siliconindia logo
Facebook Twitter google+ RSS Feed

New AI System Can Create Fake Videos From Audio Clips, Images

Monday, 22 May 2017, 11:56 Hrs
16
cmt right
28
Comment Right
31
cmt right
7
cmt right
Printer Print Email Email


LONDON: A new artificial intelligence system developed by Oxford University scientists can create fake videos of a person by using just a still image and an audio clip. 

The system works by first identifying facial features using face-recognition algorithms. As the audio clip plays, the system then manipulates the mouth of the person in the still image so that it looks as if they are speaking.

Although the results are not absolutely perfect, researchers believe that the software could soon make realistically fake videos only a single click away. 

"The application we're thinking of is redubbing a video into another language," said Joon Son Chung at University of Oxford in the UK. 

In the future, the audio from news clips could be automatically translated into another language and the images updated to fit. The new method could be useful for redubbing animated movies, the 'New Scientist' reported. 

Given enough time, experts can already create fake videos that are virtually indistinguishable from genuine ones. 

The new artificially intelligence tools make the process so quick and easy, that eventually almost anybody could do it, researchers said.



Read Also:
Panasonic Opens Innovation Centre With TCS In Bengaluru
WhatsApp Pinned Chats Now Available For Android Users


Source: PTI
Experts on SiliconIndia
Santhosh  K
Sr. Soft. Engg.
Oracle India
Nehal Vyas
Sr. Team Lead
Cyberoam Tech.
Rani Malli
Sr. Director
Philips
Sr. Executive
ISB
Vijay Balkrishna Konduskar
Business Consultant
Imans Web Tech
Dr L P  Sharma
Technical Director
NIC
Reena Khanna
Founder
Solitaireworld
Dellas  Asse
sys-network admin
Computer Station
Sign Up for DailyDose and Read the Day's Highlights
Follow SiliconIndia :
Write your comment now
Submit Reset