RIGHT OR WRONG. The music industry has been rocked by the phenomenon of audio deepfakes

Published


To update


Video duration:
5 minutes

franceinfo

Article written by

France info – L. Brisson, J.J. Buty

France TV

19/20 info’s “True or Fake” column focuses on audio deepfakes in the music industry on Wednesday, September 13th. This is a trick that involves using artificial intelligence to get an artist to interpret lyrics that they have never sung before.

On a piece of music we can clearly recognize the voice of the Belgian singer Angèle, seeexcept that she never uttered those words. His voice is generated by artificial intelligence and he was made to sing the lyrics to a French rap song. We call this trick a Deepfake Audio, and it’s a real phenomenon right now. While some are rather ridiculous, others are completely believable.

Getting easier to make

Jason Medeiros is the duo’s rapper EverythingA. A few months ago they published the title “Savages” by recreating the voice of the American superstar Jay Z. “The first thing we had to do was write a text and record it. Then we recorded this audio and mixed it with the artificial intelligence model“, he explains. “I think the fear needs to be more focused on the issue of copyright, how to legally protect artists.”believes Jason Medeiros. Ces Deepfakes Audio is becoming increasingly easier to produce and increasingly difficult to find.

Lesen Sie auch  Emma Stone verrät, dass die lang erwartete Cruella-Fortsetzung noch „in Arbeit“ ist, aber hoffentlich „eher früher als später“ gedreht wird.

Find all Vrai ou Fake broadcasts by clicking on them Here.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.