Created by a team led by researchers from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL), Speech-2Face can produce a predicted image of someone’s face from hearing them talk for only five seconds. https://speech2face.github.io
Not I – The voice, identity and the epistemic mirage of machine learning
Not I explores the problematics at the heart of contemporary vocal forensics' use of statistical learning techniques. The work develops a form of investigative aesthetics which seeks to open up the epistemic assumptions that ground the development...
Activity Log
Join our Community to View/Add Comments.

