A Statistical Classification Method for the Distribution of Articulation Movement Abnormalities in Dysarthria

A technique for dysarthria, statistical classification, applied in the field of information processing
CN109360645BActive Publication Date: 2021-06-11TAIYUAN UNIV OF TECH
8 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TAIYUAN UNIV OF TECH
Publication Date
2021-06-11

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention belongs to the technical field of information processing, in particular to a statistical classification method for abnormal distribution of articulation dysphonia. Solve the problem of pronunciation movement statistics of articulatory organs, including the following steps, S100~draw the distribution map of the pronunciation movement intervals of the tip of the tongue, the middle of the tongue, and the root of the tongue in the front, back, left and right, and up and down directions; S300~fit the distribution of the pronunciation movement interval through the lognormal distribution; S400~fit through the normal distribution, and use the 2.58 standard deviation of the normal distribution as the threshold to calculate respectively The proportion of dysarthria patients and normal people with abnormal pronunciation data. The present invention starts from the front, back, left and right, and up and down directions of the tongue space movement, and studies the distribution of pronunciation movement intervals in the three directions of the speaker, and further counts dysarthria patients and normal people according to the proportion of abnormal pronunciation movement intervals.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of information processing, in particular to a statistical classification method for abnormal distribution of articulation dysphonia. Background technique

[0002] With the development of signal processing technology, especially the interdisciplinary application of machine learning methods, scientific problems in the medical field can intersect with signal processing technology. Pathological phonetics is an in-depth and specific analysis of the acoustic and pronunciation characteristics of the speech corresponding to different diseases. It not only summarizes the laws theoretically, but also proposes different targeted strategies and measures in order to help patients do rehabilitation in practical applications. . The most widely used pathological voice databases are the Massachusetts Eye and Ear Hospital MEEI pathological voice database and the NKI-CCRT database of the University of Amsterdam. The TORGO da...

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