We're still a couple of papers before we the computation down to a reasonable amount. Or eventually Moore's Law will take care of it. It might have applications that aren't real-time, too. I'm writing a video game in my spare time, and I was wondering how I would do the foley. If I could feed in some sounds and synthesize a library of sound effects that all sound different enough that it won't be repetitive to hear that same exact footstep sound for the entire game, then I consider that a win. So, you know, this is cutting edge research we're talking about.