There are some pieces of lost media out there where the original dialog is still audible but there's a foreign narrator talking over it. It seems that this used to be the norm for when American TV shows were shown in Eastern European countries. It really seems like it should be possible to use AI to isolate voices talking over eachother, I'm not sure if there's any software that actually does that yet but I think it's still worth throwing out there
Post by tussockythree68 on Feb 10, 2023 9:53:38 GMT
I think this ties into the general debate around the use of AI in the process of restoration. I happen to fall in the camp that it can be a valuable tool if properly used. I think it's more than acceptable for media that can't really be restored by other means. I would rather have a reconstruction than nothing at all. In the case you described it would be even easier for me to support, since the AI would just be expanding upon what English audio is there (Instead of restoring fully lost audio). I would rather deal with artifacts of the AI process than a voice over.
I am a little bit of a slight piece of a miniature teeny-tiny fraction of a half-sized hob-goblin.
And if this kind of software is used to isolate Jeff Stinco's vocals away from the other Simple Plan members' vocals in their songs does in fact exist in real life, I am raising my bet on it.