Statistically Optimal Music

ShinyPlasticBag writes "'Eigenradio makes its optimal music by analyzing in real time dozens of radio stations at once. When our bank of computers has heard enough music, it will go to work on making more just like it. Since we listen to so much music all the time, Eigenradio is always on and always live. What you hear on Eigenradio is the best of the New Music, distilled and de-correlated. One song on Eigenradio is worth at least twenty songs on old radio.' Listen up here or here (SHOUTcast)."

Comments

Hello darkness, my old friend

[RobertB-DC]

I quickly checked out the site and hit the #1 "Listen" link. At first, it was an interesting mix... in fact, it sounded very much like tuning an AM radio between stations, except that the overlapping songs were in clearly-defined hi-fi.

It was jarring at first, but then I got into a groove. They're right, the beat and the ambient voices have a strange but familiar variance.

Unfortunately, I don't think I'll be able to keep up the experience. After about a minute, the rhythms stopped, replaced by a metallic, toneless hum.

Cool... I've seen the Slashdot effect before, but now I'm getting to hear it!

Footnote: the rhythm has returned, but there's a lot more buzz than before. Will be interesting to hear what happens when the non-subscriber flood hits.

video

[bobtheheadless]

I wonder if you can do the same thing with video... hm.

Re:Where are the details?

[Jerf]

IMHO this is yet another example of how academic projects are judged by the amount of attention they attract, rather than on whether they advance the state of the art.

Every Spring semester at Michigan State University's Computer Science department, the capstone class (taken by seniors to graduate) did a project and had a "poster competition" to see who did the best project.

The team that won the year I saw them was the team that wrote a program that graphed a song's FFT over time. That's it. They went on to babble about how you can recognize a song based on how it looks, visual recognition, and it did some ill-conceived 3D stuff that, by making the song data fit into even less space on the screen, was even more impossible to see. (I think you were supposed to eventually pick the song you wanted to hear by looking at this tiny, tiny representations.... at the risk of potentially offending one of the authors, who may conceivably read this, that's stupid! If they just seriously tried it once, they'd have seen how poorly this worked.) (See here for an example of a guy playing around with that kind of graph; note most songs look NOTHING like that in an FFT graph. ;-) )

The fact is, it's a neat idea but it doesn't work. All songs in a particular pretty much look alike in an FFT graph. The differences are pretty minimal. Making it smaller doesn't help at all. The program looked really cool on a poster, using one song, but use it on six or seven real songs and ask even yourself to distinguish them and you can't; you don't "see" and "hear" that way.

IIRC a dot-com was founded based on this idea, AFAIK indepedently derived.

What does this have to do with your post? I thought about half of the other posters deserved the prize over this project, in that they were useful, interesting, or potentially even groundbreaking, in the small way that a semester project can be. But they didn't have a Beatles song graphed out on their poster. They lose.

Even college professors aren't immune to judging on surface appearences and glitz, rather then real value.

Why do I get the notion

[John Zebedee]

... that this site is a wonderfully clever troll? Once you get past the notion that anyone could possibly be serious about Eigenmusic, satire is all that makes sense. A tip of the hat to the creators!

Ring Mod?

[gidds]

Does anyone else find that sort of metallic noise familiar? It sounds uncannily like the effect of an audio processor called a ring modulator - also known as a multiplier. What's the betting they're just multiplying together all the inputs?