跳到正文
原文
Nature 综合主刊· Gemma Conroy·· 2026-09-30AI 评分53

Nature 报道:语音时钟可依据声音特征评估衰老速度

AI ‘speech clock’ assesses how fast you’re ageing from your voice

AI 导读

研究团队开发出一种语音时钟,通过音高、语速等数百项语音特征估算个体年龄,并计算其与实际年龄之间的语音年龄差。该研究记录了阿根廷、智利、哥伦比亚、墨西哥和秘鲁的 2928 名西班牙语使用者,涵盖健康人群与轻度认知障碍、阿尔茨海默病或其他痴呆症患者,从录音中提取 700 多项随衰老和痴呆变化的语音特征训练模型。

正文
Older adult speaking into a handheld microphone with a bright background.

A new ‘speech clock’ analyses characteristics of a person’s voice, including pitch, to assess how quickly they are ageing.Credit: Cheschhh/Getty

A ‘speech clock’ developed by scientists can predict how well a person is ageing based on characteristics of their voice and how they talk. The clock draws on hundreds of vocal features, including pitch and talking speed, to estimate a person’s age.

‘Inflammation clock’ can reveal body’s biological age

Using the clock, the scientists calculated a ‘speech age gap’ for individuals: the difference between a person’s age as predicted by the speech clock and their chronological age. Large speech age gaps were strongly associated with cognitive issues in people, such as those that arise in dementia, suggesting that the new clock could be a useful tool for determining whether a person is growing older faster than expected.

The findings were published today in the journal Science Advances1.

“We can see a huge predictive value, just with a very simple four minutes of speech recordings,” says neuroscientist Agustín Ibáñez at Adolfo Ibáñez University in Santiago, who is a co-author of the study.

The speech clock could be a boon for tracking the ageing of people in low-resource regions, because it doesn’t rely on expensive or invasive technologies, such as brain scans and blood tests, says Jed Meltzer, a cognitive neuroscientist who specializes in language at the University of Toronto in Canada and was not involved in the study. “It is a very impressive piece of work.”

Predicting age with speech

Ageing clocks often use biological markers to assess how rapidly a person’s body is declining. For instance, ‘brain clocks’ use signatures from neuroimaging to determine whether an individual’s brain is ageing faster than their chronological age suggests. And ‘epigenetic clocks’ look at the patterns of methyl tags on a person’s DNA to estimate their biological age. But so far, researchers hadn’t developed a clock based on speech. Such a tool could offer a useful window into the ageing process because speaking involves a “huge amount of brain work”, Ibáñez says.

How quickly are you ageing? What molecular ‘clocks’ can tell you about your health

To create their clock, Ibáñez and his colleagues recorded 2,928 Spanish speakers from Argentina, Chile, Colombia, Mexico and Peru while they completed various speech tasks. The group was a mixture of healthy individuals and people with mild cognitive impairment, Alzheimer’s disease or other forms of dementia. The researchers used machine-learning algorithms to extract more than 700 speech characteristics that can change with ageing and dementia, such as pitch and vocabulary range, from the audio recordings. They then used these data to train their speech-clock model to predict each study participant’s age.

Overall, the speech clock could distinguish between healthy individuals and those with some form of cognitive impairment. The clock, for instance, categorized the speech of people with cognitive issues as being older than would be expected for their chronological age. Healthy people were generally assessed as having speech that matched their chronological age.

来源:Nature 综合主刊 · nature.com