Exploring an Audio‐based Approach for Early Detection of Alzheimer’s Disease using Chinese Speech Data
Hung‐Wei Lee, Chia‐ Fang Cheng, Yi‐Hsuan Wang, Ya‐Ning Chang · 2025
Read Exploring an Audio‐based Approach for Early Detection of Alzheimer’s Disease using Chinese Speech Data by Hung‐Wei Lee, Chia‐ Fang Cheng, Yi‐Hsuan Wang, Ya‐Ning Chang (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-11710581.txt.
Description
Hung-Wei Lee, Chia-Fang Cheng, Yi-Hsuan Wang, and Ya-Ning Chang build a speech-based test, published in 2025, to spot Alzheimer disease in Chinese speakers. Speech and language often worsen with the disease. Computer methods that listen to speech could screen people cheaply and might work across languages. The team used a deep learning model already trained on large amounts of speech.
Speech came from a picture description task done by eighty-one native Chinese speakers in Taiwan. The group held healthy controls and patients with early disease. Recordings were cut into six-second clips, and the groups were balanced by sampling. Sound features from the pre-trained model fed a small classifier. Test accuracy passed eighty-one percent, with matched scores for catching cases and avoiding false alarms. The authors say the model is promising and want to learn which sound traits drive its choices.
Catalog record
| CREATOR | Hung‐Wei Lee, Chia‐ Fang Cheng, Yi‐Hsuan Wang, Ya‐Ning Chang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |