<!doctype html public "-//W3C//DTD W3 HTML//EN">
<html><head><style type="text/css"><!--
blockquote, dl, ul, ol, li { padding-top: 0 ; padding-bottom: 0 }
--></style><title>Portraits Based On Someone's
Voice</title></head><body>
<div><a
href=
"https://gizmodo.com/an-algorithm-generated-eerily-accurate-portraits-based-1835327568"><u><b><span
></span>An Algorithm Generated Eerily Accurate Portraits Based Only On
Someone's Voic<font size="+1">e</font></b></u></a></div>
<div><font size="+3"><b><br></b></font></div>
<div>MIT researchers published a paper last month called <a
href="https://arxiv.org/pdf/1905.09773.pdf">Speech2Face: Learning the
Face Behind a Voice which explores how an algorithm can generate
a face based on a short audio recording of that person. It's not an
exact depiction of the speaker, but based on images in the paper, the
system was able to create an image of a front-facing face with a
neutral expression with accurate gender, race, and age.<br>
</a></div>
<div><a
href=
"https://gizmodo.com/an-algorithm-generated-eerily-accurate-portraits-based-1835327568"><span
></span
>https://gizmodo.com/an-algorithm-generated-eerily-accurate-portraits<span
></span>-based-1835327568</a></div>
</body>
</html>