Cognitive Decline Detection using DLB Extraction Pipelines

The Prediction and Recognition of Cognitive Decline through Spontaneous Speech (PROCESS) Signal Processing Grand Challenge focuses on detecting dementia by analyzing spontaneous speech production. The challenge proposes a classification task to distinguish between subjects categorized as healthy controls, mild cognitive impairment, and dementia. Our team tackled this task by leveraging Digital Linguistic Biomarkers (DLBs) extracted from speech. Our system outperformed over 100 competing systems, earning us first place in the classification task.