Re: [microsound] AI in microsound -> Continuator

["Balazs, Gerofi" <kedli@xxxxxxxxxxx>]

Hello There!


Sony has an intresting project called "The Continuator".
Description:
The Continuator project involves a real time interaction with a system
that learns musical styles. With the Continuator, users can play music as
they wish, and the system will automatically engage in a dialogue by
producing musical phrases designed as continuations of user input.
Gradually, the dialogue becomes more and more interesting and challenging
as the system continuously learns from all the previous interactions. We
are interested in the forms of excitement produced, and the links with,
e.g. the theory of Flow.

Check it's homepage:
http://www.csl.sony.fr/Research/Experiments/Continuator/index.php


Regards,
B. Gerofi

On Mon, 21 Mar 2005, david golightly wrote:

> I'm starting to develop a set of AI algorithms to assist in live
> performance, which will (roughly speaking) analyze control messages that I
> send and, after a certain point, be able to generate their own control
> messages based on the patterns I used.  Eventually I'd like to design an
> algorithm to analyze a continuously changing audio texture on multiple
> levels and be able to reproduce similar, non-repeating textures.  I've
> started by giving my PD patch some various recordings of birdsong (of the
> eastern Wood Thrush) for analysis, hoping to tune it to be able to generate
> its own non-repeating woodthrush-like song.
>
> For discussion:  What AI algorithms are the most useful in microsound
> performance - in practice, not only in theory?  How many of you
> microsounders are using AI algorithms, and what have your experiences been?
> Ever used neural networks/second- and third-order Markov chains/genetic
> algorithms/generative grammars/other?  On what time scale (piece-structure,
> moment, sound-event, or microsound generation)? There was an interesting
> interview with Brian Eno back in the 1980's (with The Wire mag, I believe)
> where he expressed a desire for a musical "black box" that could produce
> music in a given style, a Beethoven black box, a Beatles black box, an Eno
> black box...  Beyond whatever proprietary concerns are involved, is this
> even achievable?  There's been a lot of talk of letting your laptop play a
> wave file vs. performing the music yourself, but does anyone have any
> experience teaching your computer to make desicions for you?
>
> Cf.:
> David Cope, Experiments in Musical Intelligence
> Eduardo Reck Miranda (though I find his experiments with cellular automata
> contrived and unconvincing)
> among others
>
> thanks,
> david
>
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: microsound-unsubscribe@xxxxxxxxxxxxx
> For additional commands, e-mail: microsound-help@xxxxxxxxxxxxx
> website: http://www.microsound.org
>

---------------------------------------------------------------------
To unsubscribe, e-mail: microsound-unsubscribe@xxxxxxxxxxxxx
For additional commands, e-mail: microsound-help@xxxxxxxxxxxxx
website: http://www.microsound.org