Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?

TL;DR

This study investigates how various environmental noises impact machine learning-based Alzheimer's detection from speech, revealing that some noises can enhance model accuracy and providing guidelines for real-world deployment.

Contribution

It offers a comprehensive analysis of noise effects on AD detection models and identifies noise types that can improve accuracy, which is a novel insight for practical applications.

Findings

Certain environmental noises improve detection accuracy by up to 4.8%.

Different noise types have varying effects on ML model performance.

Recommendations are provided for leveraging noise to enhance real-world AD detection.

Abstract

Research related to automatically detecting Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional methods. Since AD significantly affects the acoustics of spontaneous speech, speech processing and machine learning (ML) provide promising techniques for reliably detecting AD. However, speech audio may be affected by different types of background noise and it is important to understand how the noise influences the accuracy of ML models detecting AD from speech. In this paper, we study the effect of fifteen types of environmental noise from five different categories on the performance of four ML models trained with three types of acoustic representations. We perform a thorough analysis showing how ML models and acoustic features are affected by different types of acoustic noise. We show that acoustic noise is not necessarily harmful - certain types of noise are beneficial for AD detection models and help increasing accuracy by up to 4.8\%. We provide recommendations on how to utilize acoustic noise in order to achieve the best performance results with the ML models deployed in real world.