, the traditional oral English test score mainly uses manual comprehensive inspection of the above two indicators to obtain the overall score of the examinee. This method has the following disadvantages: 1) The speed is slow, and it is necessary to basically listen to the pronunciation for reviewing a section of pronunciation , and then review according to the teacher's experience and syllabus requirements; in a large-scale exam, if the number of people exceeds 100,000, the teacher's workload is very complicated; 2) The comprehensiveness is poor, and 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
no application Login to view more
IPC IPC(8): G10L11/00G10L15/00G10L15/06G10L19/032G10L25/60G10L25/69
Inventor 徐波黄申梁家恩高鹏王士进李鹏
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