INTERSPEECH 2014
15th Annual Conference of the International Speech Communication Association

Singapore
September 14-18, 2014

Speech-Based Automatic and Robust Detection of Very Early Dementia

Aharon Satt (1), Ron Hoory (1), Alexandra König (2), Pauline Aalten (3), Philippe H. Robert (4)

(1) IBM Research Haifa, Israel
(2) Université Nice Sophia Antipolis, France
(3) Maastricht University Medical Center, The Netherlands
(4) CHU de Nice, France

We provide evidence to the potential use of simple spoken tasks for automatic assessment of very early dementia. Timely detection of dementia is required for effective psychological treatment and to enable patients to participate in new drug therapy research. The technology enables automatic, cheap, remote and wide-scale screening of dementia, typically a costly and complex procedure. It can aid clinicians in the diagnosis of very early dementia, as well as assessing the disease progression.
   We describe the spoken tasks, and their respective language-independent vocal feature extraction, followed by classification accuracy evaluation. We use recordings from over 60 persons, diagnosed as healthy-control (CTRL) / mild-cognitive-impairment (MCI) / early-stage-Alzheimer-disease and early-mixed-dementia (AD).
   We present a new data regularization technique to overcome data sparseness due to the limited data set size. Next, we present a comprehensive statistical analysis, showing that the suggested classifier generalizes, and revealing the role and the statistical importance of the different spoken tasks and their respective vocal features.
   We demonstrate classification accuracy of about 80% for CTRL vs. MCI and MCI vs. AD, and 87% for CTRL vs. AD, all shown to generalize. This provides an evidence for potential use for automatic detection of very early dementia.

Full Paper

Bibliographic reference.  Satt, Aharon / Hoory, Ron / König, Alexandra / Aalten, Pauline / Robert, Philippe H. (2014): "Speech-based automatic and robust detection of very early dementia", In INTERSPEECH-2014, 2538-2542.