Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Parkinsonism detection method and detection system based on voice

A Parkinson's disease and detection method technology, which is applied in speech analysis, speech recognition, special data processing applications, etc., can solve problems such as high cost, time-consuming, and labor-intensive

Inactive Publication Date: 2016-03-30
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a Parkinson's detection method based on voice, in order to solve the unfavorable factors such as time-consuming, labor-intensive and high cost brought by traditional solutions

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
  • Parkinsonism detection method and detection system based on voice
  • Parkinsonism detection method and detection system based on voice
  • Parkinsonism detection method and detection system based on voice

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 and figure 2 As shown, there is a voice collection device corresponding to each tested person. The voice collection device can be a smart terminal such as a smart phone or a tablet computer, and the specific voice emitted by the tested person is collected through software, and then the voice signal processing system from the voice Extract the features related to Parkinson's disease, record all the features into a vector in the order of extraction, and then the SVM classification system uses the Parkinson's training sample set provided by professional institutions to train the SVM classifier and classify the above vectors. According to the classification results, it is judged whether the detected person suffers from Parkinson's disease.

Embodiment 2

[0058] Figure 3 to Figure 5 The flow of the voice-based Parkinson's disease detection method is shown.

[0059] This method is mainly divided into three parts, one is recording specific audio: this method requires the tester to record a continuous vowel / a / in a relatively quiet environment; the other is speech pathology feature extraction: after obtaining the test voice, you can Use speech signal processing technology to extract pathological features related to Parkinson's in speech (fundamental frequency, Jitter, Shimmer, etc.), these features can distinguish sick patients from healthy people; the third is SVM classification: the classifier will follow the pre-learned Algorithmic model to classify samples to determine whether they have Parkinson's.

[0060] Record a specific voice: the tester records a continuous and peaceful vowel / a / , and should try to use professional recording equipment in a quiet environment when recording the audio. The recorded voice should not be t...

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 Parkinsonism detection method and detection system based on voice, belonging to the technical field of signal processing and machine learning. The Parkinsonism detection method based on voice can extract the characteristics related with Parkinsonism from the acquired voice of a detected people, and can record all the characteristics in a vector according to the sequence of extraction and use an SVM classifier to classify the vector so that the classified result is the detection result. The Parkinsonism detection system based on voice comprises a voice acquisition apparatus, a voice signal processing system and an SVM classification system, wherein the voice signal processing system extracts the characteristics related with Parkinsonism from the voice; and the SVM classification system trains the SVM classifier according to the Parkinsonism dataset collected by a professional institute, and uses the SVM classifier to classify the voice characteristics of the detected people so as to determine whether the detected people suffers from Parkinsonism. The processing process of the Parkinsonism detection method and detection system based on voice can be completed through analysis of a computer software; and the Parkinsonism detection method and detection system based on voice can solve the problems that the period for clinical observation of Parkinsonism is long and the cost is high, and have the advantages of being real time, being efficient, being low in cost and being simple and reliable in operation in the extreme environment.

Description

technical field [0001] The invention relates to the technical fields of signal processing and machine learning, in particular to a voice-based Parkinson's disease detection method and detection system. Background technique [0002] Human speech is produced by the physiological movement of the human vocal organs under the control of the brain. Human vocal organs are composed of three parts: ①The lungs and trachea produce the air source; ②The larynx and vocal cords form the glottis; ③The vocal tract is composed of the pharynx, oral cavity, and nasal cavity, all of which are controlled by the central nervous system. Parkinson's disease in the Department of Neurology will damage the neurons of the cerebral cortex and affect the vocal organs, making the voices of patients and healthy people different, so there is a certain theoretical basis for using voice to detect Parkinson's. [0003] At present, the Parkinson's detection method in the medical field is generally clinical obse...

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): G10L15/02G10L15/06G10L17/04G06F19/00
CPCG06F19/34G10L15/02G10L15/063G10L17/04
Inventor 李云叶晓江吕艳洁季薇
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com