RE: robot com-posers

Subject: RE: robot com-posers
From: Mauricio Duarte-Neira (039166d) (
Date: Thu Feb 17 2005 - 10:27:47 EST

I think it is possible for a computer to detect chords, and certain patters to detect areas in music. For example in more traditional music, it could detect bridge, coda, form, etc.
Also, a lot of traditional music has "rules". So teaching rules to a computer, it could generate a ramdom melody, that follows these rules and the more contemporary you go, the more random (yet logical) it becomes.
Being in computer science and arts, this is actually inspiring :)


From: on behalf of
Sent: Wed 2/16/2005 7:19 PM
Subject: robot com-posers

> What I what is something that actually knows
> about music, not a magic number
> filter that explains nothing.
> -- eliot

I have an idea for you. Theres alot of research being done involving engineers
trying to get computers to speak. A student mentioned at your lecture yesterday

something about music being a language. I disagree with this, but he made a
good point.
There are many languages as there are many types of music. They are both aural
or written forms of expression. They both, to a great degree express a cultural

background. They both involve the understanding of sound by recognising
patterns, and combinations of patterns...

Can you tech a computer to recognise patterns? It has been done for speach/
writing to a certain degree.

MY idea is to focus on a certain type of music, as one would focus on one
language at a time when teaching a computer how to speak. Build a big database
of rock and roll and teach the computer to recognise key percievable elements
of that type of music. I'm not saying its going to be easy.

you would have to disect the songs to their elements. Teach it to segregate the
drums from the guitar and so on, teach it to recognize modes progressions.
rhythmic patterns, timbres... but on the other hand it would have to recognise
the big picure: tempos, style, overall form,,,the list should be very long.

Then the computer could design a piece using a huge matrix, each value being
one of a million other values in its category but a problem emerges here.

How will the computer be able to choose among its options? We'll leave that to
computer generated randomness, the "language equivalent" of teaching a computer
to babble, but a difficult task nonetheless.

you like it?


Quoting Eliot Handelman <>:

> Richard Wentk wrote:
> > At 03:13 14/02/2005, you wrote:
> >
> >> The same stuff is going on in academe
> >
> >
> > Indeed. But it just highlights the difference in mindset between the
> > arts and engineering departments.
> not necessarily -- we're seeing this kind of research in music depts as
> well. I know a high-placed
> music theorist who gave a spiel about the importance of categorization
> (to what effect I forget) indicating
> at least some minor intellectual osmosis. These things WILL influence
> how music is thought about
> and taught.
> >
> >
> >> -- there's the princeton project (forget guy's name) to automatically
> >> classify
> >> music and find "similar" music, Dannenberg & Vercoe have also
> >> autrhored classification papers and I'd judge it to
> >> be the dominant idea about how music information retrieval ought to
> >> work.
> >
> >
> > But not music creation. (At least not yet.)
> That can't be long off. It's not creative though -- that is, HSS can't
> say "put a g-major chord there
> and you got it made" though this too will happen.
> >> That the project represents total music-intellectual bankruptcy goes
> >> without saying.
> >
> >
> > I don't know - isn't this what you want from a post-human world? It
> > looks to me like something that's well on its way to becoming the
> > perfect example of a post-human paradigm.
> No, rthis is just crap AI. What I what is something that actually knows
> about music, not a magic number
> filter that explains nothing.
> -- eliot


This archive was generated by hypermail 2b27 : Sat Dec 22 2007 - 01:46:06 EST