Feature selection for spontaneous speech analysis to aid in Alzheimer's disease diagnosis: A fractal dimension approach. (March 2015)

• Record Type: Journal Article
• Authors: López-de-Ipiña, Karmele; Solé-Casals, Jordi; Eguiraun, Harkaitz; Alonso, J.B.; Travieso, C.M.; Ezeiza, Aitzol; Barroso, Nora; Ecay-Torres, Miriam; Martinez-Lage, Pablo; Beitia, Blanca
• Is Part Of: Computer speech & language. Volume 30(2015)
• Page Start: 43
• Page End: 60
• Publication Date: 2015-03
• Subjects: Nonlinear speech processing -- Alzheimer's disease diagnosis -- Spontaneous speech -- Fractal dimensions; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2014.08.002
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: Alzheimer's disease (AD) is the most prevalent form of degenerative dementia; it has a high socio-economic impact in Western countries. The purpose of our project is to contribute to earlier diagnosis of AD and allow better estimates of its severity by using automatic analysis performed through new biomarkers extracted through non-invasive intelligent methods. The method selected is based on speech biomarkers derived from the analysis of spontaneous speech (SS). Thus the main goal of the present work is feature search in SS, aiming at pre-clinical evaluation whose results can be used to select appropriate tests for AD diagnosis. The feature set employed in our earlier work offered some hopeful conclusions but failed to capture the nonlinear dynamics of speech that are present in the speech waveforms. The extra information provided by the nonlinear features could be especially useful when training data is limited. In this work, the fractal dimension (FD) of the observed time series is combined with linear parameters in the feature vector in order to enhance the performance of the original system while controlling the computational cost.