AI deepfakes are now as simple as typing whatever you want your subject to say - The Verge


8 bookmarks. First posted by charlesarthur 5 days ago.


RT atmostbeautiful : 가짜뉴스 이어 딥 페이크 주의. 동영상 발음과 입모양까지 조작할 수 있는 기술 연구진이 공개 경고. 사진 포샵하듯 손쉽게 편집. 지금은 실험에서 60%만 속아넘어갈 정도(원본 식별율도 80%)지만 완성도는 시간 문제. 영상제작업계에선 유용하겠지만 포스트-트루스 시대로.. http://bit.ly/2MH0Tzf June 11, 2019 at 08:04PM http://twitter.com/atmostbeautiful/status/1138401680041467906
IFTTT  Twitter  ththlink 
4 days ago by seoulrain
In the latest example of deepfake technology, researchers have shown off new software that uses machine learning to let users edit the text transcript of a video to add, delete, or change the words coming right out of somebody’s mouth. The work was done by scientists from Stanford University, the Max Planck Institute for Informatics, Princeton University, and Adobe Research, and shows that our ability to edit what people say in videos and create realistic fakes is becoming easier every day.
dd  bf  deepfakes 
4 days ago by motiveunknown
are now as simple as typing whatever you want your subject to say
AI  deepfakes  from twitter_favs
4 days ago by cdrago
James Vincent:
<p>In the latest example of deepfake technology, researchers have shown off new software that uses machine learning to let users edit the text transcript of a video to add, delete, or change the words coming right out of somebody’s mouth.

<a href="https://www.ohadf.com/projects/text-based-editing/">The work</a> was done by scientists from Stanford University, the Max Planck Institute for Informatics, Princeton University, and Adobe Research, and shows that our ability to edit what people say in videos and create realistic fakes is becoming easier every day.

You can see a number of examples of the system’s output, including an edited version of a famous quotation from Apocalypse Now, with the line “I love the smell of napalm in the morning” changed to “I love the smell of french toast in the morning.”

This work is just at the research stage right now and isn’t available as consumer software, but it probably won’t be long until similar services go public. Adobe, for example, has already shared details on prototype software named VoCo, which lets users edit recordings of speech as easily as a picture, and which was used in this research.</p>


What do we think, a year? Less?
ai  video  programming  deception  Deepfake 
5 days ago by charlesarthur