Science Advances<\/a>.<\/p>\nUsing hundreds of acoustic and linguistic features, researchers at Trinity College Dublin developed a machine learning \u201cspeech clock\u201d that can estimate a person\u2019s biological age. The gap between a person\u2019s actual age and predicted age was found to be associated with multiple independent markers of biological aging, brain health, cognition, social adversity, and dementia.<\/p>\n
\u201cOur voice appears to contain much more information about aging than we previously recognized,\u201d said Agustin Ibanez, PhD, professor of brain health at the Global Brain Health Institute and School of Medicine at Trinity College Dublin and senior author of the study. \u201cIt captures both the passage of chronological time and signals coming from cognition, the brain, systemic biology, and even our accumulated social environment. This raises the possibility that something as simple and accessible as speech clocks could eventually complement much more expensive measures of aging.\u201d<\/p>\n
The study involved 2,928 Spanish-speaking participants from Argentina, Chile, Colombia, Mexico and Peru, including healthy adults as well as people with mild cognitive impairment, Alzheimer\u2019s disease and different forms of frontotemporal dementia. A speech age estimate was generated for each individual by combining hundreds of features, including speech rate and pauses, pitch, emotional expression, vocabulary, semantic precision and the amount and organization of verbal output.<\/p>\n
People whose speech appeared older than expected for their chronological age also tended to show signs of aging assessed through structural and functional neuroimaging, as well as independent measures of epigenetic aging based on changes in DNA methylation. Larger speech age gaps were linked to poorer global cognition, executive function, functional abilities and several forms of memory.<\/p>\n
The combined speech-age measure performed better at distinguishing clinical groups than individual acoustic or linguistic characteristics considered separately. Overall, healthy participants had the smallest speech age gaps, while larger gaps were observed among participants with Alzheimer\u2019s disease and frontotemporal dementia. Among those with Alzheimer\u2019s, speech was also associated with higher levels of the blood biomarker p-tau217.<\/p>\n
Unlike MRI scans, blood tests and specialized molecular assessments, speech can be recorded remotely, repeatedly and non-invasively at relatively low cost. That could make speech-based measures particularly relevant in communities with limited access to advanced medical technologies. However, further longitudinal research, including studies in other languages, cultures and more natural speaking environments, will be needed before the speech clock can become a diagnostic test for dementia.<\/p>\n
\u201cThe broader finding is nevertheless striking in that a person\u2019s voice may provide a remarkably compact readout of multiple dimensions of aging,\u201d said Ibanez. \u201cFrom chronological age to brain aging, epigenetic aging, cognition, Alzheimer\u2019s-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 aging\u2014potentially transforming an everyday human behavior into a window onto the biology of aging.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"Credit: Just_Super \/ Getty Images Plus The way people speak may reveal important clues about their brain health…\n","protected":false},"author":2,"featured_media":641152,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[2012,12015,5963,2926,80520,103,61,60,3966,12637,2876],"class_list":["post-641151","post","type-post","status-publish","format-standard","has-post-thumbnail","category-health","tag-alzheimers-disease","tag-biomarkers","tag-brain-health","tag-dementia","tag-digital-biomarkers","tag-health","tag-ie","tag-ireland","tag-news-features","tag-patient-care","tag-topics"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/641151","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=641151"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/641151\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/641152"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=641151"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=641151"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=641151"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"A](\"https:\/\/www.newsbeep.com\/ie\/wp-content\/uploads\/2026\/10\/IPM_Oct2025_GettyImages-2213994114_ChatBubbles-696x435.jpg\" "\\"getty_2213994114\\"\/")
Credit: Just_Super \/ Getty Images Plus<\/p>\n