61–70 of 189 posts
MuseNet will play an experimental concert today from 12-3p PT livestreamed on our Twitch channel. No human (including us) has ever heard these pieces before, so this will be an interesting showcase of MuseNet’s strengths and weaknesses. Through May 12th, we’re also inviting everyone to try out our prototype MuseNet-powered music generation tool.
Earlier quoted context omitted.
With hundreds of thousands of semi-professional and amateur musicians competing on the Internet for their 15 minutes of fame, getting film or computer game score just isn't a real problem. Besides, this is already doable, without neural networks. E.g. Karma[1]. The fact that most "AI music" enthusiasts don't know/care about such systems is a clear indicator that they aren't really interested in music or helping creat…
>just want to shove AI in yet another niche where it doesn't belong and then pat themselves on the back for contributing to "progress". Can you elaborate on why AI doesn't belong in this niche? The results are too good? The results are not good enough?
This isn't chess or go, where you either win or you don't. Chopin composed for a reason, and it wasn't just an excuse to throw a lot of notes at the page.
It might be possible for AI to work at that level someday, but it's not just a technical problem, and you won't be able to solve it by throwing a corpus of compositions at it.
Aside from that, this still sounds like aimless noodling. It's far more polished noodling with some awareness of genre cliches, but it's still essentially aimless - and so meaningless.
This may be academically interesting, but the music still sounds fake enough to be unpleasant (i.e. there's no way I'd spend any time listening to this voluntarily).
One thing with it is the distance from getting a computer to compose anything to getting it to compose close to human level could be 90% of the distance to getting it to compose at a super human level. Even several months before Alpha Go beat Lee Sedol there were people saying the AI could be good but never great. Now everyone admits it's super human. I agree that getting really texture and subtlety in the work is re…
So long as the training set only tells it what human-composed compositions look like (MIDI files of existing music), a system has no signal to find "super human" territory.
Earlier quoted context omitted.
>just want to shove AI in yet another niche where it doesn't belong and then pat themselves on the back for contributing to "progress". Can you elaborate on why AI doesn't belong in this niche? The results are too good? The results are not good enough?
The results are meaningless. This isn't chess or go, where you either win or you don't. Chopin composed for a reason, and it wasn't just an excuse to throw a lot of notes at the page. It might be possible for AI to work at that level someday, but it's not just a technical problem, and you won't be able to solve it by throwing a corpus of compositions at it. Aside from that, this still sounds like aimless noodling. It…
I disagree based on your following quote:
> Aside from that, this still sounds like aimless noodling. It's far more polished noodling with some awareness of genre cliches, but it's still essentially aimless - and so meaningless.
This sort of problem can easily be reframed as a win or lose problem, we simply consider whether the music sounds good or not. More concretely: would this music be able to convince you that a gifted human composer created it?
I'm fine with the answer being no, but I don't understand why the original comment I replied to wrote off the entire exercise. No we may not be there yet, but this seems like a good step forward to me.
I don't know the other genres well enough to evaluate them, but the bluegrass one ( https://soundcloud.com/openai_audio/genre-bluegrass ) is pretty bizarre: * Who uses piano as the lead instrument in bluegrass? * They're only using one one note velocity for the whole piece, which misses a huge wealth of variation through rhythmic accent. * Timing generally feels a bit robotic? * The best parts it sounds kind of ok bu…
Another interesting musical form to see how well MuseNet does would be boogie woogie.
This seems incredibly applicable to musical scores in movies. I can imagine a product where the editor/director/someone inputs a handful of variables (mood, genre, instruments, etc) and timing requests (crescendo beginning at 30s and ending at 75s, calm period from 90s - 120s, etc) and out comes a musical score for the movie that matches up with their scene editing.
Maybe more interesting for video games, where you can have a realtime input of gameplay variables.
This seems incredibly applicable to musical scores in movies. I can imagine a product where the editor/director/someone inputs a handful of variables (mood, genre, instruments, etc) and timing requests (crescendo beginning at 30s and ending at 75s, calm period from 90s - 120s, etc) and out comes a musical score for the movie that matches up with their scene editing.
Maybe more interesting for video games, where you can have a realtime input of gameplay variables.
While this may not be perfect composition, this is a surreal (and almost sad) moment in my life to hear music that is passable created by a computer under it's own volition. I work at a company that works with a lot of machine learning so I generally understand its limitations and haven't ever been an alarmist. That being said, I generally always thought of it being applied to automate work. For some reason I had alw…