A new study published in the international journal, Science Advances, has said that a machine-learning tool called a “speech clock” can estimate a person’s age by analysing hundreds of features of their speech.
The study included 2,928 Spanish-speaking participants from Argentina, Chile, Colombia, Mexico and Peru. The participants included healthy adults as well as people with mild cognitive impairment, Alzheimer’s disease and different forms of frontotemporal dementia.
Researchers compared speech-age estimates with brain scans, DNA-based measures of biological ageing, cognitive assessments and blood biomarkers.
They found that a larger speech age gap was associated with older-appearing brain structure and function, as well as accelerated ageing measured by three independent DNA-methylation clocks. These clocks estimate biological ageing by examining chemical changes in DNA that accumulate over time.
The association extended to thinking and memory. Participants with greater speech-age acceleration tended to have poorer overall cognition, executive function, everyday functioning and performance on several memory tests. The relationship was also seen in some cognitive tasks that did not depend directly on language, suggesting that the findings may reflect broader changes in brain health rather than simply difficulty speaking, said the study.
The speech measure also differed across clinical groups. Healthy participants generally had the smallest speech age gaps, while larger gaps were seen among people with Alzheimer’s disease and frontotemporal dementia.
In people with Alzheimer’s, the measure was associated with higher levels of plasma p-tau217, a blood biomarker linked to Alzheimer’s-related brain changes. The combined speech-age measure also distinguished clinical groups better than individual speech features considered separately.
One of the more revealing findings was the link between speech ageing and social circumstances.
The researchers found that a larger speech age gap was associated with a more adverse social exposome — the combined effect of factors such as education, financial circumstances, food insecurity, access to healthcare and early-life experiences.
This suggests that the way people age may be shaped by more than biological processes alone. Lifelong social and economic conditions can influence health, access to care and opportunities, and may also be reflected in cognitive functioning.
“Our voice appears to contain much more information about ageing than we previously recognised,” said Agustin Ibanez, professor of brain health at the Global Brain Health Institute and Trinity College Dublin’s School of Medicine, and senior author of the study.
“It captures both the passage of chronological time and signals coming from cognition, the brain, systemic biology, and even our accumulated social environment,” he said.
The findings are particularly relevant to dementia research, where access to advanced diagnostic facilities and specialist assessments can be limited. Speech can be recorded remotely and repeatedly, without blood sampling or expensive imaging equipment.
However, the researchers emphasised that the speech clock is not yet a diagnostic test for dementia. The study was primarily cross-sectional, meaning that it cannot establish whether an older-appearing speech profile predicts who will subsequently develop cognitive decline or dementia. Longitudinal studies, validation in additional languages and cultures, and testing in more naturalistic speech settings will be required before clinical implementation, they added.
“The broader finding is nevertheless striking in that a person’s voice may provide a remarkably compact readout of multiple dimensions of ageing," pointed out Prof. Ibanez.
“From chronological age to brain ageing, epigenetic ageing, cognition, Alzheimer’s-related pathology, social exposures, and dementia phenotypes, information traditionally obtained through very different and often expensive measurements appears to converge, at least partly, in the way we speak."
“If confirmed longitudinally and across populations, speech could ultimately become one of the most scalable tools for monitoring healthy and accelerated ageing—potentially transforming an everyday human behaviour into a window onto the biology of ageing," he added.
