Analyzing the Probability Density Distribution of Sustained Phoneme Voice Features in the PC-GITA Dataset for Parkinson’s Disease Identification

Pah, Nemuel Daniel and Indrawati, Veronica and Kumar, Dinesh Kant and Motin, Mohammod Abdul (2023) Analyzing the Probability Density Distribution of Sustained Phoneme Voice Features in the PC-GITA Dataset for Parkinson’s Disease Identification. In: Proceedings of the 4th International Conference on Informatics, Technology and Engineering 2023 (InCITE 2023), 14-15 September 2023, Yogyakarta.

PDF 125994390.pdf Download (946kB)

Abstract

One of the possibilities for developing computerized diag- nostic tools for Parkinson’s disease (PD) is to utilize the voice change known as Parkinsonian dysarthria. Voice features extracted from sus- tained phonemes have been statistically investigated as parameters for this purpose. However, the commonly used statistical presentation meth- ods often obscure interpretations. This paper introduces an alternative approach using probability density distribution analysis to analyze voice features. The analysis was applied to recordings of sustained phonemes from the PC-GITA dataset. The findings reveal a significant overlap between the distributions of PD and healthy subjects (HC), with PD features exhibiting a wider distribution compared to HC. This result suggests the potential use of these features to identify PD, but it should be noted that a considerable number of PD cases may have voice features similar to HC

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Parkinsonian dysarthria, voice features, probability density distribution.
Subjects:	R Medicine > R Medicine (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Engineering > Department of Electrical Engineering
Depositing User:	Eko Setiawan 194014
Date Deposited:	03 Jan 2024 08:55
Last Modified:	04 Jan 2024 03:20
URI:	http://repository.ubaya.ac.id/id/eprint/45599

Actions (login required)

View Item