Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT

TL;DR

This study evaluates three machine learning models utilizing acoustic, linguistic, and BERT-based features for early detection of Alzheimer's dementia from spontaneous speech, aiming for cost-effective and rapid diagnosis.

Contribution

It compares the effectiveness of acoustic, linguistic, and BERT-based features in classifying Alzheimer's dementia using the ADReSS 2021 dataset.

Findings

BERT-based features achieved high classification accuracy.

Linguistic features from transcripts improved detection performance.

Acoustic features alone provided moderate classification results.

Abstract

Alzheimers disease is a fatal progressive brain disorder that worsens with time. It is high time we have inexpensive and quick clinical diagnostic techniques for early detection and care. In previous studies, various Machine Learning techniques and Pre-trained Deep Learning models have been used in conjunction with the extraction of various acoustic and linguistic features. Our study focuses on three models for the classification task in the ADReSS (The Alzheimers Dementia Recognition through Spontaneous Speech) 2021 Challenge. We use the well-balanced dataset provided by the ADReSS Challenge for training and validating our models. Model 1 uses various acoustic features from the eGeMAPs feature-set, Model 2 uses various linguistic features that we generated from auto-generated transcripts and Model 3 uses the auto-generated transcripts directly to extract features using a Pre-trained BERT and TF-IDF. These models are described in detail in the models section.