Alzheimer’s Disease (AD) is nowadays the most common form of dementia . Automatic detection can help to identify symptoms at early stages, so that preventive actions can be carried out . Non-intrusive techniques based on spoken data are crucial for the development of AD automatic detectionsystems . In this light, this paper is presented as a contribution to the ADReSSChallenge, aiming at improving AD automatic detection from spontaneous speech . To this end, recordings from 108 participants, which are age-, gender-, and ADcondition-balanced, have been used as training set to perform two different tasks: classification into AD/non-AD conditions, and regression over theMini-Mental State Examination (MMSE) scores . Both tasks have been performedextracting 28 features from speech — based on prosody and voice quality — and51 features from transcriptions

Author(s) : Mireia Farrús, Joan Codina-Filbà

Links : PDF - Abstract

Code :


Keywords : ad - features - automatic - disease - speech -

Leave a Reply

Your email address will not be published. Required fields are marked *