Publication detail

Parkinson's Disease Detection based on Emotions during Speech

SKIBIŃSKA, J. BURGET, R.

Original Title

Parkinson's Disease Detection based on Emotions during Speech

Type

conference paper

Language

English

Original Abstract

One of the early syptoms of Parkinson's Disease is so-called hypomimia. This paper introduces an authomatic method, which can objectively detect PD. The method is based on analysis of emotion changes during pronunciation defined speech exercises. We achieved balanced accuracy 69 % using XGBoost algorithm. As the exercise we proposed to use a Czech tongue twister - the difficult to pronounce sentence. The features can be explained and thus it can be used in clinical practice. We identified that the most valuable emotion for PD detection in this case is fear.

Keywords

machine learning, Parkinson's Disease

Authors

SKIBIŃSKA, J.; BURGET, R.

Released

14. 10. 2020

Publisher

IEEE Xplore

Location

Brno, Czech Republic

ISBN

978-1-7281-9282-6

Book

2020 12TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT 2020)

Pages from

124

Pages to

130

Pages count

7

URL

http://ieeeexplore.ieee.org/abstract/documet/9222446

BibTex

@inproceedings{BUT167267,
  author="Justyna {Skibińska} and Radim {Burget}",
  title="Parkinson's Disease Detection based on Emotions during Speech",
  booktitle="2020 12TH INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS AND WORKSHOPS (ICUMT 2020)",
  year="2020",
  pages="124--130",
  publisher="IEEE Xplore",
  address="Brno, Czech Republic",
  doi="10.1109/ICUMT51630.2020.9222446",
  isbn="978-1-7281-9282-6",
  url="http://ieeeexplore.ieee.org/abstract/documet/9222446"
}