Multi‐dimensional Feature Extraction Technology of Spontaneous Speech Based on Machine Learning: Early Identification of Alzheimer's Disease

Quan Chen, Yatian Li, Ying Wang, Yiming Li, Jingyi Gao, Nan Chen, Jingnan Wu, Ran Li · 2025

Read Multi‐dimensional Feature Extraction Technology of Spontaneous Speech Based on Machine Learning: Early Identification of Alzheimer's Disease by Quan Chen, Yatian Li, Ying Wang, Yiming Li, Jingyi Gao, Nan Chen, Jingnan Wu, Ran Li (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11716725.txt.

Description

Quan Chen and seven co-authors published a study in 2025 on spotting Alzheimer's disease early from the way people speak. Speech changes appear early in the disease, while standard pen-and-paper tests depend on the scorer and can miss subtle signs. The team built a system that learns from both the sound of speech and its meaning.

Volunteers with normal thinking, mild impairment, or mild disease took a speech-based screening test with picture learning and recall tasks. Models trained on sound features and word features were then combined by voting. The combined system reached about ninety-two percent accuracy. Long silences during delayed recall stood out as a strong warning sign.

Catalog record

CREATORQuan Chen, Yatian Li, Ying Wang, Yiming Li, Jingyi Gao, Nan Chen, Jingnan Wu, Ran Li
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE2 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11716725

Browse the full library · About the Tower of Babel