Transcript-Free Lightweight Detection of Alzheimer's Disease from Spontaneous Speech Using Handcrafted MFCC-Dominant Acoustic Biomarkers
2026-07-11 • Sound
SoundArtificial Intelligence
AI summaryⓘ
The authors studied how to detect Alzheimer's disease using only raw audio recordings of people speaking, without needing written transcripts or complex models. They used sound-based features like pauses and speech patterns from a set of 176 speech samples. A simple machine learning method (SVM) was able to moderately distinguish Alzheimer's patients from healthy controls. Their findings suggest audio alone can help in early screening for Alzheimer's, making it easier and cheaper to use in real-world settings. However, the best feature selection results might be a bit too optimistic since it was not fully tested on separate data.
Alzheimer's diseasespontaneous speechvoice activity detection (VAD)acoustic featuresMFCCsupport vector machine (SVM)spectro-temporal analysisfluency statisticsDementiaBank Pitt corpusmachine learning
Authors
Rashin Gholijani Farahani, Azam Bastanfard
Abstract
It is still hard to find Alzheimer's disease (AD) early, especially when neuroimaging is expensive or tools that depend on language are not available. Spontaneous speech provides a non-invasive signal; however, numerous current methodologies depend on transcripts/ASR or computationally intensive deep models. We offer a simple, audio-only baseline for detecting AD using 176 Cookie Theft recordings from the DementiaBank Pitt corpus (88 AD, 88 controls). WebRTC voice activity detection (VAD) is used to separate speech from non-speech. We take out 99 hand-crafted acoustic-temporal features, including pause and fluency statistics, spectral/prosodic descriptors, and MFCC summaries with Δ and ΔΔ. Evaluation is performed using a stringent speaker-independent GroupShuffleSplit,documenting performance across 30 iterations. A lightweight SVM with an RBF kernel gets an average AUC of 0.674 across runs. For example, a single split has an AUC of 0.742 and an accuracy of 0.657. We also present an exploratory compact-feature analysis utilizing a Top-20 subset ranked by Random Forest importance; since selection is not nested within training splits, these results may be overly optimistic and are not employed for primary conclusions (AUC 0.719). The results indicate that transcript-free spectro-temporal and fluency-related cues can facilitate speaker-independent Alzheimer's disease screening from raw audio, establishing a practical foundation for deployment-oriented research.