[tsumnia]

Is this your analysis? I'm far from a novice in Music Theory (only knowledgeable it exists), but thing I'd love to see next would be generating a song through a Markov Chain, or even by applying a genetic algorithm and having viewers vote on their favorite renditions.

I've always wanted to take the lyrics of popular songs and run them through a Markov Chain, just to see what could get produced. Ultimate goal would be to generate a song, the lyrics and then have users upload videos of themselves singing it out.

[cnanders]

Yeah, I'm on the Hooktheory team that wrote the article. I love your idea! We're 100% set up to do that kind of thing. It would certainly make an interesting, fun, social set of posts. Today was our first exposure to the world and the feedback / ideas have been amazing. Thanks for the idea. - Chris

[lusr]

I also came here to suggest a Markov chain generator using your data. I know nothing about music but it seems your analysis also needs to include information about timing (A is followed by B within X ms, C within Y ms, etc.) and some sort of clustering information that would allow choruses to be produced (e.g. identify clusters + cluster timing then information about the chords within the clusters).

Even better would be if you guys released your data and allowed other people to come up with creative ways of analyzing and using it ;) I actually have an idea that I think could work quite well and I'd love to build it but lack the data.

[lt]

This has been crowdsourced once.

Scott Adams, from Dilbert, once postulated that most hit lyrics are nonsense, and asked his readers to post random phrases to create a song:

http://dilbertblog.typepad.com/the_dilbert_blog/2008/01/writ...

A German band picked it up and selected the best random phrases and recorded it:

http://dilbertblog.typepad.com/the_dilbert_blog/2008/01/the-...

http://www.youtube.com/watch?gl=GB&hl=en-GB&v=TiH9db...

It's not bad actually.