Longitudinal Monitoring and Detection of Alzheimer's Type Dementia from Spontaneous Speech Data

A method for detection of Alzheimer's type dementia though analysis of vocalisation features that can be easily extracted from spontaneous speech is presented. Unlike existing approaches, this method does not rely on transcriptions of the patient's speech. Tests of the proposed method on a data set of spontaneous speech recordings of Alzheimer's patients (n=214) and elderly controls (n=184) show that accuracy of 68% can be achieved with a Bayesian classifier operating on features extracted through simple algorithms for voice activity detection and speech rate tracking.