hckrnws

This conference paper is from 2005, not 2023, see https://link.springer.com/chapter/10.1007/978-3-540-32003-6_...

Essentially it's a glorified pseudo random generator, like many of the algorithmic composition ideas of the time.

L-systems were proposed for music even earlier. Here's a link to an article from 1986: https://quod.lib.umich.edu/cgi/p/pod/dod-idx/score-generatio...

It definitely is not a glorified PRNG. The idea is that you can create patterns that have both variety and repetition with them. I don't like the results, generally, but they are not random.

Prusinkiewicz indeed did important work on L-systems and music in the eighties, but the use of generative grammars and rewriting systems in music dates back at least to the sixties. The reslts of such approaches are not random, but "pseudo random", as written. Also the term "fractal noise" is used in this context.

Correct; here are some papers that cite the paper above in case folks are looking for more: https://scholar.google.com/scholar?cites=6968059276866815065...

I would assume that a lot of people now experiment with Large Language Models (LLMs) a la GPT-4 or Llama3 in the area of music generation.

> experiment with Large Language Models (LLMs) a la GPT-4 or Llama3 in the area of music generation

LLMs are/were indeed used for music generation, but none of these results were convincing from my perspective as a practicing musician. Language is just too different from music, so that results of (symbolic) music generation based on DNNs with linguistic embeddings are only good by chance, if at all. Convincing systems like Udio rather use an architecure for music generation as described e.g. in this article: https://towardsdatascience.com/audio-diffusion-generative-mu.... An LLM is only used to interpret text input and map it to musical features, not for the actual music generation.

L-System music is a pretty good description of gamelan.

Is it? Can you provide a reference, please?

I don't know of anything good in english on the internet, I am sure there is some, I just kind of learn this stuff at rehearsal in the group I am in. There is also this book [1] if you are really curious (its a beast of a book).

But to briefly explain what I am thinking, there is the notion of irama [2], where initially (in irama I) most instruments play something close to what is written. At some point (depending on the piece and style, but usually signaled by the drummer in Javanese gamelan) there is a transition to irama II, which sounds like everyone slowing down at first, but as soon as you get to some terminal point of the transition, certain instruments, based on their own rules, begin to "fill in" the space created by the transition. For example, if you are playing the peking, it might look like this:

main melody/irama I/balungan: 2 1 2 6

peking in irama I: 22 11 22 66

peking in irama II: 22 11 22 11 22 66 22 66

and so on

I am far from expert and so much of this is all totally different depending on region and such. But this core idea of irama and rules-based elaboration from a specific seed is somewhat always present.

Either way, just really some of the most beautiful music you will hear, highly recommend to everyone [3].

1. https://www.amazon.com/Gamelan-Manual-players-central-Javane...

2. https://en.wikipedia.org/wiki/Irama

3. https://youtu.be/3efH3WgTQRU

Interesting, thanks; though I don't think that what you describe is comparable to L-systems. Just had a look into the book "Unplayed Melodies, Javanese Gamelan and the Genesis of Music Theory" by Perlman, which I have at hand, and didn't find any indications of generative grammars or rewriting; it's rather a set of established patterns ("balungan"); this also corresponds to what my friend has learned about the traditional music in Bali (here is a recording we did together; he plays the traditional slonding instruments): http://rochus-keller.ch/?p=251. The problem with the application of fractal algorithms to music is, that music is actually not "self-similar" in the fractal sense, but there are just repetitions or variations. Music in general is not based on an ever-evolving stream of "fractal noise".

I agree that Gamelan is very beautiful music. Important western composers such as Steve Reich were there and studied the music to adopt the concepts in their compositions (see e.g. https://www.youtube.com/watch?v=TN_YSS06ZcQ&pp=ygUabXVzaWMgZ...). Here a part of the performance where you can see that Reich even adopded the orchestral layout similar to a gamelan ensemble: https://youtu.be/71A_sm71_BI?t=806.