HN Books @HNBooksMonth

> I feel like there's a lot of untapped potential in the concept particularly with more 'complex' genres

Well, you're in good company. This goes back for many decades. Here is a summary of many attempts during this time: https://www.amazon.com/Algorithmic-Composition-Paradigms-Aut.... Really convincing composition started to appear only recently using transformers, e.g. https://openai.com/blog/musenet/. The present solution is a rather primitive one in comparison.

⬐ jmfldn

Awesome thanks. Yeah I'm vaguely familiar with the history but certainly not the state of the art. Will take a look at this open AI project.

There are many ideas, even books full of ideas (see e.g. https://www.amazon.com/Algorithmic-Composition-Paradigms-Aut...), but I rarely hear an example which is not disappointing. Recent developments seem to produce better results. If you're interested in a current approach with very promising results see e.g. https://openai.com/blog/musenet/.

David Cope experimented with Markov-chain-style generation of Bach pieces in the '80s, but he ended up switching to other models, like augmented transition networks (ATNs), because he wanted more global coherence, rather than locally coherent but wandering/aimless pieces.

He eventually ended up with a more complex system, EMI, that generates pieces in the style of around 100 composers, some of which have passed the "musical Turing test" in that scholars of the composer in question thought it might've been a genuine work.

There's a lot of pretty interesting experimentation with just about every possible generative grammar by other researchers, though, from Markov models to HMMs, context-free grammars, L-systems, cellular automata, etc. This 2009 book has a pretty good overview of what people have done, though it's textbook-priced: http://www.amazon.com/gp/product/3211999159/ref=as_li_ss_tl?...

⬐ jmmcd

Yeah and there's a lot more out there

http://www.amazon.com/Art-Artificial-Evolution-Evolutionary-... (about graphics as well as music)