Researchers use AI and audio to predict where objects will land | VentureBeat

in hive-116221 •  4 years ago 

STEEM POSTS

In a new preprint study, researchers at Carnegie Mellon University claim sound can be used to predict an object's appearance — and its motion. The coauthors created a "sound-action-vision" data set and a family of AI algorithms to investigate the interactions between audio, visuals, and movement. The results, they say, show representations derived from sound can be used to anticipate where objects will move when subjected to physical force.


Shared On DLIKE

Authors get paid when people like you upvote their post.
If you enjoyed what you read here, create your account today and start earning FREE STEEM!