Slashdot Mirror
New Computer Program Determines "Hitability"
illuminatedwax writes "It looks like the process of homogenizing the mediocrity of Top 40 radio is going to be aided by a computer, according to an
article from the Music Industry News Network. Polyphonic HMI has developed a new program called Hit Song Science (HSS) and compares "underlying mathematical patterns" in current hit songs and compares them to a new song to determine if it will become a hit or not. Looks like we can expect even more of the same old junk being recycled for us on the radio, although the article claims that it 'will allow new sounds and styles to flourish.'"
This works if you assume that a "new" or "different" song isn't likely to be a hit.
The media is already telling you what songs you will be listening to. Why would they need a computer to tell them what they already know?
Information wants to be anthropomorphized.
having Britney Spears rerecord the same song over, and over, and over and . . .Arrrrgh! Just shoot me now.
KFG
I am the reason the music industry is dying.
It couldn't possibly be the crap quotient that has gone up enormously over the last decade.
It seems like more then ever the music industry just sticks with whatever sells, experimenting with new sounds, who wants to take that risk?
Wow this thing will generate more of the same.
Quantifying tastes in music.
Evil.
Oh yeah, the problem with the music industry.
My bad.
> and how is this gonna change what's on the radio right now? They just play stuff until they find something that people like, which usually sucks
Actually, they just play whatever's written on the payola $$$, and people "like" it because they think everyone else does.
Sheesh, evil *and* a jerk. -- Jade
Do they give it all the songs ever, and it says "not a hit" for all of them, and it's 90% correct, because 90% of songs are worthless?
Hell, I could write that.
#!/bin/sh
echo "not a hit"
1) Bohemian Rhapsody
2) Smells Like Teen Spirit
3) London Calling
An NPR article a few years ago reported how music companies decide which Country Music songs will be played on the radio. They cold call people and have them listen to 5 seconds of the song. This tortured person is then asked to rate the song 1-5. The music industry then takes all the songs that get 1s and 5s and discards them. It turns out that often when one group rates a song a 5 another will really hate the song and rate it a 1. So what the industry is really looking for is songs that score 3s.
The reasoning behind all this is that if you hear a song that you'd rate a 1 (hate) you're likely to turn the radio dial. But if you hear a 3 you're not likely to have any particular response at all -- thus you'll stay tuned in for more comercials.
Pop is probably done the exact same way. I guess that's why when you listen to "Classic hits of the [6-9]0s" you hear the same tripe over and again.
The songs that will be hits are the ones that get the most spins, whether it's because a local program director/music director got sweet-talked by a distribution rep (aka legal payola), or because Clear Channel says it'll be a hit. IAADJ.
Furthermore, MTV has a big part to play, still, because how many fat, bald guys do you see with hit records? Take hot chick, add dance background, have hit. For variety substitute a few decent-looking boys for the hot chick.
As for this program, remember, the nutrimat in the Heart of Gold also determined Arthur Dent would like the Advanced Tea Substitute. See what happens if he drinks it too much.....
If only they can make a program to predict "slashdotability", their server wouldn't have to suffer like this.
--
Error 500: Internal sig error
Music and Math are closely related, as anyone who's read Godel Escher Bach knows. Musical scores have themes that appear in many different variations such as canons (when a melody is offset in time) and fugues (more complicated than a fugue, read the book if you want to know).
I'm not acoustically talented, and I'm sure I couldn't recognize a fugue or a canon if I heard one, but I know that there is some music that I really like, and that sounds better made and more complete than others. I wouldn't find it hard to believe those songs have properties that a computer could pick out.
For example, have you ever listened to a song for the first time, and been able to anticipate what the next notes would be? I think on some level our brain recognizes patterns that we can't see conciously. With statistical analysis, a program could determine if more hit songs always follow a pattern or a specific pattern (easy to hum songs that get stuck in your head), or if more hit songs would break the melody and hit a note you weren't expecting (like those really mind-blowing high notes).
As a music lover, I would be thrilled if this application worked. It would really enhance websites that try to suggest other songs that you might like based on your favorite songs. In a lot of the music I like, the singer's voice gets deep and gravelly in parts. There could be bands that I hadn't considered listening to who match that profile, and a program like HSS coudl find them.
for me, ``hitability'' doesn't mean the same at all.
Reading the title made me wonder if a computer was able to do some kind of ``Hot or Not'' evaluation of a picture.
A message from the system administrator: 'I've upped my priority. Now up yours.'
hey, how long till i can have it automaticly D/L the songs that i will [Mathematically] like?
From the way progressions resolve to the overused arrangement of "Intro Verse Chorus Bridge Verse Chorus Bridge Verse Breakdown Verse Chorus Outro", most popular music has the same basic structure. Why is it that 95% of rock songs have the same 4 chord major progression? IT WORKS! Yes, there are exceptions where real song writing ability carries the song on to success (Queen, anyone?) but the general templates are there...and record companies KNOW (and bank) on it. (considering that most pop buyers can only hear the singing, I'll understand if no one gets this)
"Suburbia is where the developer bulldozes out the trees, then names the streets after them."
...this is pretty similar to the computer program described in The Jazz by Melissa Scott. A kid stumbles onto a program that can tell him how similar something is to existing works. It goes slightly further - making suggestions also - but the idea is the same. In the book, a major studio uses it for movies.
Rivers uses a mathematical formula when writing his songs based on songs by several bands including Nirvana. As a huge Weezer fan, I'd have to say he's on to something. He's talked candidly about it in interviews. I'm at least fairly interested in what comes of this.
As far as the media telling you what you'll be listening to...
You've got a point, but it's slowly eroding away. Payolla (sp) is now illegal. With all the attention companies like Clear Channel have gotten for owning such a high percentage of the nation's radio stations could soon result in regulation. Then we've got those nasty little P2P file sharing networks lurking around with mp3z to download. *wink*
You've got to face the fact that these record companies and radio stations only care about the money. If they can run a program that will reliably tell them if song A is more likely to be a hit than song B... maybe they can spend less money on promoting song A and get the same results as if they had released song B with extra money for promotion. That's just common sense, man.
thundercatzlair
This may be the excuse to buy a CD/MP3 player. Then I can listen to the hits my mom picks out for me.
A third of the way down (Jan 23 in fact) http://www.bangedup.com/archives/z ard. jpg
Is a link titled "Any idiot can rap"
and it leads to
http://www.bangedup.com/archives/MicroRBHitWi
[ ] Yes
[ ] Yes
YAW
Your head of state is a corrupt weasel, I hope you're happy.
When this algorithm can understand and reproduce the genius of the Beatles I will be impressed. recognizing tripe is still tripe. Creating tripe is still tripe. Write Yesterday, or In My Life and only then will I retire as a musician.
A Good Troll is better than a Bad Human.
I'm surprised I didn't see this mentioned anywhere. I remember one of the particularly depressing things from 1984 was the music generating machine used to create music for the proles.
A machine that checks to see if a song is going to be a hit with the masses based on mathematics is not far behind a machine that will be able to generate a hit for the masses.
Creepy.
you can take the road that takes you to the stars...
"underlying mathematical patterns"
I wouldn't have a problem with that, if they were judging each song independently. Like it or not, music DOES revolve around math. Beat, Harmony, Melody, Rhythm, and Tone are all by definition the elements that make something into music instead of just a bunch of noise.
Today MANY musicians make what is by definition closer to noise than music, because it only has some of these elements. A dripping faucet can have a beat and rhythmn, but it doesn't have a melody.
A lot of top-40 crap is manufactured garbage that is hollow and uninspired, but on the other hand it follows all of the rules of music and thus isn't exactly horrible to listen to (share and enjoy.)
On the other hand, a lot of VERY POPULAR singers completely disregard some of the most basic rules of music. (Did beat go out of style while I was off on another planet or is the entire population of the world go retarded while I was gone?)
A simple test for the quality of music is to compare it to all of the basic elements and see how much of each it has, and how well each one has done.
You can take a lot of music and quickly notice that the singer can not in tune, is off beat, isn't in harmony with the music, the music behind the singer's voice has no real melody (it's just a baseline - a common violation these days), or (very often) it's several of these things.
Again, much top 40 follows the rules. I'd rather hear that than some indi band that doesn't. Much of the top 40 doesn't, and I can do without those. Essentially I'll listen to anything well done, regardless of the type of music or whether or not it's "popular". I can even enjoy classical.
So if someone were to write a program that could simply screen out the "noise" and keep it from getting put on the charts, I don't think that would be a bad thing. Top 40 might not instantly stop being shit, but at least it would be musical shit, and not just a bunch of noise.
You're either going to agree with me on this, or flame me to death. What the hell, I have Karma to burn.
"Everything you know is wrong. (And stupid.)"
Moderation Totals: Wrong=2, Stupid=3, Total=5.
Take a peak at who wrote her songs... and then take a peak at which other acts he has produced...
It doesn't take some dumb machine to sell tons of CDs to the masses, it takes a few guys with insight into what would appeal to the masses, and then you find people who look right.
I seriously don't think that the machine would fix me up with music I like, because the parameters would be all skewed towards the drooling idiots that are the masses. No wonder I don't buy CDs anymore, I rather put my money elsewhere thank you very much.
You'd have to know more about how the system works to tell. It's very well possible that those songs share some mathematical similarities with other less original hit songs. Statistical methods can find rather deep hidden similarities even in superficially dissimilar things.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
Who was the big winner? Was it some teen sex idol? No. It was the daughter of a sitar player.
if you had access to the program, and you fed it the songs that were your own personal hits, maybe rated them, it would be better than just about anything else at telling you what else you'd like. Finding you bands you'd never heard of that were actually pretty good. It could allow you to expand your musical horizons rather than forcing you into the narrow spam mold of the cold musical marketing machine. It could easily evolve into a simple web based tool to sell more and a broader variety of music, but they'd never even think of it.
Sure music is mathematical, but you get completely different music from a computer or machine making the music (player piano, etc.) and somebody actually performing it. The person is able to put expression and feelings in the their work. Often the actual words sung are important to give the right expression and emotion.
Can a computer program really translate the meaning of the words sung and see if they are able to capture people emotionally?
Furthermore, when recording a song, there might be a lot of 'takes' to get a good song. Some are obviously better than others to the human ear, but I would be curious if this computer program rates these fairly or the same.
Live recording CDs change songs quite a bit also. When I play song, I try and change it a little each time, because it is a whole new experience. It keeps the audience interested because even if they have heard it before, they have not heard it quite the way I play it that time. The point is, little variations give a song the cutting edge to make it better. I know I have an album by the same band, but two different producers (Sponge - one by Chaos, the other by Work). One version is definately better than the other even though they are the same songs.
It is sort of the same for a song that was orginally lots of electric guitars and they re-did it all acoustic. Sometimes I even didn't like the electric and loved the acoustic. Can a computer program handle these extreme differences? I wouldn't think so.
I want one. Running every song on the radio through this algorithm would be good. Just so I can automagically switch channels if the software says it's "hit-material" mind you..
it's the music equivalent of spamfiltering.
No one can understand the truth until he drinks of coffee's frothy goodness.
--Sheikh Abd-Al-Kadir, 1587
If you can get ahold of the algorithms that are used to rate the music, you can then compose music that will make the record execs pee their pants with excitement. "Whoa, your song went up to eleven!"
We've already seen this happen -- build a spam filter and the spammers will then engineer their spam to get around it...
If I were a record exec, I'd be particularly dubious of this.
Sean
... and as a hobbyist musician I love articles like this.
When the general public get sick of all the pop and 'reality' stars made for them, they turn to the underground, and this is where you'll find people who truly allow new styles to flourish.
All this Hollywood stuff is for chumps. If you want real music, and real musicians, just look for the underground.
It's out there.
; -- the corruption of government starts with its secrets. a truly free people keep no secrets. --
Don't take this as me sticking up for a pop star. She's cute in an odd sort of way, but I definitely don't like the music. I'm more of a Blue Oyster Cult/Led Zeppelin kind of guy, crossing over to power/progressive metal as of late. Actually now that I think about it, the current batch of pop girls (Avril, Michelle Branch, Vanessa Carlton) are the most attractive group I can remember.
:)
But I have to stick up for her on a few points. Having heard two songs I think I could say that the lyrics don't seem to fit the genre of music. I read a slightly better interview of her in Newsweek a few months back, and I seem to recall she said something similar to what the previous poster had mentioned, that she focused on the lyrics and the label had used a lot of influence over the music on the first album. You can't really fault someone for saying "um" or "like" a lot in an interview because it is on the fly and most of us aren't practiced in rhetoric, don't take our time, and stutter all over the language in that situation. Also, when you're in a multiplatinum position, you probably don't want to talk about what the next album is going to be like if you don't know yet. I could forgive a lot saying she just came out of a huge album and tour, I don't blame her for being a bit exhausted and not really wanting to think about the next album right away. Particularly when you get asked it a lot and are going through the harrowing new star thing.
That said, my interpretation of the whole Avril thing is this: she was on the path to being one of their born 'n' bred country pop sensations. She for whatever reason came out differently than they expected. At 15, her "rebellion" probably didn't consist of walked into the CEO's office and terminating the contract over musical differences. Did anyone notice how mention of her parents is curiously missing from these interviews? My guess is that she told her parents she wasn't going to do it anymore. They went in and told the label, who came up with a "compromise." She could do "whatever she wanted"--as long as she followed along with what they wanted in the areas that didn't have to do with the music. Since she really didn't know a damn thing about music other than pop, it's what her first album sounds like. It's what she knew. Of course the rebellion didn't have anything to do with musical differences, she just didn't want to become a primped and preened mass media sex object.
Predictably, the label saw this as an excellent chance to make her a mass media sex object, only aiming her for the so-called angst-filled teenager market rather than the popular pop market. The uproar over this now seems really no different than the uproar that followed the release of American Pie or Something About Mary, except it's music and it's several orders of magnitude more benign. In actual fact, every teenager has angst, so her demographic is huge. Britney can't exactly convey the angst message, plus she suffered from over exposure. (I'd argue that pop is an inherently limited media that prevents more complex messages than simple teenage love/angst from being transmitted in the first place, but that's another rant.)
I bet they gave her all the freedom she could think of, and then just shuffled her off to do their photo shoots and various other PR without making a big deal about it. Being completely unworldly, she doesn't know 1) what she's rebelling against, or 2) what is intrinsic to the music business that she should be rebelling against, and isn't.
If my theory is correct, here's what I would expect to happen in the upcoming years:
1. Each successive album she creates is more of a departure from the first album until she finds her style (probably 2 albums from now).
2. Her fanbase grows smaller but more dedicated until she is taken seriously as a "real artist" in some circles. Along with that, it will be acknowledged that she has her own style, even if it's representative of some genre, but that genre will not be pop.
3. The label eventually drops her, inspite of which she continues to release albums on a smaller label and fill medium-sized venues well into her old age.
Is it likely? No. But the fact that her bass player left because he was tired of being a "marketing tool" might merely mean he is too talented to be wasted playing second fiddle for a clueless teenage girl who gets all the time in the spotlight. (It's not real likely he's talented either, but this is the music industry not the software industry). But here's what I expect would happen if she is nothing more than a marketing trick:
1. There are 2 additional albums from her, neither showing any marked improvement in skill in terms of songwriting or lyrics (or even any additional maturity or increase in vocabulary).
2. Each successive album cover shows her revealing more skin (in the other scenario, album covers are less likely to feature her prominently).
3. After the third album is a complete failure, the label drops her and she is never heard from again in any capacity. 20 years later, on VH1, we learn that she spent half her money moving to India where she teaches English and Computer Science in a middle school and is a devout Hindu. Or, alternately, she becomes an MTV anchorwench, which I think is at the same level of general interest and importance.
Of course, I could be wrong.
--
Daniel
There is a great saying that I love that I've heard credited to David Cronenberg (never been able to verify it). The saying goes, "An entertainer gives you what you want. An artist gives you what you didn't realize you wanted."
This kind of hit-finding software will give music execs the abillity to perfect their entertainment while pushing them almost entirely away from art. For real artists out there, this could be a good thing, in the long-run.
--Rick "If it isn't broken, take it apart and find out why."
They weren't called The Hit Factory for nothing...
OTOH, Pete Waterman is *still* churning out acts that are hits (and has been a judge on two major UK Popstars talent shows along with his old mate Simon Cowell). And still happily copying classical structures.
And if you think this is a phenomenon of the last 2|5|10|20 years, bear in mind such formulae as the 12 bar blues and the 4 chord trick (I, VI, IV, V, repeat).
But much of the gloss of pop music is (as suggested by parent post) in the arrangements, not the composition. Look at the number of covers in that compilation. Covers from the 50s, the 60s, the 70s. I would guess that much of the software we're talking about analyses arrangements and applies collaborative filtering based on what's selling at the moment.
In the end though, it doesn't matter. Pop music is primarily entertainment, defined by commercial success. Don't mistake it for Art.
The only thing you can accurately describe as "Scotch" is a sticky tape made by 3M. And it's
Launch.com currently allows you to vote on a scale how much you like/dislike a song - then based on that it recommends other songs to you.
But it doesn't analyze anything in the acutal music.
For that, I would recommend FFT and backprop Neural Nets being added to the existing ranking methods that they have - but in the end, your own brain is likely better at it.
There are some odd things afoot now, in the Villa Straylight.
This is just more evidence of the growing irrelevance of record companies. As technology moves forward, the record companies seem determined to find ways to decrease creativity and thwart musicians, not promote artistry. This will prove a fatal approach, in my opinion.
Musicians can now create and engineer music in their own homes with a relatively modest investment. They can advertise and distribute on the web. By charging a modest sum to download the music, they could quickly out-earn the average 35 cents a cd they now make. When someone (Napster?) comes up with the appropriate delivery vehicle for this scheme, the music-as-big-business era will have come to an end.
Record companies ought to recognize this now and stop treating their talent as noisome middlemen. It seems like they start with packaging and marketing, and add in the music as an afterthought.
But all is not lost --- great musicians want to create great music, and people will want to hear it. You can't keep the two apart.
http://ob-la-blog.blogspot.com/
Maybe they should rank songs in the Top 40 by how many times it is downloaded on Kazaa. I mean, the idea is to rank how POPULAR the song is, what better method than to measure how many people are getting using the most popular method for getting new music?
Yea, I know, its illegal, but at least it would be more accurate. Then again the purpose of the Top 40 is to SELL CDs, not to inform you on what is really most popular.
Tequila: It's not just for breakfast anymore!
I assumed computers were already responsible for top 40 music.