express gazette logo
The Express Gazette
Wednesday, September 30, 2026

Your Voice May Be a Window Into Aging and Cognitive Health, Study Suggests

A new 'speech clock' tool uses machine learning to analyze voice patterns, potentially offering an accessible way to assess biological age and cognitive decline.

Health • 2 hours ago
Your Voice May Be a Window Into Aging and Cognitive Health, Study Suggests

Subtle changes in vocal patterns could offer insights into a person's age and how well they are aging, according to a study by an international team of researchers. The scientists developed a machine learning tool, dubbed a 'speech clock,' capable of analyzing hundreds of voice features to estimate a person's chronological age.

The study, which analyzed the voices of nearly 3,000 adults aged 18 to 88 across five countries, found that the difference between a person's estimated 'speech age' and their actual age could indicate their biological age—or how rapidly their body is aging. If an individual's speech age was older than their chronological age, they were more likely to be experiencing cognitive decline.

Dr. Agustin Ibanez, a senior study author and professor at Trinity College Dublin's Global Brain Health Institute, stated that voices contain more information about aging than previously understood, capturing signals from cognition, biology, and social environment. He suggested that accessible tools like speech clocks, potentially combined with biomarkers, could supplement more expensive aging assessment methods.

Vocal Changes and Aging

Researchers observed that older voices often exhibit slower speech, flatter pitch, and reduced emotional inflection compared to younger voices, which tend to be faster and more concise. These vocal changes are associated with the natural aging process, where vocal folds can lose elasticity and lung capacity may decrease. These physiological changes typically begin around the age of 50.

The study, published in the journal Science Advances, involved 2,928 participants, including healthy individuals and those diagnosed with Alzheimer's disease or other forms of dementia. Participants with Alzheimer's were, on average, older than the healthy group.

The machine learning model identified six key speech elements: timing, pitch, emotion, vocabulary, correctness, and the number of words needed to convey an idea. Individuals whose speech age exceeded their chronological age demonstrated poorer cognitive skills and memory compared to those whose ages aligned.

Speech Clock and Cognitive Health

In the second phase of the study, researchers correlated the 'speech age gap' with brain scan data. Larger speech age gaps were linked to a higher likelihood of dementia. Specifically, when the model predicted an older age based on speech patterns, individuals were more prone to exhibiting poorer memory, overall cognition, and executive function.

For participants diagnosed with Alzheimer's disease, a greater speech age gap correlated with higher levels of plasma p-tau217, a biomarker associated with the disease. Alzheimer's and dementia can impact speech due to difficulties with word-finding, articulation, and swallowing.

The researchers propose that the 'speech clock' could serve as an accessible alternative for assessing biological age, particularly in regions with limited access to invasive testing methods like blood samples and MRI scans. However, they emphasized that further research is necessary before widespread implementation.

'The broader finding is nevertheless striking in that a person’s voice may provide a remarkably compact readout of multiple dimensions of aging,' Ibanez noted. He added that if validated across diverse populations, speech analysis could become a scalable tool for monitoring healthy and accelerated aging, transforming an everyday behavior into a diagnostic insight.


Sources