Using data from thousands of individuals who suffer from certain health conditions, we can teach AI algorithms to detect the vocal patterns that are common among these patients. These vocal features or ‘vocal biomarkers’ can then help diagnose when anyone starts experiencing depressive symptoms.

“We discovered that our AI model’s results did not depend on the language the people were speaking, their age or gender, or even the part of the world they lived in,” says Seiilova-Olson. The deep signals in one’s voice transcend all these differences.