Speech barrier multi-dimensional measurement system and method based on real-time speech multi-dimensional modeling

A real-time voice and measurement system technology, applied in diagnostic recording/measurement, medical science, sensors, etc., and can solve problems such as few characteristic parameters

Active Publication Date: 2016-01-27
SHANGHAI TAIYIGE REHABILITATION SERVICE CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention overcomes the shortcomings of single-dimensional measurement and less targeted characteristic parameters in the existing speech impairment measurement system, and proposes a speech impairment multi-dimensional measurement system and method based on real-time speech multi-dimensional modeling technology

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
  • Speech barrier multi-dimensional measurement system and method based on real-time speech multi-dimensional modeling
  • Speech barrier multi-dimensional measurement system and method based on real-time speech multi-dimensional modeling
  • Speech barrier multi-dimensional measurement system and method based on real-time speech multi-dimensional modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Embodiment 1: speech intelligibility measurement

[0042] In this embodiment, the microphone is used to record the voice read by the user through linear input, so as to collect the phoneme data of the voice segment. There are several scoring points in the test speech material, which can be used to judge speech clarity, such as figure 1 shown. After the full text was judged and divided, computing device 2 calculated the percentage of the correct number in the speech and the total judged points. Parameters such as speech intelligibility, such as figure 2 shown. The judging device 3 compares each parameter value of the user with the standard numerical range corresponding to its age and gender according to the user's information. If the parameter value is within the standard numerical range, it means that the user's speech intelligibility ability is normal; If the parameter value is lower than the standard value range, it means that there is a speech disorder, and the ...

Embodiment 2

[0043] Embodiment 2: Speech fluency measurement

[0044] The test voice material is respectively in the form of rising tone, falling tone and rising and falling tone, and the collection device 1 collects the voice that the user sends according to the test voice material to obtain the supersegmental phoneme data, and the computing device 2 calculates the supersegmental phoneme data. Calculate the standard deviation of the fundamental frequency to obtain the parameter value of the rate of pitch change.

[0045] In this embodiment, the pitch-increasing measurement is taken as an example. The test voice material is a vowel / i--i / that is raised from the smallest pitch to the largest pitch as far as possible in the form of a rising pitch. The user pronounces according to the test voice material, and the collection device 1 Acquire phoneme data in the speech signal. Preferably, during the collection process of the collection device 1, the user's voice is pre-processed such as pre-f...

Embodiment 3

[0049] Embodiment 3: Unvoiced and voiced conversion ability measurement

[0050] The ratio of unvoiced and voiced sounds mainly refers to the ratio of the duration of unvoiced sounds to the duration of voiced sounds in a speech segment. The collection device 1 collects the mixed-type segmental phoneme data from the user's speech segment, and the computing device 2 performs unvoiced and voiced discrimination on the mixed-type segmental phoneme data to obtain the duration of the unvoiced part and the voiced part, and divides the duration of the former With the latter duration, a parameter value of a mixed segmental phoneme is obtained, that is, the ratio of unvoiced and voiced sounds.

[0051] This implementation takes the voice material "cuff" (kao4) issued by the user as an example, which contains both unvoiced and voiced sounds. After the phoneme data is collected by the collection device 1, the computing device 2 discriminates the unvoiced and voiced sounds, detects and mar...

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 discloses a multi-dimensional voice disorder measuring system based on the multi-dimensional real-time voice modeling technology. The system comprises a collecting device, a calculating device and a judging device, wherein the collecting device collets phoneme data, the calculating device calculates parameter values of the phoneme data, the standard numerical range of the phoneme data is stored in the judging device, the parameter values are compared according to the standard numerical range, voice disorder does not exist if the parameter values are within the standard numerical range, the voice disorder exists if the parameter values are lower than or higher than the standard numerical range, and the type of the existed voice disorder is judged. Real-time detection processing and real-time voice multi-dimensional modeling are carried out on voice and rhinolalia, so segmental phoneme data, supersegmental phoneme data, mixed segmental phoneme data and separted segmental phoneme are evaluated, numerous pointed multi-dimensional characteristic parameters are increased, and therefore evaluation of voice disorder is more comprehensive and precise. The invention further discloses a multi-dimensional voice disorder measuring method based on the multi-dimensional real-time voice modeling technology.

Description

technical field [0001] The invention belongs to the field of speech measurement, in particular to a multidimensional measurement system and method for speech impairment based on real-time speech multidimensional modeling technology. Background technique [0002] Speech impairment is an important part of speech impairment, so the assessment of speech impairment is also an important module in the assessment of speech impairment. At present, the assessment of speech impairment in China includes two aspects: subjective assessment and objective measurement; subjective assessment is mainly aimed at specific test speech materials, and by analyzing the scoring results of patients reading specific test speech materials, the patient's continuous speech clarity and other results can be obtained , and compared with the results of the normal population, so as to realize the subjective evaluation of the patient's speech function; the objective measurement includes the measurement of supra...

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 Patents(China)
IPC IPC(8): A61B5/00
Inventor 高栋黄昭鸣李宁王恒民莫思霞
Owner SHANGHAI TAIYIGE REHABILITATION SERVICE 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