Slashdot Mirror
AI Bots Pick The Hits of Tomorrow
Wolverine Inspector writes "The Music Industry uses a product called HSS (Hit Song Science) made by Spain's Polyphonic HMI. According to The Guardian "while no one's talking about it, it seems that the whole record industry is already using AI to choose hits. From unsigned acts dreaming in their garage, to multinationals such as Sony and Universal, everyone is clandestinely using a new and controversial technology to gain an edge on their competitors."
Even though it costs about $5,200 US/$6,500, many artists are starting to buy it to help them write succesfull songs."
That's just great.
Remember how video card manufacturers were tweaking their drivers to perform well in benchmarks? "Musicians", and I use that term loosely, will be tweaking their songs to score a "hit" on this service. Right, but it will be harder than ever to produce something out of the mainstream when a record exec will look only at the score on HSS and potential effect on the bottom line. Art for art's sake is virtually a thing of the past. Prepare for more of the same on the FM dial! (thank goodness for etunes.com)
Trolling is a art,
Who would have thought that in 2005 technology would
have failed so miserably?
Remember the good old days when the listeners picked the hits?
Next up: bots that generate pop music.
Why the majority of today's music sucks!
...on Slashdot.
*sigh*
It would appear that the music industry is not ailing as much as they would like us to believe.
Air Supply and Ashlee Simpson.
No mod points, no meta-moderating/Firehose/all the other free work Slashdot wants me to do.
So instead of people blaming the HUGE record industry that produces crap, they can blame a machine! Sounds like a scapegoat to me. Either that, or the record execs are SO STUPID when it comes to music, that they have to get a machine to help them out.
I mean, come on. WTF?
How many times are they going to try and force her down our throats.
Many big name "artists" these days have no talent and are just digital hacks. Their "sound" is solely the product of digital reprocessing and manipulation.
Back to my Zappa..
This is not AI. The music companies are using clustering technology.
The basic idea is that you measure certain characteristics of a song,
such as voice quality, cadence, etc. I'm sure the actual
characteristics used are much more complicated, but the idea is the
same. Once you have your characteristics you can build a three
dimensional vector out of a song. After you have your three
dimensional vector, you can then use many different algorithms, one
such is the Bi-secting K-means algorithm to group the songs together.
After you have built your cluster, you take a new song, run it through
the process and check to see how close it falls to a "hit" cluster.
We use this same process for document classification at my work, and I
don't think it bears any relation on AI. As I stated above, it's a
rather simple grouping technique.
There is a downside to this technology though. By measuring how close a
song is to previous hits, you are guaranteeing that all new songs will
be similar to old hits. This type of system tends to minimize or
eliminate fresh new types of music.
(why the word wrapping? Emacs auto-fill-mode)
Doug Tolton
"The destruction of a value which is, will not bring value to that which isn't." -John Galt
Can it generate songs which are cross-format focused and guaranteed to break on radio based on state-of-the-art marketing technology?
I wonder whether "supply & demand" will play a role here. If thousands of artists start producing formulaic output, won't the per-artist demand drop? With perhaps a compensating increase in demand for innovators?
Sheesh, evil *and* a jerk. -- Jade
many artists are starting to buy it to help them write succesfull songs."
Comercially successful != good
---
"I can't complain, but sometimes still do..." Joe Walsh
I think what the music industry needs is a tsunami tidal wave of insipid filth to just wash over the airwaves for several years, and this software has got to be the ticket.
I'm hoping that after another ten years of generic, predictable, and bland popular pabulum, the music-buying public will abandon the major labels and start going to coffee shops to hear something different.
You are in error. No-one is screaming. Thank you for your cooperation.
...to never, ever buy a new album ever again. I'll just use this crane here to put it on the tippity top there, like the star at the top of a Christmas tree.
Is it just me or did the article quote music industry folks as saying the software must work becuase 95% of the hits of the last decade scored highly. The software is a mathmatical model based on the hits of the last century.. so of course it scores them highly.
So, we'll get even more cookie-cutter, mass produced crap that no one can listen to for even a few seconds?
Great!
The creatures outside looked from Alt-Right to Antifa; but already it was impossible to say which was which.
The program works by applying the formula. It takes three variables.
Boobs
The artist must have boobs. The larger they are, the higher this value.
Blandness
The blander it is, the higher this value.
Beat
The stronger the beat, the higher this value.
These are multiplied together.
B * B * B = X
If X is greater than or equal to the Olivia Newton-John quotient, a recognized standard throughout the popular music business, the song will be a hit and we release an album.
If X is lower, we don't do one.
Q: Are there a lot of these kinds of artists?
You wouldn't believe.
Q: Which record label to do you work for?
A major one.
Unknown host pong.
www.lonseidman.com
It is just stuff or back ground noise.
Sometimes I feel like we move ever closer to the story of "Hyperion" - a saga written by Dan Simmons.
And incase you haven't read it, you really should consider doing so.
Turn it off.
Lets hope someday they'll use same kind of AI for movies too...
...as I understand it, the music industry will continue to sell what has successfully sold in the past ( specifically: crap ).
Got it. Nice to know I don't need to budget in CDs in the foreseeable future.
Mod me down with all of your hatred and your journey towards the dark side will be complete!
This announcement from the producers of this record contains important information for radio program directors, and is not for broadcast.
The first cut on this record has been cross-format-focused for airplay success. As you well know, a record must break on radio in order to actually provide a living for the artists involved. Up until now, you've had to make these record-breaking decisions on your own, relying only on perplexing intangibilities like taste and intuition. But now, there's a better way.
The cut that follows is the product of newly-developed compositional techniques, based on state-of-the-art marketing analysis technology. This cut has been analytically designed to break on radio. And it will, sooner or later.
For the station that breaks it first, the benefits are obvious. You lead the pack. Yes, no matter what share of this crazy market you do business in, no other release is going to satisfy your corporation's current idea of good radio like this one. On this cut, we're working together, on the same wavelength, in scientific harmony.
But remember, this cut is constructed for multi-market-breaking NOW. Don't waste valuable research with needless delay. We've done the hard work of insuring your success; the final step is up to you.
SPECIAL DESIGNER SONG FOLLOWS IN 5.. 4.. 3.. 2.. 1.
In a related story, the IRS has recently ruled that the cost of Windows upgrades can NOT be deducted as a gambling loss.
If you look at the likes of Britney Spears, Christina Aguillerra and the like, it would follow that the systems the music industry is using to pick out the 'hist of tommorow' like skin, and lots of it.
For example, many stock transactions are decided by a rudimentary form of AI these days.
Pretty soon we'll have a permanent virtual world where systems run and make decisions constantly, affecting the real world as concretely as any decision made by a human manager.
The NSA: The only part of the US government that actually listens.
Here's the algorithm:
potential hitability = visual nudity / melodic complexity
It works great.
Sincerely,
Pan Tarhei Hosé, PhD.
"Homo sum et cogito ergo odi profanum vulgus et libido."
They care if they make good music.
Sucess [which is a very relative term] is just a consequence of making good music.
If you tweak your music to make it more likely to be a 'hit' instead of what you were aiming for artistically you've already lost.
i saw the baby, and the baby looked at me
Olivia Newton-John no longer has boobs. She had to have a masectomy because her breast cancer was going to kill her and now campaigns to raise awareness about breast cancer.
This was discussed last November, which was a repeat of the same tech from February.
A quick search for "polyphonic" in the music category would've easily picked this up, they're the only 3 matches!
i wonder how william hung scored.
Runnin' On Empty
- The first step in the process for our technologies is to analyze a representative sample of music (up to date we have
- analized more than 1 Million tracks)
Analized? Analized? - what dedication these folks have. Brings tears to my eyes.that episode of STTOS where they visit a planet where they simulate nuclear war based on mathematical calculations and the people who would statistically die in the attacks where supposed to go into a chamber and kill themselves.
Sillyness. Nothing is left to chance anymore.
The label's marketing department are promoting him to the Norah Jones audience. But Polyphonic's analysis has shown that the crooner's song patterns are more similar to Linkin Park, Aerosmith and JayZ.
future HSS developer: You know who I really hate? The record industry.
future HSS collaborator: Well, you should do something about that.
future HSS developer: You're right! Recording execs are really, really, stupid. I bet it'd be easy. I've got a plan.
future HSS collaborator: Sigh... fine, what's your plan?
future HSS developer: They pay us $6000, and we tell them if their song will be a hit or not, then give them some printouts with, you know, clusters of dots on them, random numbers, whatever. Then we say "Artificial intelligence! The magic boxes say this will be a hit because it resembles Tupac Shakur and Wagner!"
future HSS collaborator: You know, unlike your plan to hack people's PVRs to make them think they're gay.... this would actually work. Let's do it. Get me a dartboard.
The good and new comes from no quarter where it is looked for, and is always something different from what is expected.
The bunch of numb nut fuck wads wonder why people don't buy full albums or why sales are down. look at artists like david bowie, who continues to sell. RIAA needs to be killed and the record execs all need to die or get out of the business.
I do not actually recall anything in the books like these hit-bots. Care to explain?
Don't blame Durga. I voted for Centauri.
I just use a bot to listen to the music and tell me if I liked it or not. It mostly says "no", so I assume it's working fine.
Producing something for a desired effect like that is not art, it's a manufacturing process if you make it this automatic. Any monkey can produce such regurgitated music, so why should I pay them, I can buy the software myself and make such music. There is a way to make use of this kind of principle without automating and dehumanizing it, for example, Neil Sedaka wrote Oh, Carol by studying the number 1 hits in a number of countries around the world for weeks and then he drew on that to come to some conclusions which helped him shape his creative output.
This automated way described in the article takes away that creative role from the artist by providing the output as well. Why do you need such monkey artists? If you really want that kind of music just set up a system that automatically generates songs which would be free to download to the first 2,000 people who would be required to rank the song and then at the end of each week make the top ranked song available for sale to everyone else.
An alternative (and cheaper) method is to simply play the song for your 14 years old kid sister. If she likes it it's gonna be a hit.
SIG: TAKE OFF EVERY 'CAPTAIN'!!
Its already generated several hundred ideas using Adam Sandler alone.
"First you get the Linux, then you get the power, THEN you get the women"
make sure your speakers are on
~/.sig: No such file or directory
The major moral, legal and philosophical foundation of copyright law is that an 'artist' utilises his/her creative abilities to create a unique and original piece. Copyright law exists to protect this effort and create incentive. If artists are NOT using their creative abilities and are instead waiting for a piece of software to tell them what statistically will be popular...then I think there is a argument for rethinking giving 'artists' life + 50 years protection.
1. Software is fed with most recent hit song.
2. Software picks next hit song from album.
3. Song becomes a hit.
4. Repeat from 1.
Pretty soon, EVERYTHING will sound similar.
Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
Someday, I hope to see artists successfully and profitably release songs to the Internet unencumbered by industry contracts. When I think about it, pretty much all of the functions of the industry can be replicated effectively by the Internet community today (promotion, sales, distribution, etc). The only things missing are a centralized ratings system and a standard business model. These are not technical hurdles as much as they are problems of critical mass. I think that the more lame and generic industry 'hits' become, the better the chances for a new and better music paradigm.
People should not fear what they do not understand; people should fear because they do not understand.
A subsection of the Music Department composes popular songs especially for the proles, using a special machine, rather than human artistic talent. An especially popular number at this time is "It was only a hopeless fancy," sung by the woman who hangs her washing outside Wilson and Julia's room
You know,Everybody needs to do something - and i guess some people thought of some "Hit Music Predictor S/w " and they made it.And some 'moron' bands are using it.Thats all about it......
I think the music scene is really big,and I believe good music will certainly keep coming,albeit in lesser frequency.
But my weird thought is this:Future Cd's will come with a sticker - ***This artist has a score of 9.5/10 on the polyphonicHMI Rating System "!***
Why does yahoo do this
Just think - you could release two or three versions of a CD! "New & Improved - Now Scores An 8 on the HSS Scale!" Or we could organize record stores by number instead of genre, and we could sterotype the people that are browsing in each section.
I remember a story from my BSc AI course, the US army wanted an AI program to detect tanks in satellite photos. Spent ages training it with countless pictures (with and without tanks).
In the end they had a system which had no idea what a tank was; their training photos with tanks were all taken in summer, those without in winter.
They _did_ have a kick-ass "have the trees got leaves on" detecting program, though.
What betting this system has been trained on "derivative shit", and will detect your quotient of derivation, rather than actually if the world will like your song?
I can't help but think this (and similar issues) is in some small way a lost opportunity for academia, which likes to pretend that popular music (i.e. music that people like to listen to) is somehow less valuable than "serious art music." Here, we have thousands of people who could be leading intelligent discourse on music, many of whom like popular music but won't dare say it because of an unwritten stigma that popular music is "low brow". Because of this, a potentially vocal, educated population that could be smacking RIAA execs upside the head now and again, or at least crying foul, instead relegates itself to the "classical" niche, often the "new music" sub-niche. Said people actually do speak out from time to time, but are so isolated by genre that they seem rarely to be noticed.
As one of said people, please excuse me while I return to my clarinet practice and writing my string quartet.
-- I prefer the term "karma escort."
We're now only one step away from having an actual versificator. Sadly, under current digital rights laws, the versificator will still have more rights than both real artists playing real music and customers purchasing CDs.
I think they're digging their own grave. There is progressively less magical wonders and more blatantly formulaic crap out there.
I can feel a new revolution coming within not too many years. After all - they had the same stranglehold over the music industry in the 80s (and especially the late 80s - how many great records were released in the late 80s?). Then grunge and alternative rock detonated and created quite a bit of upheaval in the business.
You can even go back to the mid-70s. The coked up soft rock they're trying to make cool again got a fist up its ass by punk rock. And the early 60s - demented harmonies by well-groomed stylish young men - and then there was a revolution when the Rolling Stones and the Beatles made girls scream and guys wear their hair longer.
The current dull music scene is the end of a cycle. The revolution will come. Again.
Stop the brainwash
The application of math and science to music is nothing new. What I find odd is that any recording executive would rely on this too heavily. Haven't they ever heard Gwar?
This sounds a bit familiar... I think the RIAA stole this idea from Southpark. Cartman dressed up like a robot (AWESOM-O) to get secrets from Butters... but he ended up in Hollywood creating blockbuster movie ideas. Here is how it went down:
...golden retriever, or something. ...boxer, or something. ...Yes, it's flawless!
Mitch: Punch-Drunk Billionaire!
Producer: Gentlemen, this little boy was kind enough to let us show you his robot. The AWESOM-O 4000. [approaches the robot, who's seated at one end of the table] I've already seen what he can do.
Staffer 1: Uh, excuse me sir, but uh, that's not a robot.
Producer: It's not?
Staffer 1: No, it clearly had bipedal movement, so the correct term is "computerized automatron."
Mitch: Oh, very nice, Mitch.
Staffer 2: You are the smart one.
Producer: Well, regardless, I believe maybe this automatron can help us come up with new movie ideas.
Staffer 2: How can a robot come up with better ideas for movies than us?
Producer: Watch this: AWESOM-O, given the current trends of the movie-going public can you come up with an idea for a movie that will break a hundred million box office?
Cartman: Um... okay. How about this: [the staffers take pen to paper and anticipate the ideas] Adam Sandler is like, in love with some girl, but then it turns out that the girl is actually a
Staffer 2: [thinking over this idea, then write it down] Oh, perfect!
Staffer 3: We'll call it "Puppy Love"!
Staffer 2: Give us another movie idea, AWESOM-O!
Mitch: Yeah yeah!
Staffer 3: Let's hear it!
Mitch: Yeah, we wanna hear it!
Staffer 3: Come on, come on!
Cartman: Okay, how about this: Adam Sandler... inherits like, a billion dollars, but first, he has to, like, become a
Staffer 3: [the producers start writing again]
90% of being smart is knowing what you're dumb at.
Living near New York City, I consider myself lucky to have access to the New York Times Classical Music station. I am so sick of the garbage that has been produced in the last 10 years (Except Eminem, for some retarded reason I like his crap) that I barely ever change my radio tuner off 96.3
As for what I listen to at home and work... Ironically it's all old school stuff from Black Sabbath and Beasty Boys earlier music, plus.. more classical
I wonder if I'm the only guy who's so totally jaded to new music that I touch nothing new, period.
"It's not stealing if you don't get caught!"
The machine "tells them" which artists are likely to be hits, so they then put the big money behind those artists, promote the shit out of them - and voila they become hits. The machine "tells them" another artist isn't worth the effort, they don't get any promotion, they dont sell any albums. It's a self-fulfilling prophecy.
It's the promotion and marketing that made them "hits", not the machine. You tell people that Ice T is a gritty talented actor and musician with real street cred enough times, people believe it. They stop seeing him as an ugly lisping tone-deaf idiot.
Hell, I could have a #1 album and be a major movie star within a couple years - all I need is a good publicist, and really deep pockets.
Kudo's to the company that built this machine. They're printing money based on the idiocy of the execs.
It's only marginally more effective than a focus group, or a dartboard.
But my point is - publicity and promotion make stars, not a machine.
Get over it. If you think talent will make you famous, you're wrong.
I don't need no instructions to know how to rock!!!!
I seem to remember a Piers Anthony series called the "Apprentice Adept" in which there was a game where you could play music. It was judged by a computer, so while your music may have sounded like utter crap to humans, it would be given a high score because it was "technically" right. This reminds me of that.
I've seen a demonstration of what they call "Music Retrieval System Based on User Preferences" which is a music search engine and a retrieval system that can discover and suggest music based on a user's preferences. The project is still in its infant stages but surprisingly it works well on a collection of thousands of popular music CDs. The system currently also features "search by humming" concept, in which you simply sing ur hum your tune and the engine will retrieve the relative song for you. This is currently being developed by KDDI Corporation and will be integrated to next generation mobile services in Japan.
This is my sig. There are thousands more, but this one is mine.
Welcome to Asian pop music... where the only music produced is mass market drivel. See other discussions about how Asian pop has become the only music produced because no one buys music there for a number of reasons, not the least of which is that there are basically no copyrights and music CDs are pirated on large scale.
The music industry might turn itself around; they go ahead and do something this stupid. Music is art. It is not objective. It is not rational. It is not definable. It is not quantifiable.
This system will destroy popular music. It will define the elements of a "hit" song, then it will only determine that songs with those elements could possibly be hits. That ignores the history of music where what's a hit changes from year to year.
I listened to punk rock for decades. In the 80s songs by the bands All and 7 Seconds would never have been recognized by any system as being hits. But fast-forward a decade and suddenly artists like Blink 182 and Greenday ARE having hits using the same formula.
Basically, this system will stagnate the music industry as it will lock it into a very narrow form of music and it will not be allowed to grow. People will get even more bored which will lead to decreases sales.
If someone says he and his monkey have nothing to hide, they almost certainly do.
That's why there is so much crap nowadays. Most of the current 'pop-hits' is so lame it can rival with the 'bothers of the hood' rap.
:-)
;-)
It's so dull, colorless and less-the-original they increasingly have to start showing some boobs or ass (on MTV) to make it even remotely worth listening too. (you could turn of the sound, though
I guess that's the reason why the RIAA keeps its prices sky-high too; they have to make so much effort in marketing to sell their crappy stuff, they can't reach their 85% profit-margin otherwise!
--- "To pee or not to pee, that is the question." ---
I thought ClearChannel picked the hits of tomorrow.
If is there is no torrent is anyone working on an open source project of this? :)
in theory these "AI"'s will update their "opinions" on whats hot by checking out the top 50 songs every now and again.. eventually they'll corrupt their own pool of choices..
It'll be inbreading for music *shudder*
"Consider how lucky you are that life has been good to you so far. Alternatively, if life hasn't been good to you so far
And then when the crud doesn't sell as well as expected, they can blame P2P and sue another 13 grannies. "One Bot to bring them all and in the contracts bind them. In the land of Polydor, where the records lie."
One line blog. I hear that they're called Twitters now.
This has been my approach to songwriting for years...
This announcement from the producers of this record contains important information for radio program directors, and is not for broadcast. The first cut on this record has been cross-format-focused for airplay success. As you well know, a record must break on radio in order to actually provide a living for the artists involved. Up until now, you've had to make these record-breaking decisions on your own, relying only on perplexing intangibilities like taste and intuition.
But now, there's a better way.
The cut that follows is the product of newly-developed compositional techniques, based on state-of-the-art marketing analysis technology. This cut has been analytically designed to break on radio.
And it will, sooner or later.
For the station that breaks it first, the benefits are obvious. You lead the pack. Yes, no matter what share of this crazy market you do business in, no other release is going to satisfy your corporation's current idea of good radio like this one. On this cut, we're working together, on the same wavelength, in scientific harmony. But remember, this cut is constructed for multi-market-breaking NOW. Don't waste valuable research with needless delay. We've done the hard work of insuring your success; the final step is up to you.
SPECIAL DESIGNER SONG FOLLOWS IN 5.. 4.. 3.. 2.. 1....
"Look, Smithers! I'm Davy Crockett!"
In many areas of the US, we're seeing a rise in the demand for organic, non-trans-fatty, less-processed foods (e.g., Whole Foods). Actually, it's more acurate to say we're seeing a rise in the supply. The rise in demand necessarily preceded this rise in supply.
Similarly, if too many musicians over-process their music, we will see an increased demand for more "organic" music that will evenutally lead to an increased supply. The end result might even be better music.
Ben Hocking
Need a professional organizer?
No wonder they are churning out such crap. Music today is about money and fucking. Watch your average video today and tell me it's not true. Bling Bling and asses. The music has nothing to say. You know, people fucked just as much in the 70's, only then they had great music to listen to afterwards. Another thing, notice how all the great artists of the 70's were butt ugly. ACDC would have never existed had they come along only today. But hey at least we have Britney.
Coincidence ? I think not !
Simon is obviously a bot, and he uses his AI to pick the next American Idol.
"Whoever would overthrow the liberty of a nation must begin by subduing the freeness of speech."--Benjamin Franklin
Can we blame the RIAA for force-feeding this garbage down our throats?
Or do we blame the "artists" who sign up for this crap in the first place?
Or, just maybe we should be blaming ourselves for tuning in and/or buying this shit because Britney / Justin is a "hottie" and we want to watch them wiggle around?
With a one album band, they don't have time to renogatiate a draconian contract. Just move on to the next band. Of course you must factor in the money spent on marketing a new act, which would seem to be higher than for a pre-existing one. But I'm sure there is a formula for this too.
Anyone ever see the musical We Will Rock You? It's based on the music of Queen and is definitely tongue in cheek, but the premise is that the world is ruled by a giant corporation, and all music is written by computers. They even have a great pseudo timeline at the beginning (starting with real events and then moving into fake ones in the future), which includes such great things as "ugly people no longer allowed to be rock stars".
Who's "Al Bots"?
Everyone knows computers don't really possess intelligence.
So they'd pick music that is artificial and without intelligence...
I don't know the meaning of the word 'don't' - J
sentimental songs which were composed entirely by mechanical means on a special kind of kaleidoscope known as a versificator
You should not be surprised that you like BOTH Classical Music and Eminem. Mr. Mathers is probably one of the best poets today, disguised as a "Musical Performer".
...you mean, we'll actually have to go outside and see live music in our neighbourhoods to hear something outside of mainstream? Gosh!
"You can drive out Nature with a pitchfork, but It always comes roaring back again." - Tom Waits
... are intricately related. Many AI techniques are forms of statistical inference or statistical classification techniques. Some neural nets implement grouping techniques not that different from k-means.
Any box which learns from a set of data in order to predict future data by implicitly extracting trends and patterns from that data is an implementation of some form of statistical inference algorithm and is subject to all of the general results statistics has to offer about such algorithms. Conversely, statistical inference algorithms are often implemented in ways associated with AI, for example as neural nets.
Given this situation, it's hard to define the boundaries that separate artificial intelligence, pattern recognition, statistical inference and classification and the rest. Of course, there is a legitimate question as to whether such techniques actually mimic genuine intelligence even in principle, and there are other approaches.
From the point of view of terminology, there is a huge range of techniques that can be called AI, and statistical inference is one of them. If you call a VLSI neural network implementing a statistical inference algorithm "AI", then why not call a normal computer implementing a statistical inference algorithm "AI"? Besides, AI sounds a hell of a lot sexier than statistics when you're trying to extract maximum dough from the ample coffers of the recording industry.
"The Milliard Gargantubrain? A mere abacus - mention it not."
The article says: ". . . [an] A&R director at EMI believes that HSS as a hit predictor merely reinforces decisions taken by A&Rs, those record company employees given the job of discovering new songs and artists. "A good A&R has a very accurate instinct for what the market needs," he says - and the fact that 95% of hit songs in the past 50 years are high scorers seems to back him up."
Um, HSS is using past hit songs to define high scores, so the fact that past hits have high scores is not some sort of vindication of the job these mysterious A&R guys have been doing. The real question is why that figure isn't 100% - I'm guessing this is probably because the clusters are fairly wide, so some songs manage to be far enough from the algorithm's definition of the cluster to be classed as non-hits, despite being part of the training set?
I could classify the songs I already know and like, and apply this automatically to new music to let it make suggestions.
And let Amazon know I just patented this idea.
I'm just waiting for some company bent on total worldwide media dominance (Apple, Microsoft, Real, etc.) to develop a personal version of this. Somethis that can be configured to an individual's tastes, and which can then sample and select new music from the company's music library. Sort of a 'Tivo Suggests' for music. I'd buy that.
Did anyone else wonder "who the heck is Al Bots?"
As a test I compiled a list of streams that I though were a little too similar in format (Clearchannel)
Turns out they play songs and nearly the same percentage (varies by maybe 5%) per day.
Even new hits seem to rotate in at the same rate.
It doesn't matter how good the song is, it's the marketing team that can shake clearchannel's hands.
Oddly enough, the AI bot's predicted hit song of 2005? ...
The Laziest Men on Mars - All Your Base
Just because some marketing 'droid calls something 'hot' doesn't mean that anyone out there's gonna like it.
Frequent repetition will utterly kill the radio station that falls for the hype.
Its not a question of skepticism (though the next time it will be engaged,) or of the quality of the hype, or of the quantity.
As long as people listen to other people, that will have a wide spread filter for the crap that's out there.
In a way I don't envy the industry. The very thing that make a band, word of mouth, also kills a band.
Either you're for real of your getting a day job...
MSBPodcast.com The opinions expressed here are my own. If you don't like 'em... Think up your own stuff.
This type of system tends to minimize or eliminate fresh new types of music.
So they must have been using it all the time...
Seriously, this just shows how redundant the "music" industry is. In a market scenario, it would be the customer who chooses what's hot or not among many different channels. Instead, we have a monopolistic dinosaur industry which aims to control the channels and thus the customer's decision. And at the same time they are talking about choice!. Goebbels could have learned from them. Like the Nazis did, they are pouring billions into propaganda.
And $5,000 for the hit-or-not software.
Ah yes, and $1,000 for the artist.
But I'm confident they will stumble upon their own stupidity. Every arrogant industry has gone this way... bye bye!
... Make Your Own.
Seriously. The days of the hegemonous rockstar are over.
Good riddance.
; -- the corruption of government starts with its secrets. a truly free people keep no secrets. --
This will streamline the music even more than today. Rest asure that this will ignite a counter culture.
I really hope that the music industry misses that train and culture is being sold from artist to consumer. Whats missing is the liberation of the radio stations who currently seems to play anything the music bizz tosses at them.
HTTP/1.1 400
funny stuff, they ripped THEMSELVES off, my local "rock" (and i use the term loosely) station played this one night, it was hilarious. for those of you wondering, it plays their original song in one speaker and the new song in the other, it pretty much sounds like ONE song with different lyrics on each side
i hate my local "rock's cutting edge" station, (105.7 The X) EVERYTHING they play has that "Nickelback drone" sound, basically you drag out a long scuzzy chord progression slowly while you growl your horrible depressing lyrics over it. I hate that kind of music, the only other thing the station plays is lame hair-metal from the 80's. Apparently Clear Channel doesn't think that central PA is sophisticated(?) enough for The Killers or Modest Mouse or any INTERESTING music out there.
May you be touched by His Noodly Appendage. RAmen.
...an AS (artificial stupidity) bot?
Who the hell is Al Bots and why should he get to choose?
We now have an algorithm for scoring a piece of music on it's "hit potential".
So how long until this is combined with a genetic algorithm or simulated annealing to automatically pump out "hit" after "hit" without the need of those pesky artists?
"And just as with athletes and performance-enhancing drugs, there is a remarkable reluctance to talk about it."
;)
Don't let McCain hear this... last thing we need is an RIAA drug testing policy. Then we'll have no more good music.
When CDs came out, they were really expensive to the consumer, and they stayed that way for a long time, although the cost to the record companies dropped quickly. Many execs took that extra money home, but many invested it wisely.
The rapid drop in production cost made it possible for major labels to take chances on minor bands. Because of the costs of manufacturing, packaging and shipping vinyl, they used to have to do a run of at least 50,000 records to make a new band worthwhile. With the diminuitive CD, that dropped to 10,000. Because of that, record companies were able to roll the dice on lots of bands who were just enough outside the mainstream that they'd never have otherwise gotten on a major label.
From Laaz Rockit to Greenday, the late 80's saw an explosion of diversity. Not all of it weas quality, but people were able to find more stuff to their liking than ever before, and it was reflected in sales. The inflation-adjusted price of the CD was still WAY above that of the record, but people were buying more music per capita than ever before. And it was the little bands that were doing it. Michael Jackson used to be the big winner for his label, but do you know ANYONE who bought HIStory?
Then I'm not sure what happened. I guess bands like NKOTB started tapping the HUGE kid-pop market with formulaic music performed by no-talent lip-syncing meat-mannequins. I know that the sort of music was available before (i.e. Menudo), but I worked security at one of the NKOTB shows, and the love and dedication I saw in the eyes of the 4- to 14-year olds in that crowd of 60,000 at the Oakland Coliseum was amazing. This music was being rammed down their eardrums, and they were loving it.
Follow it up with similarly targeted bands composed of ex-mouseketeers like N-Sync, Britney Spears and Christina Aguilera, and suddenly you've found a formula that makes the mega-stars mega-important again. Queue up Jessica and Ashlee and all the other teen queens with super-managed images and dubious levels of talent.
I think it's like the story of the goose and the golden egg. The record companies are on a meeeee toooooo run with the trash and with diversity killers like this AI system. But it's just a golden egg. The goose they're killing is the diversity they had for one brief glimmering moment.
The good news is that, with the advent of the Internet, no one record company owns music distribution. They want to put severely limited DRM on their music? Fine! They want to only push stuff that is guaranteed to sell on the mass market? Fine! What'll happen eventually will be a rise of the niche label again, and the fall of the dinosaurs. It might not be quite as dramatic as all that, but the music-sales-bot is not the end of good music. It's just the end of good corporate music.
But me, I'd rather give my money directly to the bands, anyway.
The CB App. What's your 20?
I wonder if I'm the only guy who's so totally jaded to new music that I touch nothing new, period.
Not at all. I get home from work, turn on NPR. Once their news/talk/interview stuff is done at 8:00 I sometimes leave it on at a lower volume, sometimes turn it off, and sometimes fire up iTunes. Never any "new" "music" involved.
I'd *love* to find some new music, but so very little of what's coming out today is worth a damn. It's all either watered down or off-key.
Quantum materiae materietur marmota monax si marmota monax materiam possit materiari?
Obscure Negativland reference: +5! http://www.negativland.com
"You could even cut a tin can with it, but you wouldn't want to." - Weird Al Yankovic
If songs like these are indicative of the tastes of today's youth, I weep for the future.
If construction was anything like programming, an incorrectly fitted lock would bring down the entire building...
Perhaps yet another nail in the coffin for 'traditional/pop' music.
Thankfully, i only listen to alternative..
---- Booth was a patriot ----
Synthetic Pitch 001: Create a film starring Adam Sandler, where he falls in love with ... a golden retriever.
...
"Puppy Love" coming soon to theaters.
Synthetic Pitch 002:
The differences were consistent. It was obvious that mainstream versions had african musical characteristics (rhythm based) whereas the popular versions were more european influenced (melody and harmony).
If you listen to what is mainstream music today, the same patterns emerge. Virtually all pop songs follow the same template. The chorus and verses are always in the same places, the breaks are always at the 3/4 mark etc...
The beats are also important. Pop music relies heavily on the 4/4 beat, with the accent on the downbeat. African influenced musics have a lot of syncopation (accent on the off beat). Syncopation is what makes something "funky".
Lastly, there is a great book called "How to Have a Number One The Easy Way" by the KLF. Its online here: http://www.tomrobinson.com/work/klf.htm
Just follow this to the T and they guarantee you a hit. Its really just a matter of following certain rules and watering down to the least common denominator.
But why do we really like the music that we like?
Becuase we're told to. The fiasco that is Ashlee Simpson verifies this: she came from nowhere, is obviously bad to even the most undiscerning listener, but all of a sudden she's everywhere because she got signed up for the "Star Treatment Package", $19.95.
They push crap like this down our throats because they think they have a "product" and don't care enough to think about it too hard; then they blame poor sales on pirates. Thank God for internet radio. Those bastards are going to sell out to irrelevance if they aren't very careful.
--
$tar -xvf
Must be made +10!! This was the first thing I thought of when I read the title.
7 November 2006: The day Americans realized corruption and incompetence weren't addressing 11 September 2001
Saw this quote at the bottom of the page when reading the comments on this article:
One of the chief duties of the mathematician in acting as an advisor... is to discourage... from expecting too much from mathematics. -- N. Wiener
Slashcode doesn't pick quotes based on context, right? Never seen a quote that seems to fit the discussion so perfectly.
======
In X-Windows the client serves YOU!
Yes, I remember. It was yesterday, when I picked a new Li Yúndí's CD with Chopin's scherzi. I am listening to the most brilliant performance of Frédéric Chopin's scherzo no. 2 in B flat minor op. 31 I have ever heard, right now as we speak. This kid is truly amazing. My point is: who cares what are the hits? We are not forced to listen to them any more than we are forced to eat at McDonald's.
Sincerely,
Pan Tarhei Hosé, PhD.
"Homo sum et cogito ergo odi profanum vulgus et libido."
What accounts for the continuing popularity of the "classic rock" format, then? I'll wager it made some sense in the (early) 1980s when some of the bands that fit this format actually put out new records, toured and looked like something other than Dorian Gray's portrait.
My wife and I were at a restaurant and the muzak being played was a string of classic rock songs; we wondered if anyone noticed that the music they were listening to was in some cases nearly 40 years old. I can't remember the widespread popularity of 40 year old music in 1985, other than an AM station that played Glenn Miller type music that even MY parents wouldn't listen to, and they were born in '35.
Even today bands like Aerosmith, Elton John, Rolling Stones, etc are STILL featured on TV or other SuperMegaPopStar events. It makes you wonder if we need to wait 20 years for them all to finally die off before something else will replace them, besides the continual churn in the narrow top 10 category.
Eigenradio already does this by analyzing top 40 music and generating new music based on that. Too bad it sounds horrible.
Someone post that junk on alt.binaries.warez, please :)
"... 95% of hit songs in the past 50 years are high scorers ..."
I'd like to know which 5% of past hit songs did NOT score well on this AI test!
Similarly, I'd love to hear a horrible piece of music that scores a 10 on this baby. I'm sure out of the hundreds of thousands of songs that have flopped over the years, you could find a few that pass the specific chord progression, pitch, rhythm, and volume tests with flying colors :-)
They can cluster Backstreet Boys and Britney Spears all they want. Just please, pretty please, don't kill any newborn Pink Floyds or Deep Purples with some junky software. This would make me fold little paper boats from my IT degree, that's for sure.
I am putting myself to the fullest possible use, which is all I can think that any conscious entity can ever hope to do.
* first they invite the artist to a lonely dark place.
* [lots of yucky stuff and moaning and panting]
* based on the pitch of moans and efficiency of bjs, the artist is rated
* based on rating, they pick out a hit track, rename it as the one by that and present the artist to the recording company along with the scores
all get happy
grep --count baby lyrics.txt
:}
can I have my $5200 licensing fee now?
Well here in eurasia, our bots produce the hits!!!
Saturday Night Live parodied MPAA's creation of movies, making a roulette-style gameshow starring movie producers.
Frank Zappa: Yeah, but who wants to go through life with a tiny nose and one glove on?
The Russians have won. They have made the world a cesspool of distrust, greed, fear and hate.
Sorry, but I subscribe to the "music's in your blood" theory of being a musician. You've gotta have the passion and the drive to get it out, as well as the desire to explore your creativity. At least that's the way I think.
When people pay several thousand dollars to have a computer tell them what kinda of music they should be making, they're no longer musicians in my book. At this point, they become money grubbing attention whores, incapable of original thought or expresion.
While the real musicians are out honing their craft, and improving themselves, these "plastic musicians" are out trying to find a shortcut to easy street via techniques as this.
The only bright spot for real musicians these days is the fact that as the Net and other technologies become more prevelant, there's many more options for the average listener (the one's who think that if it's not on the radio, then it's not real music). In fact I think that the growing success of podcasting, and shoutcasting is a direct result of people finally getting fed up with the crap that radio forces upon us! Once people realize that they too can easily "dial in" something other than the next Jessica Simpson lipsync'd hit, then this industry will slowly die away.
As proof of this, scan Shoutcast sometime, or hook up with some podcast feeds. You'll soon notice that there's hardly any cookie-cutter pop music being played on them.
Obviously not!
See, the formula is correct.
...ever since Disco died! (Honey, where'd you put my white polyester suit and gold chains?)
"My country, right or wrong; if right, to be kept right; and if wrong, to be set right." --Senator Carl Schurz (1872)
HSS doesn't come cheap. At 4,000 (£2,800) to score a finished CD it's no surprise that some are viewing it with suspicion.
Oh no! America has lost its edge. Not only did a Spanish company produce the software, but there is no dollar figure in the article.
What if you came up with set of criteria and ran your music library through it. Then your player could rcognize what music you are playing/skipping and automatically adjust the playlist to trend toward things you are listening to at the momemnt. Forget random... now it's an educated guess.
"When I die, I want to go quietly, like my grandfather, in his sleep... not screaming, like the passengers in his car."
If I were a musician, I'd tweak just one song to become a radio hit... and count on people buying my record so they can hear the music I really wanted to make.
"The advanced societies of the future will be driven by competing systems of psychopathology." -JG Ballard
Or maybe these techniques are letting musicians dial in to what we culturally desire most in terms of music.
If Bachelor Chow has all the essential needs for life, who are you to disparage it?
What we call folk wisdom is often no more than a kind of expedient stupidity.-Edward Abbey
[% slash_sig_val.text %]
How are they determining hit songs? I mean obviously there has to be a set of 'hit' songs to derive the successful characteristics from. However, since the inception of pop music, they have used questionable tactics to get people to purchase music (e.g. paying radio stations to increase paying). And by that, aren't they only really selecting the songs that they told people to purchase or like, and not the ones that people actually like and would be a hit by themselves? You can't choose a set of unbiased hits, from a set that has already been biased by their marketing.
Maybe the RIAA has decided that, since we've all downloaded the *good* music, they're just going to create crappy pop syrup that no person with two ears will want on his hard drive. If they put enough Ashlee Simpson records out, eventually the downloaders will give up looking new music, and the industry can go back to overcharging for silver platters with decent music.
Secret Industry Memo
From: RIAA
To: All artists
Don't forget- Every time a crappy song is played on the radio, a downloader goes to hell. So record CRAP!
Just out of curiosity, I'd like to see how some of my favourite songs score on such a system. I have a hard time believing that 'Echoes', 'Shine on..', or other great music fits their calcuations very well.
TZ
Otherwise, you could put a genetic algorithm and a synthesizer on the job. Use the HSS application as an evaluation function, and let it crank until it had composed an optimal song. Or just run every free MP3 on the web through. (Now that would be a good idea. Somewhere, there may be a garage band that doesn't suck.)
There's a similar program to predict Wine Advisor scores. If that were easily available, people would be synthesizing the optimal wine.
why not form an indy band and get some gigs
Three things:
Jan 19, 2005: Tune into your local radio station today to hear the latest single from BMG! Britney Spears' "Badgers Badgers Badgers!"
UTF-8: There and Back Again
Whatever happened to playing a song live and gauging fan reaction? Then again, I guess that would require being able to play live...
Who doesn't like free music?
I would be greatly interested in seeing how past hits score with this system. Obviously some, like the ill-conceived "Kokomo" by the Beach Boys, would probably score well, as it sounds like every other Beach Boys hit (almost to the point of parody).
But what about songs that were on the leading front of changes in musical taste? Specifically, I wonder how songs by Hendrix or Dylan would fare? Or the Sex Pistols and the Ramones?
This sounds like a great tool to create songs that would have been popular six months before, but not six months from now. Unless there is some way for the tool to forecast the tastes of the music buying public?
Everyone seems to be complaining about art or the nature of art. Jeez. Doesn't anyone know the algorithm? Only algorithms are true art. That and the Mac Mini.
Why isn't there an Open Source art detector?
Actually there are a lot more words, but "Hit" is not one of them.
"Mass Culture" is something done with bacteria, not people.
"Flyin' in just a sweet place,
Never been known to fail..."
My first reaction to this was that this MUST be a hoax. It's just the kind of thing my friends and I would have joked about in high school. For the record, we also came up with the McCow which is a rectangular (well cuboid) bovine that's stackable. These occasionally get loaded onto trolley cars and driven through an astroturf pasture for the visitors. But that's another story...
My second reaction is that for this to be in any way scientific, we need free access to the source code. It sounds like we're presented with basically one alrogithm that converts a song into 2 or 3 numbers, and these are compared with the distribution of other known-to-be-popular songs. Well, what happens when these algorithms change? How stable are the results against using different algorithms or different constants or different datasets of known-good music? The lack of this kind of in-depth analysis (which would have to be done by an independant party to have any validity) calls into question the whole technique.
I still don't like the idea of a computer algorithm helping to determine what future songs get airplay, but maybe it's not any worse then our present situation. Today we have "top-40" stations with play lists less than 20 songs deep, and big-wigs that listen for the hook in the first 15 (IIRC) seconds of a song.
the marketing blitz (which she didn't get)
I realize that the frenzy is not as intense as when say, a new Britney Spears album comes out, but most indy bands would kill for even 1/100th of the publicity she has been getting.
*cough*Magnatune*cough*
...Had this been an actual emergency, we would have fled in terror, and you would not have been informed.
So its Eurovision Song Contest in a bottle. Not worth gnashing a tooth over.
The retard that modded parent Offtopic has now stepped outside to polish his Yugo. Parent comment is spot on topic and better than most of the comments in this thread.
The recording industry is using an algorithm to determine what songs are going to sell best? Checkmate. Use the algorithm to design a real-time generator of hit-worthy pop music. Congrats, you've just dealt the final blow to an already damaged recording industry. They didn't adapt. They were warned.
I posted it elsewhere in the thread, but you should check out AudioScrobbler. You'll create an account there, download a plug-in for your media player (in your case, iTunes), and configure it. It will automatically submit every song you listen to (assuming you have them tagged right) to the site.
After a few hundred listens (or a bit more, they're adding new hardware soon to speed things up), it'll generate "musical neighbors" for you - a list of people whose musical taste is most like yours. You can browse their top lists to get ideas for music to check out, or look at the "similar artists" pages for the artists you like, which are generated via similar means.
As it's all generated based on what people are actually listening to, instead of crap like "genre" or such, it's of rather good quality.
I've found an incredible amount of new music I like recently due to the site. Almost half of my top list now is stuff I've found in the last few months. It is definitely something to look at.
"You know your god is man-made when he hates all the same people you do."
I echo most honest musicians' take on this (as stated) .. but also do want to say that even mainstream music has become polarized - 5-10 years ago, it used to be pretty much homogenized crap, but now it's split up into utter crap and "hmm, this is actually not bad" - i think a lot of "sellout" musicians have made it past their freshman/sophomoric label-satisfying cookie-cutter crap and are fighting for their creative independence.
.. (although once again, in the spirit of polarization, minnie driver's record sounds like it's worth checking out), so i guess there is still balance.
:)
i mean - alter bridge's record actually has two or three honest to goodness 16th-note riffin' metal tunes instead of your average nu-metal whole-note compressed-guitar crap, and these guys used to be CREED, ffs!
and yet, you have your ashlee simpsons and *insert yet another actress-turned-talented-musician here*s
~A
ps: my post in no way intends to take honest musical credit from the bands that are still struggling to get their voices heard and deserve to and probably never will, nor does it intend to overlook the initial sell-out-age of the bands in question in the body of the post.
pps: shameless self-promotion: blatant innuendo
Linux, Vai, Satch and Guitars.. that is the life ICQ# 7357858
"The music industry has proven again and again that "time" no longer matters. "
No. Customers with short attention spans have shown that it matters a great deal.
"They want acts like Spears, Maroon5, etc who rise to the top of the charts quickly through marketing, consolidation, and payoffs, and who are only there for a short time before the next big thing hits."
Sure explains the "nostalgia" market.
"Touring, actual music playing, and actual singing are overrated. The HSS printout says so."
Same thinking that's putting your job overseas.
A complaint that seems to be going around is that this would destroy creativity in music and force artists to stick to a formula, giving us more of the same crap. If I'm thinking straight here, that wouldn't necessarily be the case. TFA mentioned that some U2 songs were in the same cluster as Beethoven; clearly, from a listener's standpoint, there's a huge difference. This is only looking at various mathematical properties of the music, and the actual sound can vary.
Two experiments I would want to do:
TFA mentioned that they were considering marketing a jazz musician to a different demographic because his music fell in the same cluster.
Experiment 1: have a sample of people list their 10-20 favorite songs. See how often they fall in the same cluster, to see if songs in the same cluster tend to appeal to the same people.
Experiment 2:
In your cluster diagram, create an animation adding the songs to the chart in chronological order. Do the same with removing them in chronological order. Do any clusters appear or disappear over time? Can you find the time period where one cluster is popular, and how long it lasts? Are clusters appearing and disappearing tied to popularity of various forms of music? If the clusters do *not* appear tied to time period, it seems unlikely that basing future marketing decisions on this program would destroy creativity.
Being a (non-commercial) musician myself, and enjoying classical music and jazz, I agree with the caution many people are displaying here. However, these experiments are relatively doable (by someone with unlimited access to the program) and would give insight into just what the clusters represent.
It's got tattoos, it's got a pierced hood,a l
It's got Generation X
It's got lesbians and vitriol
and sadomasochistic latex sex
It's got Mighty Morphin' Power Brokers
and Tonya Harding nude
Macrobiotic
lacto-vegan
non-confrontation
Free Range Food!
It's got the handshake, peace talk,
Non-Aggression Pact
A multicultural interracial non-segregated historical fact
Say Amen. Hallelujah! Say Amen
Certifiable number one smash
Hallelujah! Amen.
Certifiable undeniable solid platinum number one smash.
-Shaming of the True, Kevin Gilbert, 1999
There's a link to a practice of the song here, but keep in mind that it's done by somebody else entirely (KG died before the album was released) and the original is MUCH cooler.
Actually I am a lab rat in an elaborate plot to take over the world.
Computer-generated music is bad for music industry because once it becomes an accepted and popular musical trend than anyone can generate their own music by simply downloading the software and running it through a soundcard or 'softSynthesizer'. There will be no need to buy music recordings from global media corporations. The 'globos' would definitely want to avoid this situation. The best situation for the 'globos' is the way things were in the 1960's. Everyone connected to a narrow number of media outlets, everyone developing an emotional connection to a limited number of 'artists' who were all under corporate contract, and total corporate ownership of the disk and media distribution network.
These conditions lead to a generation that has an abnormal emotional attachment to music, especially recordings owned by media corporations.
Those days are gone. Today's youth no longer have an abnormal emotional attachment to music. Young people today are fine.
Celebrate the future. Weep for the emotionally-crippled boomers who will lose their entire life cultural framework as the 'globos' put their music into permanent DRM limbo.
In an old Archie comic, Dilton used a scientific analysis of the top songs for the best x years to write music for his band.
FWIW, I remember that story too, I think. The author (female) using it got damned depressed because the computer's books were selling better than hers. Can't remember the name, but just verifying you're not crazy (this time).
This sig has absolutely no significance and serves only to take up screen space and waste the time of the reader.
If artists are NOT using their creative abilities and are instead waiting for a piece of software to tell them what statistically will be popular...then I think there is a argument for rethinking giving 'artists' life + 50 years protection.
Especially given that a stochastic algorithm built on music theory will more likely than not reproduce a substantial portion of a copyrighted song. Combinatorics don't lie; music publishers love combinatorics almost as much as pie.
It's just a simulation of the average intelligence of a record exec.
Which is why it can run on a Commodore 64.
Disclaimer: MINAA (Mummy! I'm Not An Animal!)
I've heard of it, and seem recall making a mental note to myself to check it out. I must have mentally lost said note. Maybe it's behind the mental couch.
Thanks.
Quantum materiae materietur marmota monax si marmota monax materiam possit materiari?
If you are under 21, you have all the time in the world to pickup a musical instrument.
In fact, it's not as much the people under 21 who are playing but rather the people under 21 who are listening. Most establishments in my area where people of any age play live music are considered bars, and independent bands can't afford to get on commercial radio, so how would kids in high school learn that local indie bands exist? The way to reduce the RIAA's power to buy laws is to get the teen-age masses to stop buying its members' records; how can we go about doing this?
I do know how to read music - took some music composition in college
Yes, we have no original melodies. I used to write music; then I read about Bright Tunes Music v. Harrisongs Music, 420 F. Supp. 177 (S.D.N.Y. 1976), which held that subconsciously copying something you heard a decade ago is infringement. When were you studying music in college? Was it before Bright Tunes and other judicial decisions that expanded the scope of what is considered misappropriation of melody? Is it even possible to create an original melody anymore?
They don't need that AI crap to know if the song is any good just ask me I 'll tell them.
Maybe some of these 'so-called musicians' have tired of ratty hotels and washing dishes to support their desire to play music? Why does what is played for the public have to be the limit to what they play. Can it be that you're a little jealous because they've found a gig to support their avocation that makes them rich, and you haven't? And what's so wrong with being a "money grubbing attention whore", as long as you're being paid handsomely for it? Where is the honor in turning down fame and fortune for the sake of turning down fame and fortune?
Aah, change is good. -- Rafiki
Yeah, but it ain't easy. -- Simba
no hits, but I love him
Weasels Ripped my Flesh
...they'll need bots to listen to the music, too.
It accomplishes this by mapping the patterns of hit music from the past. Songs can then be compared to the database of patterns that are known to be appealing to see if they match a known pattern.
No doubt there are other patterns that have never been reflected in American pop music that are also appealing, songs that fit that category will not be identified.
Are there other factors that come into play besides just the intrinsic appeal? Of course, plenty of music fails to match any intrinsically appealing pattern and still does ok because of external factors. Nevertheless, big hits that will be appealing for years to come will do so by appealing to the audience at a very basic level. This software helps to test if a particular song has that potential.
If you read the article, you would note that two radically different pieces of music can both match the same basic pattern. I'd say this software is likely to reduce the production of music that isn't intrinsically appealing, and will have no effect on new music that hits on a new pattern that has not yet been discovered - songs like that will take off despite the music industry.
*This may be somewhat culturally based, though I suspect that the cultural aspect is not very strong.
--- There are two kinds of people, those who accept dogmas and know it, and those who accept dogmas and don't know it
Don't worry. Hardly anybody is going to mistake a prefab major-label pop act for a group of musicians.
0 1 - just my two bits
A short story by Arthur C. Clarke describes one possible consequence of this sort of thing. The scientist involved builds a computer to study the underlying theory of music, harmonic relations, wave analysis, frequency distribution, etc. and how it interacts with the brain on a physiological level. His search is related to the notion that all existing tunes are crude approximations of the fundamental melody that has eluded composers for centuries (basically a rehash of Plato's theory of ideals applied to music.) The scientist is later found in a permanent catatonic state in his lab (by his tone-deaf assistant) with the Ultimate Melody repeating over and over in an endless loop. Because the overwhelming power of the Ultimate Melody (the ideal form on which all melodies in the universe are patterned after), his mind is completely dominated by it--much the same as when a catchy tune gets stuck in your head for days, only much more powerful. The melody formed a fugue in the pathways of his brain, going round and round forever, obliterating all other thoughts.
the RIAA will soon use similar AI technology to predict who will pirate songs, which songs will be pirated, and when such piracy will occur. The goal is to have the lawsuit issued in mid-download, effectively catching the pirate in the act.
If they use this sort of things, then they could hardly be considered artists
"The Music Industry uses a product called HSS (Hit Song Science)"
Shouldn't that read SSS (Shit Song Science) ?
If they use the same computers at the BCS, we're screwed.
and here I thought all music was made a guy named Roger somewhere in the bowels of hollywood.
Keep in mind that the Beatles were so new and different that any scalar rating algorithm like this would have dumped them, for say, The Four Freshmen or some such.
Mumia Abu-Jamal is *laughably guilty*. Check the evidence.
A technology like this can only mean one thing:
The destruction of all originality and creativity, unless we fight to preserve it.
This makes me sick...
Really, I am feeling sick...
We owe all this to the people who first put the words music and market together into a phrase.
God help us.
That is just great. Now that we have pre-formatted music since a while and an automated way to find a "hit" song, we do no longer need artists to write songs or anything.
To me that's good news!
Seriously speaking, although I am not surprised, this is very sad for the future of music.
Worse thing is that it is BECAUSE of that damn software that we now have to hear Norah Jones and her awfully boring songs all the bloody time.
given the sheer amount of classical and other music in the public domain, I am sure a smart lawyer can find prior art for just about every contemporary melody out there (has anyone tried that to defend against frivilous lawsuits, I wonder)
This is one place where copyright law differs from patent law. In order to mount a prior art defense under copyright law, the alleged infringer has to prove that he or she was aware of the public domain melody at the time of writing the song. Remember that in a civil case, the burden of proof is on the party with less money to spend on legal representation and expert witnesses.
why not promote streaming audio of all-indie internet 'radio' stations, as one example?
Easy. The only Internet service available from a moving motor vehicle is IP over some GSM or CDMA network, and that's too expensive for most parents or young adults to afford. No, they can't just record a stream on a cassette, CD, or MP3 player, as many high schools prohibit students from carrying electrical or electronic equipment, such as a "potentially disruptive" iPod, onto school property or onto any school bus without express staff consent.
SMS all your friend's cell phones with the URL to your favorite Indy station etc. (be creative)
And it'll work only when they're sitting in front of a computer.
Who here agrees that the music industry basically peaked in the early 90s and that nearly all of the stuff in the last decade was misogynistic crap rap and teeny-bopper tunes?
You seem to have developed your own little universe where an "artist" is somehow above the common musician because of some hair-splitting difference in "intent". In order to help you deflate this pretensious tomfoolery, I'm now going to reveal a great secret imparted to me by my 10th grade English instructor.
All great literature was composed for one purpose:
To make money.
So drop the coffee house tone, already. Most of the musicians that "produce a piece of work intended to convey emotion and inspire" in a garage somewhere suck just as much as most of the ones hand-picked by record executives for the size of their breasts. Actually, more, because the hand-picked ones can usually comprehend at least common time.
...it's really a sad day for America when we require a goddamn ACT OF CONGRESS to make our DVD players work properly. ~
No, no, no.
"In this modest home we find one Earnest Scribbler: writer of jokes. In several moments, he will have written the funniest joke in the world, and as a result, will DIE laughing...."
The Funniest Joke was written by a lone comedian... they had a team of linguinsts translate it into german one word at a time (one translator saw two words and had to be hospitalized for a week).
It was the Germans that used the mathematicians for their counter-joke, which was "Two peanuts vere valking down da street, unt one was assaulted... peanut! Ho ho ho." Truly an ill omen for the quality of music selected by this bot...
...it's really a sad day for America when we require a goddamn ACT OF CONGRESS to make our DVD players work properly. ~
With some AI in there, the music industry can finally claim to have some intelligence.
I've long suspected that somewhere in the dark recesses of the Walt Disney complex, there rests a small room full of activity. In the center stands a device about the size of a photocopier, with a large opening at one end, and a slot at the other. Out of the slot, a constant flurry of movie and television scripts fly, piling up incoherently on the ground. At the other end, a migrant worker of indeterminate origin shovels manure into the large opening, fueling the device.
Also, for some reason, I picture the thing being crank-driven, with a monkey turning the crank.
I suppose I would apply the same thinking to modern music. I just hadn't thought about it that much.
Happiness is relative, Based upon the way we live.
it isn't working.
How's my programming? Call 1-800-DEV-NULL
"If you can tell me subjectively why I like one particular song versus another, please do."
Social training. What do I win?
...it's really a sad day for America when we require a goddamn ACT OF CONGRESS to make our DVD players work properly. ~
This reminds me of that one episode of South Park where Cartman dresses up and pretend he's a robot to play a trick on Butters. He actually gets hired by Hollywood (who believed he was a robot) to come up with new ideas for movies. He came up with thousands... most of which starred Adam Sandler. /vince
You've gotta have the passion and the drive to get it out, as well as the desire to explore your creativity.
You forgot acqured technical ability stemming from extensive education or massive quantities of experimentation.
...it's really a sad day for America when we require a goddamn ACT OF CONGRESS to make our DVD players work properly. ~
But that isn't the right answer. Why do I like different songs from other people in my same social circle? How could "social" training train us differently? There is certainly more than that.
If someone says he and his monkey have nothing to hide, they almost certainly do.
Everyone seems to be saying (as was my first reaction when I read the story) that this will lead to everything sounding the same, being bland, etc - as if that wasn't already the case. However, I believe there is cause for optimism - because when something good comes along that really doesn't fit the "hit box" it will stand out so much above the background mush of the rest that it will be worth taking notice of. When I was growing up mainstream music seemed to be a lot more diverse, and you had to pay close attention to really keep up with what was going on. It was hard work (but usually rewarding) to sort the good from the bad. Now all you need to do is keep the radio on but turned down low so you don't actually have to listen to it, but loud enough so that when something interesting does get played, your brain suddenly wakes up and notices it. Thus it becomes much easier than it used to be to pick out interesting stuff. Thanks, lazy pigopolist music industry-type guys!
:) entering at number one was virtually unheard of - Slade's Merry Christmas Everybody did it in 1973, the next one to do so was about 5 years later! And back then you needed to sell hundreds of thousands if not millions of records to make No. 1. So basically the music industry has ruined what used to be a useful indicator of popular taste (within limits) into something that isn't even a useful indicator of how successful their marketing is, except in pure binary terms (number 1 = did OK-ish, not number 1 = flop). Basically the chart has been quantised down into fewer and fewer bits. I say it's time it was officially abandoned altogether, though those of us with any musical sensibility personally abandoned it some time in the early 1980s.
If you think I'm joking, consider this. The UK has just now "celebrated" the 1000th number one record in the charts. The track in question is Elvis Presley's tune One Night from about 2000 B.C. Last week's number one (the 999th) was Elvis Presley's Jailhouse Rock. Hrrrmm... could there be a marketing campaign around promoting Elvis records? Perhaps to help flll up the special "limited edition" (only 500,000 issues!) box sets of Elvis's Greatest Hits that were flogged off the other week, a bargain of an empty carboard box for only 10.99GBP. Marketing genius really, get the punters to stump up for an empty box, then get them to fork out 3 quid a week for fifty weeks to fill it! (Elvis fans - just say no!)
Every number one nowadays comes IN at number one, because of hyping and marketing techniques. But the 1000th number 1 needed only 29,000 sales to make it there. Of the last 530-odd number ones, all but 2 entered at number one. This makes the chart meaningless. Back in my day
Based on my work with AI this smells like a logical fallacy to me. It is likely that this system is picking out a very small subset of the patterns which make a song a hit. So this system may be able to accurately pick out songs which are in fact hits from those that aren't. However, that does not necessarily mean that any song with a high score will be a hit.
If an artist were to use this system in a tight feedback loop, tweaking his music until it got a high score, the music likely would lack many of the other features of good music, and it would probably sound terrible!
A good research experiment (for those of you who are grad students ;) would be to take the artist out of the loop completely and use genetic algorithms to build a MIDI song which would score high according to this rating system. Would that song be a hit? I doubt it. Would it even sound like music? I doubt that too.
-- Marcio
that Britney Spears sucks.
I, for one, welcome our computerized music overlords...
Lodragan Draoidh
The more you explain it, the more I don't understand it. - Mark Twain
Next up: bots that generate pop music.
Heck, legend has it that Autechre has been doing that for years, except instead of pop music they make schizophrenic robot music.
I'm surprised no one has tried to implement machine learning to get "hit posts" on Slashdot.
Someone ought to write an evolutionary program that generates songs to max out the score on this program. I would be interested in hearing what it sounds like.
...and it carries some rather stiff penalties.
Because I work for a radio station, I am familiar with what the FCC Rules say about it. You DON'T want to be involved in ANY kind of "pay-for-play" activity. The fines are substantial, and the station would jeopardise its license.
Willie...
Next.. to factor X,
applying S * E to transform factor X in the following manner, you arrive at a new equation:
S * E * X = SALES
Versificator from 1984, anyone?
Hopefully good instrumentation will get high marks on these things. It seems like every hit song in the last ten years has been extremely focused on the vocals. When was the last time you heard a nice, long guitar solo in a song that got radio play?
Those damn proles will swallow whatever plays every hour on the top-40 station anyway.
Perhaps I wasn't clear. My point wasn't that you couldn't discriminate between "statistical inference, pattern recognition, classification and the rest", but that it was hard to draw a line between AI and each of these, as AI involves at least elements of all of them.
You're absolutely right that these areas of mathematics are well defined. It's artificial intelligence that's poorly defined, which is inevitable because intelligence is poorly defined.
"The Milliard Gargantubrain? A mere abacus - mention it not."
http://www.last.fm/
In my book What is Music? Solving a Scientific Mystery, I discuss predictive algorithms, generative algorithms and (in the last chapter) the Future of Music.
A predictive algorithm is one which accepts music or alleged music as an input, and outputs an estimate of its musicality. A generative algorithm is one which generates new and original music. The secret Hit Song Science algorithm is a predictive algorithm. The Future of Music (according to my book) is that someone will eventually discover a generative algorithm, and when that happens, and we all have an implementation of it installed on our computers, much of the existing music industry will become irrelevant.
In the Hit Song Science FAQ, Polyphonic HMI state that their technology cannot create new music. So they are not claiming to have a generative algorithm. Also there is the obvious fact that they have to get other people to send them musical items.
In principle a predictive algorithm can be converted into a generative algorithm, simply by feeding randomly generated music into it until an item of music is found that has a high score. The practical problem with this approach is that strong music may be very rare compared to not so strong music, so you will be waiting a very long time for a hit to be found. However, unless there is something intrinsically irreversible about the predictive algorithm (in the sense that a cryptographic hash function is intrinsically irreversible), it should be possible to reverse the predictive algorithm in some way to define a generative algorithm which generates different items of music, such that the generated music scores highly according to the predictive algorithm.
As I point out in my book, it is very unlikely that we will discover a complete predictive or generative algorithm until we properly understand the biology of music, i.e. what happens inside our brains when we respond to music, and why such a response has evolved.
The details of how Polyphonic HMI have developed their algorithm raises some further issues:
Is my book a better deal than a Hit Song Science report?
Music: a super-stimulus for the perception of musicality. Musicality: a perceived aspect of speech.
The bottom of the barrel does look funny.
Benny Benassi & Panjabi Mc form an excellent and obvious examples of HSS-better-score modded and tweaked "songs" if this trash can be called so.
:)
strange that Average Joe's brain complys with this HSS technology. Or he just follows anything this Stylish Radio Guy tells!