In a recent article published by the Smithsonian Magazine, we discover a new kind of AI which is capable of generating faces based on a voice recording. Utilizing an algorithm programmed to “think” like the human brain, the Speech2Face can accurately identify a person’s gender, race, and age, and render a face that reflects these data. Though the images being developed cannot yet be identified as a specific person, it is easy to see how this software can be utilized and abused by people with malicious intent.
Read Original Article
Click the button below if you wish to read the article on the website where it was originally published.
Click button below if you wish to read the original article offline.