return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 6 months agoMicrosoft’s VASA-1 can deepfake a person with one photo and one audio trackarstechnica.comexternal-linkmessage-square54fedilinkarrow-up149arrow-down12cross-posted to: technology@beehaw.org
arrow-up147arrow-down1external-linkMicrosoft’s VASA-1 can deepfake a person with one photo and one audio trackarstechnica.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 6 months agomessage-square54fedilinkcross-posted to: technology@beehaw.org
minus-squareDasus@lemmy.worldlinkfedilinkEnglisharrow-up1·edit-26 months agoOne use of this I’m in favour of is recreating Majel Barret’s voice as an AI for computer systems.
minus-squarekromem@lemmy.worldlinkfedilinkEnglisharrow-up1·6 months agoThis project doesn’t recreate or simulate voices at all. It takes a still photograph and created a lip synched video of that person saying the paired full audio clip. There’s other projects that simulate voices.
minus-squaretrolololol@lemmy.worldlinkfedilinkEnglisharrow-up0arrow-down1·6 months agoYep it’s part of it to generate the sound track One of the videos show the voice changing in mid sentence
One use of this I’m in favour of is recreating Majel Barret’s voice as an AI for computer systems.
This project doesn’t recreate or simulate voices at all.
It takes a still photograph and created a lip synched video of that person saying the paired full audio clip.
There’s other projects that simulate voices.
Yep it’s part of it to generate the sound track
One of the videos show the voice changing in mid sentence