Linear classification in speech-based objective differential diagnosis of parkinsonism - Archive ouverte HAL Access content directly
Conference Papers Year :

Linear classification in speech-based objective differential diagnosis of parkinsonism

(1) , (1) , (2) , (3)
1
2
3

Abstract

Parkinsonism refers to Parkinsons disease (PD) and Atyp-ical parkinsonian syndromes (APS). Speech disorder is a common and early symptom in Parkinsonism which makes speech analysis a very important research area for the purpose of early diagnosis. Most of research have however focused on discrimination between PD and healthy controls. Such research does not take into account the fact that PD and APS syndromes are very similar in early disease stages. The main problem that has to be addressed first is then differential diagnosis: discrimination between PD and APS and within APS. This paper is a continuation of an earlier pioneer work in differential diagnosis where we mostly address the machine learning problem due to the small amount of training data. We show that classical linear and generalized linear models can provide interpretable and robust classifiers in term of accuracy and generalization ability.
Fichier principal
Vignette du fichier
Daoudi-Final.pdf (200.21 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01696617 , version 1 (30-01-2018)

Identifiers

  • HAL Id : hal-01696617 , version 1

Cite

Gongfeng Li, Khalid Daoudi, Jiri Klempir, Jan Rusz. Linear classification in speech-based objective differential diagnosis of parkinsonism. IEEE-ICASSP - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Canada. ⟨hal-01696617⟩

Collections

INRIA INRIA2 ANR
202 View
335 Download

Share

Gmail Facebook Twitter LinkedIn More