On a related note, I’m quietly amazed why there isn’t yet a working generator of electronic music. I mean something that I can download, run, and it would stream believable IDM/techno/trance into my earphones. It sounds like it should be so possible, if not outright easy — yet it’s still humans who are toiling away at their Abletons weeding through that search space. I wonder what crucial problem I’m not seeing.
So there is research on generating music, but like a lot of cool research, nobody is making an effort to turn it into products.
In this case the author is using math to paint shapes and fill in colors, but the wider scene composition is authored. The equivalent of this for music would be hardcoding music composition/sequencing using code and writing procedural synths using math (like http://www.shadertoy.com music shader!), not a server somewhere generating music with no human involved.
Entirely procedural music is a genre though, as far as procedural music being "believable" (I guess aesthetically pleasing?) for you it probably depends on the right artists coming along and developing a sound you like, moreso than it not being possible.
The minute we realise music isn't the authentic voice of another human being we reject it.
Even my enjoyment of arguably mechanical music like some of the early minimalist stuff - where to a degree processes determine the structure and unfolding of the work - is mediated through my awareness of the authorial intent of the composer. (I'm talking more about Piano Phase than Pendulum Music here - the latter is slightly too devoid of human intervention to be 'real music' for me)
How would you feel about a novel generator? Why is that so different?
Another reason why such utterly cheap production habits have been wildly accepted is because of the already established history of house music and techno, which was originally revolutionary, because those sounds and the contexts for which they were experienced ironically represented newfound human feelings of liberation, from a youth movement to escape a bankrupt Detroit to the fallen Berlin wall. Techno was a way for people to grab the rising technocracy by the horns so to speak and make something specifically human out of it.
Anyway, my point is: even music with "repetitive structural patterns overlaid on similar timbres" cannot be replicated with any genuineness by computers. Not yet, and probably not for a very long time. We, as people, can sense the insincerity. Now, if the goal is literally to have repetitive background noise with no real melody or structure then sure we can certainly already do that. But I also would not call that music in the true sense of the word.
Being an Artist with a background in technology I can't help but appreciate this differently than I believe intended. I've been thinking a lot recently about the boundries of what is and isn't art in regards to technology (up to and including the division of Arts and Sciences at the Academic level) and feel like I need to say something about the use of the word Art here.
To me, the Art is your unique contribution to the Art World, which is always the aspect of the work the Artist puts their heart into the most. Unless someone really picks up this tool as their medium of choice and makes true Art with it, the Art to see here will always be the code Alan Luo has writen. Code is poetry and deserves every bit as much respect as forms of it like concrete poetry, where things like indentation matter. It just kind of irks me to see Art get demeaned by people I would consider Artists if they reframed their work.
With the rise of the likes of Google's Magenta project, the use of the word 'art' is brought into question, just as you mention. So as the original dev, I'd like to give my two cents.
I do not consider the outputs of this program as 'art.' Whether or not the code is art is an entirely different question that I don't think is really important to address.
The documentation was a little hastily assembled for a deadline, so the following sentiment is not reflected in it, but the purpose of this project was never to create 'art' with code, it was to demonstrate that there exists a bridge between creativity and code. For me, the output of this program is not art in itself. However, I have used the output as a place to draw inspiration for other pieces of work that I would consider art. In this case, I use the program as an infinite source of inspiration rather than as the art itself.
By the way, I may write a blog entry about this topic in the future. You've brought up very interesting ideas. :)