RE: robot com-posers


Subject: RE: robot com-posers
From: Philippe-Aubert Gauthier (Philippe-Aubert.Gauthier@USherbrooke.ca)
Date: Thu Feb 17 2005 - 12:13:21 EST


About randomness and constraints, my most impressive algo-thing for generating
music is some sort of jazz/fusion which only relies on randomness weighted by
statistics, and some modal things. A very small prototype, few hours of works
maximum. Incredibly simple. Drum, bass guitar and piano are surprinsingly
interesting, but as the minutes goes it is always different, but similar.
Remind me some historical things ...

One of the thing which I think that might be interesting is to create
interaction between some "agent" (without going into artifical intel and other
thing that I don't knwo too much!) where one is always trying to understand is
friend. One of my first goal would be tempo tracking using now well-know
beat-tracking things ... but time is missing.

...

Selon "Mauricio Duarte-Neira (039166d)" <039166d@acadiau.ca>:

> 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 :)
>
> Mauricio
>
> ________________________________
>
> From: owner-cec-conference@concordia.ca on behalf of
> n_kondon@alcor.concordia.ca
> Sent: Wed 2/16/2005 7:19 PM
> To: cec-conference@concordia.ca
> 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?
>
> nick
>
>
>
>
>
>
>
>
>
>
> Quoting Eliot Handelman <eliot@generation.net>:
>
> > 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
> >
>
>
> --
>
>
>
>

%====================================================================%
% Philippe-Aubert Gauthier, B.Ing, M.Sc. %
% Étudiant au doctorat en reproduction de champs acoustiques %
% %
% GAUS (Groupe d'Acoustique et de vibrations de l'Université de %
% [ Sherbrooke) %
% CIRMMT (Centre for Interdisciplinary research in Music, Media %
% [ and Technology) %
% %
% http://www3.sympatico.ca/philippe_aubert_gauthier/acoustics.html %
%====================================================================%



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