Automatic detection of mild cognitive impairment from spontaneous speech using ASR

TLDR

Mild Cognitive Impairment, a prodromal stage of Alzheimer’s disease, is hard to diagnose, but recent studies indicate it subtly alters patients’ speech. The study aims to automate the extraction of acoustic features for MCI detection by applying automatic speech recognition. Using ASR, the authors obtain phonetic‑level segmentation and annotation, compute features such as speech rate, handle filled pauses as hesitation indicators, and train machine‑learning classifiers to distinguish MCI from controls. The ASR‑based approach achieved an F1 score of 85.3, only slightly lower than manual feature extraction, suggesting it is promising for automated MCI screening.

Abstract

Mild Cognitive Impairment (MCI), sometimes regarded as a prodromal stage of Alzheimer’s disease, is a mental disorder that is difficult to diagnose. However, recent studies reported that MCI causes slight changes in the speech of the patient. Our starting point here is a study that found acoustic correlates of MCI, but extracted the proposed features manually. Here, we automate the extraction of the features by applying automatic speech recognition (ASR). Unlike earlier authors, we use ASR to extract only a phonetic level segmentation and annotation. While the phonetic output allows the calculation of features like the speech rate, it avoids the problems caused by the agrammatical speech frequently produced by the targeted patient group. Furthermore, as hesitation is the most important indicator of MCI, we take special care when handling filled pauses, which usually correspond to hesitation. Using the ASR-based features, we employ machine learning methods to separate the subjects with MCI from the control group. The classification results obtained with ASR-based feature extraction are just slightly worse that those got with the manual method. The F1 value achieved (85.3) is very promising regarding the creation of an automated MCI screening application.