Artificial Intelligence Generates Humans’ Faces Based on Their Voices

Publication Title
Publication/Creation Date
June 12 2019
Meilan Solly (creator)
Massachusetts Institute Of Technology (MIT) (contributor)
Persuasive Intent

A new neural network developed by researchers from the Massachusetts Institute of Technology is capable of constructing a rough approximation of an individual’s face based solely on a snippet of their speech, a paper published in pre-print server arXiv reports.

The team trained the artificial intelligence tool—a machine learning algorithm programmed to “think” much like the human brain—with the help of millions of online clips capturing more than 100,000 different speakers. Dubbed Speech2Face, the neural network used this dataset to determine links between vocal cues and specific facial features; as the scientists write in the study, age, gender, the shape of one’s mouth, lip size, bone structure, language, accent, speed and pronunciation all factor into the mechanics of speech.

HCI Platform
Location on Body
Not On The Body
Marketing Keywords

Date archived
June 14 2019
Last edited
June 14 2019
How to cite this entry
Meilan Solly. (June 12 2019). "Artificial Intelligence Generates Humans’ Faces Based on Their Voices". Smithsonian. The Smithsonian Magazine. Fabric of Digital Life.