MIT Researchers Taught An Algorithm to Generate Sound Based on Silent Videos

The Massachusetts Institute of Technology (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) announced quite the impressive invention on Monday: Artificial intelligence that can generate the appropriate sound when fed a silent video. While there are limitations to the software, the results indicate yet another advance in the rapidly developing field. And his comes right on the heels of IBM showing off its new music creation AI powered by the Watson supercomputer, to boot. Only when the new algorithm sees an object being hit does it properly work to determine exactly what type of sound is being “When you run your finger across a wine glass, the sound it makes reflects how much liquid is in it,” explained CSAIL PhD candidate and research paper lead author Andrew Owens to…


Link to Full Article: MIT Researchers Taught An Algorithm to Generate Sound Based on Silent Videos