From audio recordings of clinical-subject interactions, we determine the spoken language bio-markers that are associated with cognitive impairment (e.g. Dementia and Alzheimer's Disease).

Dementia is a particularly debilitating condition costing $200 billion in the USA alone, and coming second only to spinal-cord injuries and terminal cancer in the severity of its effects. Laboratory tests and imaging scans are used to evaluate cognitive health, but are costly to acquire and process.  This motivates the exploration of measures that are easier to record and are less invasive,  specifically, speech. In collaboration with Prof. Rhoda Au and the Framingham Heart Study, we look to extract and identify audio and text features that are most predictive of cognitive impairment from audio recordings of 5,000 subjects undergoing neuropsychological evaluations (composed of memory, recall, and comprehension tests), collected over the past 10 years.

Research Areas

Impact Areas