Related Experiment Video
Updated: Jul 17, 2025
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
Automatic Detection of Putative Mild Cognitive Impairment from Speech Acoustic Features in Mandarin-Speaking Elders
Rumi Wang1, Chen Kuang2, Chengyu Guo2
1Rehabilitation Medicine Department, Speech and Language Pathology Therapy Section, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China.
Background:
To date, the reliable detection of mild cognitive impairment (MCI) remains a significant challenge for clinicians. Very few studies investigated the sensitivity of acoustic features in detecting Mandarin-speaking elders at risk for MCI, defined as "putative MCI" (pMCI).
Objective:
This study sought to investigate the possibility of using automatically extracted speech acoustic features to detect elderly people with pMCI and reveal the potential acoustic markers of cognitive decline at an early stage.
Methods:
Forty-one older adults with pMCI and 41 healthy elderly controls completed four reading tasks (syllable utterance, tongue twister, diadochokinesis, and short sentence reading), from which acoustic features were extracted automatically to train machine learning classifiers. Correlation analysis was employed to evaluate the relationship between classifier predictions and participants' cognitive ability measured by Mini-Mental State Examination 2.
Results:
Classification results revealed that some temporal features (e.g., speech rate, utterance duration, and the number of silent pauses), spectral features (e.g., variability of F1 and F2), and energy features (e.g., SD of peak intensity and SD of intensity range) were effective predictors of pMCI. The best classification result was achieved in the Random Forest classifier (accuracy = 0.81, AUC = 0.81). Correlation analysis uncovered a strong negative correlation between participants' cognitive test scores and the probability estimates of pMCI in the Random Forest classifier, and a modest negative correlation in the Support Vector Machine classifier.
Conclusions:
The automatic acoustic analysis of speech could provide a promising non-invasive way to assess and monitor the early cognitive decline in Mandarin-speaking elders.
Insights
Speech analysis can detect early cognitive decline in Mandarin-speaking elders. Acoustic features accurately predict putative mild cognitive impairment (pMCI), offering a non-invasive assessment tool.
Area of Science:
- Gerontology
- Speech Science
- Computational Linguistics
Background:
- Detecting mild cognitive impairment (MCI) in elders is challenging.
- Few studies explore acoustic features for identifying Mandarin-speaking elders at risk for MCI (pMCI).
Purpose of the Study:
- Investigate using automatic speech acoustic features to detect elderly individuals with pMCI.
- Identify early acoustic markers of cognitive decline.
Main Methods:
- Collected speech data from 41 pMCI patients and 41 controls performing reading tasks.
- Extracted acoustic features and trained machine learning classifiers.
- Correlated classifier predictions with Mini-Mental State Examination 2 scores.
Main Results:
- Temporal, spectral, and energy acoustic features effectively predicted pMCI.
- Random Forest classifier achieved 81% accuracy and 0.81 AUC.
- Strong negative correlation found between cognitive scores and pMCI probability.
Conclusions:
- Automatic acoustic speech analysis is a promising non-invasive method.
- This approach can assess and monitor early cognitive decline in Mandarin-speaking elders.
