this post was submitted on 18 Sep 2023
158 points (93.9% liked)
Movies and TV Shows
33 readers
1 users here now
General discussion about movies and TV shows.
Spoilers are strictly forbidden in post titles.
Posts soliciting spoilers (endings, plot elements, twists, etc.) should contain
[spoilers]in their title. Comments in these posts do not need to be hidden in spoiler MarkDown if they pertain to the title's subject matter.
Otherwise, spoilers but must be contained in MarkDown as follows:
::: your spoiler warning
the crazy movie ending that no one saw coming!
:::
Your mods are here to help if you need any clarification!
Subcommunities: The Bear (FX) - [!thebear@lemmy.film](/c/thebear @lemmy.film)
Related communities: !entertainment@beehaw.org !moviesuggestions@lemmy.world
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Modern models need about 5sec of audio to replicate a voice. The days when you needed a large amount of audio for replication are long gone. Same for faces by the way, the original Deepfake needed hundred of images and hours of training, now you can do it with as little as a single good image instantly. Software to automatically clone the voice, translate the audio into another language and adjust the lip motion exists as well, again without any lengthy training or material, just needs the clip you want to change.
Where the whole thing gets interesting is in remixing. If you stolen Stephen Fry, sure that's bad and there might be laws against it. What if you remix Stephen Fry and Patrick Steward into a brand new AI-persona? What if you remix a Stephen Fry sound-alike out of other peoples voices without ever touching his voice?
This whole issue gets very blurry very fast.
Do you have a reference for the 5secs of audio? And what would the quality of the ai be? I mean it would have to infer a lot of training just given 5 seconds of audio.
And re: remixing:
How long until enough people put recordings of their voices out with a CC0 license that you can legally digitally remix any voice you want?