Comment on Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
Dasus@lemmy.world 9 months ago
The only use of this I’m in favour of is recreating Majel Barret’s voice as an AI for computer systems.
Comment on Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
Dasus@lemmy.world 9 months ago
The only use of this I’m in favour of is recreating Majel Barret’s voice as an AI for computer systems.
kromem@lemmy.world 9 months ago
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.
trolololol@lemmy.world 9 months ago
Yep it’s part of it to generate the sound track
One of the videos show the voice changing in mid sentence
kromem@lemmy.world 9 months ago
No, it isn’t. In that clip they are taking two different sound clips as they are switching faces. It’s not changing the ‘voice’ of saying some phrase on the fly. It’s two separate pre-recorded clips.