When the world gets closer.

We help you see farther.

Sign up to our expressly international daily newsletter.

blog

Prison fire in Honduras leaves 272 dead

A fire has swept through a jail in Honduras, killing at least 272 inmates.

(AP) Tegucigalpa - A forensic official in Honduras says a fire that swept through a prison has killed at least 272 inmates.

Lucy Marder, chief of forensic medicine for the prosecutors' office, gave the death count to reporters in a radio news conference early Wednesday.

The head of the national prison system, Danilo Orellana, said the fire broke out Tuesday night at a prison in the town of Comayagua, 90 miles (140 kilometers) north of the Central American country's capital, Tegucigalpa.

READ MORE

You've reached your limit of free articles.

To read the full story, start your free trial today.

Get unlimited access. Cancel anytime.

Exclusive coverage from the world's top sources, in English for the first time.

Insights from the widest range of perspectives, languages and countries.

Future

Listening For Illness: Your Voice May Soon Help Detect Health Problems

Applying Artificial intelligence to vocal cues is increasingly being used to detect a range of illnesses from COVID-19 to asthma and even depression. But such technology also comes with serious ethical concerns.

photo of a man yelling with white paint in background

What's that you say?

Guillaume de Germain Unsplash
Benoît Georges

PARIS — Thanks to artificial intelligence (AI), your voice can already be used to dictate messages to your smartphone, give commands to your Bluetooth speakers, or chat with your car's dashboard. But soon, it may be able to evaluate the state of your health by detecting respiratory (asthma, COVID-19) or neurodegenerative illnesses. It could even pick up mental health struggles, such as depression or anxiety.

The concept is simple: every pathology that affects the lungs, the heart, the brain, the muscles, or the vocal cords can lead to voice modifications. By using digital tools to analyze a recording, it must be possible to detect vocal biomarkers, the same way vocal recognition algorithms learned to understand a spoken language based on millions of sound samples.

Keep reading...Show less

You've reached your limit of free articles.

To read the full story, start your free trial today.

Get unlimited access. Cancel anytime.

Exclusive coverage from the world's top sources, in English for the first time.

Insights from the widest range of perspectives, languages and countries.

The latest