Offline
Los Angeles

I just tried out this hit computer site Uplaya to see what it would rate my music. It's free to try it with2 songs. The idea is that they have "Hit Song Science™ software that provides immediate feedback on your song´s potential for commercial success and instant legitimization in the market for high-scoring music."

http://uplaya.com/about_hss/hsstech

Anyone else try this or something like it? If so what did you get? I think the site likely says everyone is some sort of hit so they will sign up for their press/promotion service.

Last edited by 8bitweapon (Feb 12, 2010 6:12 pm)

Offline
̛̛̩̥̩̥̩̥̅ ̥⎬̛̛̛̛̛̥̥̩̥̩̩

How could they tell if it's going to be a "hit" or not? Do they just like check to see if it's a cover of that owl city song?
And why would you want "commercial success"?

Offline
Los Angeles

I have read articles about how computers (usually at some major lab  or uni) can breakdown songs and compare them to a database of hits song structures. That being said, I don’t know if this is the same thing.

People want commercial success so you can roll like this:

Last edited by 8bitweapon (Feb 12, 2010 6:43 pm)

Offline
uhajdafdfdfa

I think it's fake, since it took less than a second for my 4 megabyte file to be uploaded.

Offline
Los Angeles

maybe its faster for hits?

Offline
New York City

What a load of bullshit! big_smile

Offline
Los Angeles
akira^8GB wrote:

What a load of bullshit! big_smile

Which is bullshit:

A) the notion that a computer can compare song data to see if it has characteristics of other hit songs or
B) that website? (im guessing this one)

Offline
Planet Zaxxon

Whenever you upload a song to that site it goes directly to Timberland's desktop. Then he "samples" it and makes it a "hit."

Offline
Los Angeles
OxygenStar wrote:

Whenever you upload a song to that site it goes directly to Timberland's desktop. Then he "samples" it and makes it a "hit."


LOL 10 points for Oxy

Offline
New York City
8bitweapon wrote:
akira^8GB wrote:

What a load of bullshit! big_smile

Which is bullshit:

A) the notion that a computer can compare song data to see if it has characteristics of other hit songs or
B) that website? (im guessing this one)

Both, man! big_smile
Just the fact that it has "characteristics" of other hit songs doesn't mean it will be a hit. I can copy how a Snoop Dogg song is and it could not be a hit! Also, this will depend on socio/geographical factors.

A website existing that offers this "service" is 10x more bullshit big_smile

Hilarious link of the week!

Last edited by akira^8GB (Feb 12, 2010 7:42 pm)

Offline
Los Angeles

I think there is software being run by uni's & labs that can identify characteristics that are similar, but yeah, that doesnt mean its gunna be a hit.

And yes, that site is pretty far feetched. lol

Offline
A gray world of dread

Well, I know that there have been some experiments with pattern recognition (fuzzy logic, neural networks) where they fed it 'hits' and then charged it to produce one. Kinda like when they did that with pictures of beautiful people and then had it make a picture- in both cases the result was rather bland, but not too far off the mark.

The idea that a trained neural network could compare input to it's 'perfect' template and then calculates the overlap is viable, but probably not practical (yet). That seems to be what they're offering from what I've read, and a comparison with the DB of the neural network would be very quick (The dissection of the input data should however take a while depending on the width of parameters). The accuracy of the result depends on how well the network was trained, how many aspects of the input are compared and human-made adjustments for exceptions, training errors and such.

So, yes, it could work to a degree. I'd file this particular site under 'toy' though, because I have yet to see a neural network that was trained so well that it could tackle a complex beast like the effect of music on the human brain*, mainly because we still haven't figured out how exactly our brain works. There were some interesting efforts in combining genetic algorithms (evolution based self-writing networks) with AI last I checked on the topic, and complex tasks in areas that are explained well (ie we know most of the system parameters) can be solved. For example, a few years ago a trained network was able to perform the landing operation of a jet.

*) See for example the yet unsuccessful attempts of using neural networks as a translation tool. Language is comparable to music in width of parameters and complexity

Edit:Fixed some Germanglish

Last edited by µB (Feb 12, 2010 9:11 pm)

Offline
The Mountains

It seems legit enough that a program could recognize a hit to a certain degree. Obviously the real hits are chosen by people and not a program but there are very specific formulas and elements to commercial music.

I can't remember their name but there was a band back in the day that sometime during their career decided they wanted to step away from their usual writing style briefly and focus on writing a song that would almost certainly be a number one on the charts.

So they did, and it was, and they wrote a book about it called "How To Write A Number One Hit", and some band in sweden or somewhere went by the book, literally, and also managed to pen a number one single. Pretty rad if you ask me.

Offline
uhajdafdfdfa

The Manual by The KLF? tongue

Offline
New York City

As said, it could indeed recognize patterns of stuff that once formed a hit, but that is not necessarily a hit. A hit tune in music depends on a shit ton of factors way above this  analyzation's scope, like social factors, demographics, geographical factors, time period, culture of deployment, etc. etc.

Thanks for the schooling, µB. Neural Networks is something that always attracted my attention since I was a kid and it's always cool to learn more about the current developments big_smile

Last edited by akira^8GB (Feb 12, 2010 9:04 pm)

Offline
New York, New York
ant1 wrote:

The Manual by The KLF? tongue

I actually was so thinking about the The KLF's The Manual, but seeing that the OP was about AI, I just thought it was too off-topic. tongue