Parkinson's disease detection method based on voice context dynamic characteristics

A technology of dynamic features and Parkinson's disease, applied in speech analysis, speech recognition, diagnostic recording/measurement, etc., can solve problems such as low prediction accuracy and poor system usability

Pending Publication Date: 2021-05-18
GYENNO TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of low prediction accuracy and poor system usability caused by too few features, only static features, and artificial feature engineering in the existing speech-based Parkinson's prediction technology, this application provides a speech-base...

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
  • Parkinson's disease detection method based on voice context dynamic characteristics
  • Parkinson's disease detection method based on voice context dynamic characteristics
  • Parkinson's disease detection method based on voice context dynamic characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to express the present invention more clearly, the present invention will be further described below in conjunction with the accompanying drawings.

[0032] Parkinson's disease (Parkinson disease, PD) is a chronic progressive neurodegenerative disease, and its diagnosis is usually based on the special clinical features found in medical history and neurological examination. In the prior art, various methods are used for the diagnosis of Parkinson's disease. For example, a Parkinson's disease speech detection method based on power normalized cepstral coefficient features is disclosed. The method enhances the robustness of the extracted features, and the detection method steps: 1) set up Parkinson's disease speech database and healthy speech database; 2) carry out power normalized cepstral coefficient feature extraction to speech signal: at first speech signal is carried out preprocessing , and then use the Gammatone filter to filter to obtain the speech short-ter...

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 Parkinson's disease detection method based on voice context dynamic characteristics. The Parkinson's disease detection method comprises the following steps: collecting a voice sample; preprocessing a voice signal; extracting voice features; establishing a voice detection model; establishing a Parkinson's voice detection model by combining the voice features; and rapidly detecting the Parkinson's disease by using the Parkinson's disease voice detection model. The problems of low prediction precision and poor system availability caused by the problems of few features, only adoption of static features, artificial feature engineering and the like in the existing Parkinson's disease prediction technology based on voice are solved. The invention provides the Parkinson's disease detection method based on the voice context dynamic characteristics; the Parkinson's disease voice detection model is established by using a bidirectional long-short term memory recurrent neural network so as to quickly study and judge Parkinson's disease.

Description

technical field [0001] The invention relates to a method in the technical field of signal processing and pattern recognition, more precisely, the invention relates to a method for detecting Parkinson's disease based on dynamic features of speech context. Background technique [0002] Parkinson's disease (PD) is a common neurodegenerative disease that seriously affects human health. With the intensification of population aging, more and more patients with Parkinson's disease, and there is a trend of younger patients, the situation of diagnosis and treatment of Parkinson's disease is becoming increasingly severe. With the development of time, the symptoms of the disease become more and more serious, and it cannot be completely cured, but early intervention and treatment can relieve symptoms and improve the quality of life of patients. Since the initial symptoms of Parkinson's disease are not obvious, and there is no universally applicable standard that can quickly and accurat...

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): G10L15/06G10L15/16G10L25/03A61B5/00
CPCA61B5/4082A61B5/4803G10L15/063G10L15/16G10L25/03G10L2015/0631
Inventor 全昌勤罗志伟任康凌云陈仲略
Owner GYENNO TECH
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