Slashdot Mirror
Software Predicts Music Success
Frankenbuffer writes "The Globe and Mail today reports that MIT researchers have developed a computer program to analyze pop music and predict how people will react to it. The method, developed at MIT's Media Laboratory, analyzes the pitch, rhythm, and other characteristics of music. What makes the technology unusual is that it also takes into account social responses to hit music gathered from weblogs, chat rooms, music reviews, and other online discussions, and correlates this data to the music to guage the popularity of a particular sound. According to the researchers, the software has accurately predicted Billboard hits for the past several months."
the record labels are going to get ahold of this and turn it around to actually produce the music. then it will all sound the same.
wait....
Can Independant artists who want to see how well their songs are going to do be able to use this software for themselves?
I'm not sure I care whether or not this software can predict the next pop craze... but I wouldn't mind a more personalized version. Maybe something that analyzes my mp3 collection, and then automatically checks new releases and looks for tracks that correlate well with my preferences? It would be nice to have a system that pulls out the things I'm most interested in. And a piece of software would be more impartial than the media executives and promoters who want to sell me the "next big sound."
I think lots of people would love something like that. If iTunes automatically integrated technology like that, I think it would be a hit. And best of all, it would level the playing field. Small bands could "get noticed" by the common person if their sound was something that the given person liked.
Now if they could just crack the algorithm the music industry uses to generate music, all of the geeks of the world could create free music that sounds just like Britny Spears/P Dilldy dooldy whatever/Pop or Rap Group D'jour....
No wait, on second thought I'd rather keep my sanity.
Joking aside, this sort of research might be interesting from a psychological point of view. If they've developed an algorith that can tell what music is "good" it seems like with some proper research it might provide some insite into the way the brain process music, which could help scientists to better understand the way the brain interprets patterns, etc. If such an algorithm could be used to generate "good" music, it might be useful for things like games, where the game could provide parameters based on what's going on, and algorithmically generate appropriate music.
Famous Last Words: "hmm...wikipedia says it's edible"
According to the researchers, the software has accurately predicted Billboard hits for the past several months.
... maybe I'm in the wrong business.
Hell, I can do that. My friends have noticed that, for a long time, any piece of popular music that I can't stand to hear becomes a hit. Hm
The higher the technology, the sharper that two-edged sword.
This is not the first such program, and I suspect it shares the failing of its predecessors... It will not predict new trends, it will only follow existing ones. The more it is used to decide if an artist is going to be promoted, the less variety we will see in the music world. When new artists can no longer make it unless they are cookie-cutter copies of current acts (which has arguably already happened), the mainstream music scene will cease to evolve, and the really progressive, groundbreaking groups with a chance to become superstars and jumpstart new genres will be buried even farther under a pile of sameness.
for up-and-coming artists? Music companies will be able to use this to pay artists less because the computer doesn't like their music.
MAL (Music AnaLyzer): "I'm sorry Dave, I'm afraid I don't like that."
"Scud Storm!" -- Jeremy of PurePwnage.com
I wrote a predictor too. It's a neural net, actually.
int music_predictor(int artist_type,float rhythm, int genre, int tempo, int male_or_female, int quality, int singing_quality, int band_quality, int number_of_band_members) {
if (artist_type == BIG_NAME_POP_ARTIST_WITH_STUDIO_BACKING)
return true;
else
return false;
}
Ok, so it's a one-axon neural net. But it gets 99%+ accuracy.
On a personal level, I think we're going to head into an era where experimentation and unique sounds will be cherished. We've been listening to this sort of tin-pan alley redux for about 10-20 years now, and a lot of people sense discomfort with the existing pop music trends. Look at the 40s-70s and I think you'll see the same sort of musical revolution in the next 30 years.
Dupe! ;)
We don't need software to predict how many posts will mention Britney Spears even though she faded away years ago. She's no longer an appropriate proxy for manufactured pop music. Pay attention people. It's 50 Cent's world, we just live in it.
robotic taste-shaping overlords
Most people don't know it, but that level of technological sophistication was achieved nearly a century ago.
Nowadays, we call them "studio executives". They used to work reasonably well, but nobody has updated their programming since 1957.
The higher the technology, the sharper that two-edged sword.
Even though a system such as this would seem to have the logical result of killing the art of music, it simply can not.
As a musician I have noticed that the more I study music theory (theory is really just the language to describe music) the more I come to realize that almost all music is the same. You can spot similarities between four hundred year old classics and current "Indie"/Pop/Rock/Whatever, the connection is there.
So what might you ask makes it different?
The style makes it different. The way the individual artist performs/arranges/records a piece. Not to mention that lyrical content adds a whole new dimension?
Saying something like this will ruin the art of music is like saying that the grammar checker in any document editor ruins the art of writing. Though it is neat that a program could possible sort out "popular" music, which just means it's able to emulate the human ear just a little bit.
Read the whole story, at: http://www.infinityplus.co.uk/stories/worth.htm
If you're interested, Greg Egan's site: http://gregegan.customer.netspace.net.au/
.sigs: Just Say No!
The secret to success is apparently: more cowbell.
Did you know you can fertilize your lawn with used motor oil?
Trying to shape a song so it becomes successful has been tried many times before - with unsatisfying success. On a higher level it led to the categories of music we know today, like Blues, Trance, Metal, etc.. On a lower level we see follow-ups to first hits, that use the same kind of harmonies, rhythm and sounds. But there still are a lot of songs that become successful not because they sound the same like other songs but because they are innovative, think Kraftwerk or Nirvana.
Music trends are a system between unification and diversification. The more songs sound alike, the more people will appreciate songs that differ and vice versa. This system is very hard to predict. I am sure the music industry tries to predict it and synthesize hit records and I think this is why there are so few truely creative artists with a contract from a major record label.
On se Internetz nobody noes your German.