Going Beyond the Cookie Theft Picture Test: Detecting Cognitive Impairments using Acoustic Features

TL;DR

This study demonstrates that acoustic features from various standardized neuropsychological tests and random speech samples can reliably detect cognitive impairments, achieving up to 85% accuracy with advanced features.

Contribution

It extends previous work by evaluating acoustic features on multiple standardized tests and spontaneous speech, improving detection accuracy and demonstrating broader applicability.

Findings

Acoustic features can discriminate impaired from non-impaired individuals.

Wav2vec 2.0 features outperform traditional OpenSMILE features.

Achieved up to 85% classification accuracy.

Abstract

Standardized tests play a crucial role in the detection of cognitive impairment. Previous work demonstrated that automatic detection of cognitive impairment is possible using audio data from a standardized picture description task. The presented study goes beyond that, evaluating our methods on data taken from two standardized neuropsychological tests, namely the German SKT and a German version of the CERAD-NB, and a semi-structured clinical interview between a patient and a psychologist. For the tests, we focus on speech recordings of three sub-tests: reading numbers (SKT 3), interference (SKT 7), and verbal fluency (CERAD-NB 1). We show that acoustic features from standardized tests can be used to reliably discriminate cognitively impaired individuals from non-impaired ones. Furthermore, we provide evidence that even features extracted from random speech samples of the interview can be a discriminator of cognitive impairment. In our baseline experiments, we use OpenSMILE features and Support Vector Machine classifiers. In an improved setup, we show that using wav2vec 2.0 features instead, we can achieve an accuracy of up to 85%.