Descripción
|
|
---|---|
Literature documents the impact of Parkinson?s Disease (PD) on speech but no study has analyzed in detail the importance of the distinct phonemic groups for the automatic identifcation of the disease. This study presents new approaches that are evaluated in three diferent corpora containing speakers sufering from PD with two main objectives: to investigate the infuence of the diferent phonemic groups in the detection of PD and to propose more accurate detection schemes employing speech. The proposed methodology uses GMM-UBM classifers combined with a technique introduced in this paper called phonemic grouping, that permits observation of the diferences in accuracy depending on the manner of articulation. Cross-validation results reach accuracies between 85% and 94% with AUC ranging from 0.91 to 0.98, while cross-corpora trials yield accuracies between 75% and 82% with AUC between 0.84 and 0.95, depending on the corpus. This is the frst work analyzing the generalization properties of the proposed approaches employing cross-corpora trials and reaching high accuracies. Among the diferent phonemic groups, results suggest that plosives, vowels and fricatives are the most relevant acoustic segments for the detection of PD with the proposed schemes. In addition, the use of text-dependent utterances leads to more consistent and accurate models. | |
Internacional
|
Si |
JCR del ISI
|
Si |
Título de la revista
|
Scientific Reports |
ISSN
|
2045-2322 |
Factor de impacto JCR
|
3,998 |
Información de impacto
|
|
Volumen
|
9.19066 |
DOI
|
10.1038/s41598-019-55271-y |
Número de revista
|
|
Desde la página
|
1 |
Hasta la página
|
16 |
Mes
|
SIN MES |
Ranking
|