A forced gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing

Moro Velázquez, Laureano and Gómez García, Jorge Andrés and Godino Llorente, Juan Ignacio and Villalba López, Jesús and Rusz, Jan and Shattuck-Hufnagel, Stephanie and Dehak, Najim (2019). A forced gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing. "Biomedical Signal Processing and Control", v. 48 ; pp. 205-220. ISSN 1746-8094. https://doi.org/10.1016/j.bspc.2018.10.020.

Description

Title: A forced gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing
Author/s:
  • Moro Velázquez, Laureano
  • Gómez García, Jorge Andrés
  • Godino Llorente, Juan Ignacio
  • Villalba López, Jesús
  • Rusz, Jan
  • Shattuck-Hufnagel, Stephanie
  • Dehak, Najim
Item Type: Article
Título de Revista/Publicación: Biomedical Signal Processing and Control
Date: February 2019
ISSN: 1746-8094
Volume: 48
Subjects:
Freetext Keywords: Speech processing; Machine learning; Parkinson's Disease; Phoneme; Forced alignment
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Otro
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (7MB) | Preview

Abstract

Literature evidences the existence of hypokinetic dysarthria in parkinsonian patients and, consequently, the objective characterization of the dysarthric signs associated to the articulatory aspect of speech can be used to detect Parkinson?s Disease (PD) providing clinicians with new tools to support the clinical diagnosis. However, no work has analyzed in detail the importance of the different phonemes in the automatic detection of PD from the speech. This work proposes new approaches for this detection by using new classification schemes that allow to compare independently the different phonetic units of patients and controls employed during several speechtasks. Three different parkinsoniancorpora were used allowing cross-validationand cross-corpora trials. The results of cross-validation trials (k-folds) provided accuracies between 81% and 94%, with AUC between 0.87 and 0.97 depending on the corpus, while cross-corpora trials yielded accuracies between 66% and 76% with AUC between 0.76 and 0.87. These results suggest that PD affects to the articulatory sequence as a whole, influencing more clearly phonetic units requiring a higher narrowing of the vocal tract. Additionally, text-dependent utterances are considered as the recommended speech task for the detection of PD in this type of schemes as these allow to compare more precisely the phonetic units of patients and controls. Lastly, this work discusses the existence of a glass ceiling in the accuracy of the systems for the automatic detection of PD using speech, concluding that this is below 95% for most of the cases.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainDPI2017-83405-RUnspecifiedUnspecifiedBiomarcadores para el diagnóstico y la evaluación de la enfermedad de Parkinson basados en estudios multimodales de voz y oculografía
Government of SpainTEC2012-38630-C04-01UnspecifiedUnspecifiedDetección del trastorno neurológico por medio de correlatos de la fonación obtenidos por modelado inverso a partir de la fuente glótica

More information

Item ID: 64433
DC Identifier: https://oa.upm.es/64433/
OAI Identifier: oai:oa.upm.es:64433
DOI: 10.1016/j.bspc.2018.10.020
Official URL: https://www.sciencedirect.com/science/article/pii/S1746809418302842
Deposited by: Memoria Investigacion
Deposited on: 20 Dec 2020 08:34
Last Modified: 02 Mar 2021 23:30
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM