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.'"

Comments

Never would have made it past

[burgburgburg]

1) Bohemian Rhapsody
2) Smells Like Teen Spirit
3) London Calling

Jokes Aside...

[PepperedApple]

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.

Re:open source implementation of hit song detector

[RTPMatt]

hey, how long till i can have it automaticly D/L the songs that i will [Mathematically] like?

Rivers Cuomo from Weezer

[thundercatzlair]

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

Re:Rivers Cuomo from Weezer

[ATMAvatar]

Payolla (sp) is now illegal.

Forgive me if I'm wrong, but while it's illegal, I was under the impression it's still the de facto standard.

If they can run a program that will reliably tell them if song A is more likely to be a hit than song B...

That's a pretty big if. You have to make the assumption that in general, music tastes don't change, and that all hit music sounds the same. You also have to make the assumption that music tastes are not affected by the geopolitical situation or the economy. New genres never become popular and every generation likes the same thing.

If it turns out that the program actually works, what does that say about music? Are we as listeners *really* that predictable? Is music really *that* formulaic? I'm not sure you could even call it art after this realization - there would be nothing to stop another program being written that uses the hit calculation formula to spit out cookie-cutter hit music.

I really hope I don't have to mourn creativity's death at the hands of the knuckle-dragging masses and the "bottom-line."

1984, anyone?

[doubleyewdee]

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.

As a professional musical instrument maker ...

[torpor]

... 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.

Re:It's a great idea, but they've got it backwards

[AssFace]

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.

The growing irrelevance of record companies

[izora]

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.