# Machine learning for age estimation via voice analysis

> Live situation record from CLSTR: https://clstr.news/situations/machine-learning-for-age-estimation-via-voice-analysis
> Updated: 2026-10-02T06:09:45.000Z. Sources: 26. Developments: 3.

Researchers are developing machine learning models to estimate age through vocal analysis. An initial study published in npj Aging introduced the ‘Voice Age’ model, which uses 30 seconds of recorded speech to estimate chronological age. Testing on Hebrew-speaking adults showed an average deviation of approximately four years for women and 4.4 years for men, utilizing physiological changes in the respiratory and nervous systems as indicators.

Subsequent research published in Science Advances expanded this concept into a ‘speech clock’ that analyzes acoustic and linguistic features, such as pitch, vocabulary, and speech rate. This model identifies a ‘speech age gap’ between a person’s actual age and their predicted speech age. In a study of Spanish-speaking participants across several South and Central American countries, researchers found that a speech age older than chronological age correlated with accelerated biological aging and cognitive decline. These discrepancies were notably significant in individuals with Alzheimer’s disease and various forms of dementia. While offering a non-invasive alternative to expensive medical scans, researchers note the tool requires further validation across different cultures and is not yet a formal diagnostic instrument.

Building on this, researchers at Trinity College Dublin utilized data from 2,928 Spanish-speaking participants across Argentina, Chile, Colombia, Mexico, and Peru to refine the ‘speech clock’. The model analyzes hundreds of features, including pauses, semantic precision, and emotional expression. The study found that participants with a speech age older than their chronological age showed higher associations with Alzheimer’s disease, frontotemporal dementia, and mild cognitive impairment. Additionally, the findings linked speech aging to social adversity, such as economic hardship and limited healthcare access, suggesting the tool could serve as an accessible method for monitoring cognitive health in low-resource regions.

## Claims

- Researchers developed an AI tool called a ‘speech clock’ to estimate biological age from speech patterns. (disputed by 12 sources)
- A positive ‘speech age gap’—where estimated age exceeds chronological age—is linked to cognitive impairment and dementia. (corroborated by 12 sources)
- The research was published in the journal Science Advances. (corroborated by 12 sources)
- The study analyzed 2,928 Spanish-speaking adults from Argentina, Chile, Colombia, Mexico, and Peru. (corroborated by 11 sources)
- The AI analyzes over 700 acoustic and linguistic features, including speech rate, pauses, tone, and vocabulary. (corroborated by 11 sources)
- The study included participants with Alzheimer’s disease and frontotemporal dementia. (corroborated by 11 sources)
- A research team led by Trinity College Dublin developed a machine learning model to analyze speech. (corroborated by 3 sources)

## Timeline

### 2026-10-02: Speech clock AI tool links voice patterns to biological aging

Researchers have developed an AI ‘speech clock’ that estimates biological age from voice patterns, linking speech-age gaps to dementia and cognitive decline in a study of nearly 3,000 Spanish speakers.

14 sources. https://clstr.news/cluster/ai-model-estimates-biological-age-through-speech-analysis

### 2026-09-30: Trinity College Dublin researchers develop AI ‘speech clock’ to detect cognitive decline

Scientists have developed an AI ‘speech clock’ that uses machine learning to estimate biological age and detect signs of cognitive decline, such as Alzheimer’s, through vocal and linguistic analysis.

10 sources. https://clstr.news/cluster/speech-clock-developed-to-estimate-biological-age-via-voice

### 2026-09-17: Voice Age model estimates chronological age through speech analysis

Scientists have developed ‘Voice Age’, a machine learning model that can estimate a person's chronological age using only 30 seconds of recorded speech.

2 sources. https://clstr.news/cluster/voice-age-model-estimates-chronological-age-through-speech-analysis

---
Cite as: Machine learning for age estimation via voice analysis. CLSTR, https://clstr.news/situations/machine-learning-for-age-estimation-via-voice-analysis