[MLUG - DISCUSSION] so this is pretty scary [MUSIC]

[Vern Green]

This is not scary to me, this is downright exciting if it works as well as
they let on which I am skeptical.

I doubt it would work well on any mixed tracks. For instance a track that
has guitar, sax and bass on it, along with a piano, drum and vocal track,
but even if you could only do this with a single track it is pretty awesome.




On Wed, Mar 12, 2008 at 9:48 PM, Mike Miller <mbmiller at taxa.epi.umn.edu>
wrote:

> On Wed, 12 Mar 2008, Jonathan King wrote:
>
> > Part of me thinks this is so cool. The other part of me is very afraid:
> >
> > http://www.celemony.com/cms/index.php?id=dna
>
> Afraid of what?  That it takes music away from musicians and puts in in
> the hands of computer scientists?  It is pretty interesting.  How long
> before computers with software like this and some kind of AI can produce
> new music that we really like?
>
>
> > So the geek-dude programmer suggesting this is theoretically impossible
> > is, I believe, exaggerating the case somewhat. I think what he did was
> > find an efficient implementation of pretty well-known blind source
> > separation algorithms. I don't think it's accidental the demo uses
> > guitar chords rather than piano chords primarily. Still...I'm impressed.
>
> Would the separation be harder for piano?  I'm not sure.  I can think of
> another good reason to focus on guitar -- lots of hobbyists play guitars.
>
> Mike
>
> _______________________________________________
> discussion mailing list
> discussion at mlug.missouri.edu
> http://mlug.missouri.edu/mailman/listinfo/discussion
>



-- 
Thanks
F Vernon Green
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mlug.missouri.edu/pipermail/discussion/attachments/20080312/3abadbef/attachment.html