MIT scientists built a neural network that can pass the ‘Audio Turing Test’

Sound is one of the building blocks which helps us understand our surroundings, and may even aid us in building up an intuitive theory of physics and how the physical world works. A new project by a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) sets out to replicate this same kind of learning in a computer. What they have created is an algorithm capable of being shown a silent video clip of an object being hit and then selecting the appropriate impact sound. Sound prediction 3 More “In order to know what sound to play, the computer has to know something about the object being struck, and about the action that produced the sound,” Andrew Owens, one of the PhD students who worked on the project, tells…


Link to Full Article: MIT scientists built a neural network that can pass the ‘Audio Turing Test’