Automatic speech analysis for early Alzheimer's disease diagnosis

Saeideh Mirzaei (1, 2, 3) , Mounim El Yacoubi (4, 1, 2, 3) , Sonia Garcia-Salicetti (4, 1, 2, 3) , Jérôme Boudy (4, 1, 2, 3) , Christian Kahindo Senge Muvingi (1, 2, 3) , Victoria Cristancho-Lacroix (5, 6) , Hélène Kerhervé (5, 6) , Anne-Sophie Rigaud Monnet (5, 6)

1 TSP - EPH - Département Electronique et Physique
2 SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
3 CNRS - Centre National de la Recherche Scientifique
4 ARMEDIA-SAMOVAR - ARMEDIA
5 AP-HP - Hôpital Cochin Broca Hôtel Dieu [Paris]
6 EA 4468 - Maladie d'Alzheimer : marqueurs génétiques et vasculaires, neuropsychologies

We extract voice features from read speech of patients diagnosed as having Alzheimer's disease and mild cognitive impairment versus healthy control group at the AP-HP Broca Hospital. Two classification methods are used to evaluate the efficiency of these features. Finally, a wrapper feature selection method as exploits both methods is also evaluated

Mots clés: Speech analysis; Alzheimer; K-NN; MCI; SVM; Feature selection

Domaines: Traitement du signal et de l'image [eess.SP]

Saeideh Mirzaei, Mounim El Yacoubi, Sonia Garcia-Salicetti, Jérôme Boudy, Christian Kahindo Senge Muvingi, et al.. Automatic speech analysis for early Alzheimer's disease diagnosis. JETSAN 2017 : 6e Journées d'Etudes sur la Télésanté, May 2017, Bourges, France. pp.114 - 116. ⟨hal-01618834⟩