| T O P I C R E V I E W |
| Cult_Of_Frank |
Posted - 01/18/2005 : 07:34:32
Just when you thought the state of the music scene couldn't get any worse. How people even accept this manufactured garbage as music anymore is what eludes me. Thank God for indie:
http://www.guardian.co.uk/arts/features/story/0,11710,1391951,00.html
Together in electric dreams
Monday January 17, 2005
The Guardian
quote:
A computer program is changing the face of the music business by allowing record labels to predict a hit at the click of a mouse. Is this the death of pop as we know it, asks Jo Tatchell, or a new hope for unsigned bands everywhere?
Norah Jones ... HSS predicted her success despite industry scepticism
Martin and Ruth, aka Spike, the next big girl/boy duo (so they hope) add some synth and a new background vocal to the mix. He saves the song and she emails it to Polyphonic Human Media Interface who, within 24 hours, will tell them whether their song will be a hit. When the results arrive they hover over the 20in screen and click on the returned mail. There is a graph, showing a cluster of many dots, like a constellation, and somewhere in the cluster a red spot. The spot marks their song, not quite a bullseye, but still in the throng. "It's scored a seven," Ruth says, scanning down. "We're in. The record company will definitely meet us now." Their future suddenly looks a lot rosier.
Sounds unlikely? It shouldn't. Because, while no one's talking about it, it seems that the whole record industry is already using just this process. 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. And just as with athletes and performance-enhancing drugs, there is a remarkable reluctance to talk about it. But the secret is out: the record biz, once that bastion of wayward creative flair, is succumbing to the plain old-fashioned science of statistical analysis.
The magic ingredient set to revolutionise the pop industry is, simply, a piece of software that can "predict" the chance of a track being a hit or a miss. This computerised equivalent of the television programmer Juke Box Jury is known as Hit Song Science (HSS). It has been developed by a Spanish company, Polyphonic HMI, which used decades of experience developing artificial intelligence technology for the banking and telecoms industries to create a program that analysed the underlying mathematical patterns in music. It isolated and separated 20 aspects of song construction including melody, harmony, chord progression, beat, tempo and pitch and identifies and maps recurrent patterns in a song, before matching it against a database containing 30 years' worth of Billboard hit singles - 3.5m tunes in all. The program then accords the song a score, which registers, in effect, the likelihood of it being a chart success.
Ever since its initial trials, HSS has proven a hit with record labels who sent material to Polyphonic in hope of a second opinion. HSS confidently predicted Norah Jones's meteoric success (tipping no less than 10 songs on her debut album Come Away with Me) well in advance of her chart-topping appearances and in the face of an industry unconvinced she would have any commercial impact. HSS also picked out all the Maroon 5 hits, including both This Love and She Will be Loved. Other artists, including Anastacia, J-Lo and Robbie Williams are also rumoured to have asked for the hitmaker's analysis.
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. Certainly Mike Smith, 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.
Tom Findlay of Groove Armada puts it into perspective: "HSS is a kind of polling instrument, but a lot of artists already poll stuff as they create it. We do. With [their song] Superstylin' we DJ'd various versions to see what kind of reaction each got live." What human beings may lack in mathematical accuracy they make up for with cultural understanding. Besides, Findlay says, "while there is a rules of construction in play - verse, bridge, chorus and so on - the aim as a musician is to make the musical statement you want to make. The end game is not to get the mathematics right." Though that doesn't mean it shouldn't be a money-spinner too.
HSS's crucial design flaw is that it can only look at the past. Those "leftfield", illogical and grassroots-inspired departures from the norm, such as disco or drum and bass, could not have been predicted - but they shift the mainstream and provide the momentum any culture needs to remain fresh. As Smith says, "Art is the one area where people can, and should be able to, make radical statements. Anything that encourages safe, consensus-driven music should be used with caution."
So perhaps it isn't so much about what the software does, but more about what it says about the music business. Some of the biggest names in the industry - such as the former head of Sony Records UK, Muff Winwood, and Tommy Mottola (the man who has put more divas on the map than anyone - and in the case of Mariah Carey, married one) - have backed the software. Labels within all of the major corporations are now using the software. It seems only a matter of time before it reaches tipping point to become an industry standard, like Dolby or ProTools.
Of course, the appeal to record labels is obvious, as it offers a rational underpinning for commercial decisions. With the recordings themselves being the least expensive element of launching an act, the marketing resource being the greatest, and most companies being run by bean counters, we can be certain that this kind of analytical software won't go away.
But neither is it all bad. Ironic as it seems, with the industry struggling it may be that radical application of HSS could inject some much-needed energy into the business. Mike McCready, CEO of Polyphonic, believes HSS will help executives make braver artist-related decisions. A high HSS rating may, paradoxically, encourage bolder, more unusual signings.
It's all in the clusters, you see. Hit songs, typically, fall into one of a number of groupings - there are around 50 in the US and 60 in the UK where, traditionally, tastes have been more diverse. Belonging to the same cluster does not mean songs sound the same, though, more that they are mathematically similar. And the analysis has thrown up some very unlikely musical bedfellows: Some U2 songs are in the same cluster as Beethoven, while spandex ultra rocker Van Halen sits right alongside MOR piano babe Vanessa Carlton. It is for this reason that Polyphonic are confident their software won't homogenise our already stratified and similar sounding charts. They are already working with one radio station to expand their playlist without losing audience share by selecting songs with the correct mathematical rhythms. In a world where drearily repetitive playlists have become the norm this could be the answer to an oft-uttered prayer.
This strategic approach may seal the software's place in history. McCready explains how they are helping a very well known "smooth male jazz crooner" who is finding it difficult to break into the US market. 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. This kind of interpretation offers an unprecedented rationale for appealing to a seemingly unlikely demographic.
There is also an HSS Basic model on offer to struggling musicians. With a good score, the story goes, you will get a record company to take a second look. While some artists may be lost under this new regime, others will surely be found.
But its greatest usefulness might be, as Smith says, in "helping with that all too frequent record company problem - a band that has written an album without any hits on it. Using the technology they might be able to write the radio-friendly songs required for the album release." For any artist that relies on success in the singles charts this technology provides a useful barometer of work-in-progress. Ric Wake, producer of international acts such as Jennifer Lopez and Anastacia, has drawn the technology into the heart of the creative process. When you're only a few "mathematical rhythms" away from a great hit this could save hours, days, even weeks of studio grind. At the end of each day relevant tracks are downloaded and feedback is presented the next morning. Supporters of the software argue that it does not detract from the artistic process; it is still the humans who must find the solutions to a low-scoring song.
Ultimately HSS is like focus groups to advertising, or audience research to film - it helps those afraid to be accountable to make decisions. But make no mistake; HSS aims to become a generic term, as Hoover is to vacuum cleaners, and a standard part of the signing and creative process for labels and producers. "'What's the HSS score?" should be in the first line of questions of any band at any stage of their career, says Tracie Reed of HSS. "We promise 100% success rate for songs released rather than the usual 20%. Which makes it a justifiable investment." And it would have to be in the current cost-cutting climate.
Though it might make the accountants happy and ultimately, even the artists and audiences too, isn't HSS just still a little, well, boring? Isn't half the fun of the pop industry the mistakes, legendary, apocryphal episodes that go into making the best - and worst - of the records we listen to? With HSS would we have had Led Zeppelin's Red Snapper escapades (no singles here), Brian Wilson's lost Smile album, Jeff Buckley et al?I doubt it. But while there's no doubt the romance has gone and while it might feel like a sad mathematical indictment on these most indecisive and creatively fearful of times, you had better get used to HSS. Your listening DNA is about to be mapped.
 "Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| 33 L A T E S T R E P L I E S (Newest First) |
| Visiting Sasquatch |
Posted - 01/21/2005 : 06:05:04
I guess my attitude to this is good for them, it doesn't affect me at all. I don't listen to popular radio or CDs. Like the article said, because of this machine, there will be some artists who WILL be overlooked and never heard. And because it will keep reaffirming pre-fap formulated pop hits, it can only predict more of the SAME. Same same same. Who cares. |
| Daisy Girl |
Posted - 01/20/2005 : 20:19:07
quote:
Originally posted by VoVat
I can't wait for someone to submit something random and nonsensical, and have the program report that it'll be a hit.
"According to HSS, the next big hit will be this recording of someone's vacuum cleaner."
"Reunion? Shit union!"
It is a statistical certainty based on the model... but to see this proven in the marketplace would be less likely... but there is William Hung!!!!  |
| Cult_Of_Frank |
Posted - 01/20/2005 : 19:24:56
And the publicity of people wanting to hear that vaccuum cleaner and what the fuss is all about would doubtless make that a self-fulfilling prophecy. :)
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| VoVat |
Posted - 01/20/2005 : 19:12:25
I can't wait for someone to submit something random and nonsensical, and have the program report that it'll be a hit.
"According to HSS, the next big hit will be this recording of someone's vacuum cleaner."
"Reunion? Shit union!" |
| Cult_Of_Frank |
Posted - 01/20/2005 : 13:13:36
That is pretty bad, K. I don't even listen to Canadian stations, except the occasional CBC and CFCR.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| Homers_pet_monkey |
Posted - 01/20/2005 : 12:54:46
Ours is so bad that I just don't listen to the radio, except online and only at certain times.
http://www.thefutureheads.co.uk/ |
| kathryn |
Posted - 01/20/2005 : 12:22:15
Trust me, Homers, US radio is much worse than you might imagine. This is how bad it is: I listen to the Canadian stations that I can tune in!
Seriously, COF, I do agree with you, it is a scary new low.
I still believe in the excellent joy of the Frank |
| Homers_pet_monkey |
Posted - 01/19/2005 : 14:45:04
I can't see how radio stations in the US could be much worse than ours. They MUST be bad if they are.
http://www.thefutureheads.co.uk/ |
| Cult_Of_Frank |
Posted - 01/19/2005 : 13:11:33
This has little to do with what we listen to, I agree. I'm also well aware that radio "music" is focus tested and playlists are dictated by higher powers who think they know what's best and play "what sells". But to have a machine analyzing what music is to be made in the first place is, I would say, a new low and certainly a very overt way of doing something that perhaps until now mass skeptics (who believe in radio/today's "music") would have denied.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| Cheeseman1000 |
Posted - 01/19/2005 : 13:02:35
That's why I like living in the UK. Although there's a large number of pretty bland radio stations, a lot of the time we retain a sort of attitude that being such an important exporter of music, we have a duty to keep making and playing good music. This is why, on most of the major stations you will be able to find some decent programming.
Also, we have a publicly funded main broadcaster with a job to do, i.e. not just provide huge listening figures, but to 'improve' us somewhat. How do you explain the consistent appeal of John Peel for example?
We are pretty much sans ClearChannel, and its good.
And if a double-decker bus
Crashes into us
To die by your side
Well, the pleasure and the privilege is mine. |
| kathryn |
Posted - 01/19/2005 : 12:56:50
This isn't that radically different from what's been going on
for the last few years on the radio, in the States at least.
What you hear on the majority of U.S. radio stations is something
a DJ thousands of miles away pre-recorded the day before
(including the weather, and the chit chat about xyz taking place
downtown) and emailed (his/her voice tracks) to the
corporate drone running your hometown phantom
radio station.
The songs you hear (especially on Clear Channel stations,
which are the majority of stations) are selected through audience
testing, which is an Orwellian exercise, focus tests taken to
the extreme, where a group of people (fitting a precisely targeted
demographic) are "invited" to sit in an auditorium, eat some baked
goods and click a little handheld device the second they recognize one
of hundreds of song snippets being played. Out of the most
"recognizable" and "preferred" songs, the Clear Channel
programming gods devise playlists, which are then sent
to the properties (radio stations) across the country so that
a programmer (what used to be a DJ talking live and playing
whatever music he or she liked) can preprogram on a computer
days and days in advance a station's music, then dump the
commercials into the program and the aforementioned human
voicing from hundreds of miles away. Voila! Bland, uniform radio,
Clear Channel style. Radio with a condom. Safe and boring.
I still believe in the excellent joy of the Frank |
| Steak n Sabre |
Posted - 01/19/2005 : 12:29:20
I don't think I've ever really listened to 'hit' songs anyway, at least since those Beatle guys, so it's not like some software is going to make any difference to me. Yet again consumers will end up paying for something they did not ask for....
The Cult of Frank 2.0: It's not the coming of the aliens or anything... |
| Homers_pet_monkey |
Posted - 01/19/2005 : 04:44:31
Not really a dig, that's a bit harsh. I just think that it's a little sad if we are gonna end up having technology dictate everything to us. I mean, I am far from a technophobe, but I think that this is a little too far. I know that the end product may still be shit, as most chart music is, but I just prefer the idea of a human making that mistake, not a machine.
Some say I'm a dreamer, but I'm not the only one.
http://www.thefutureheads.co.uk/ |
| ObfuscateByWill |
Posted - 01/19/2005 : 04:39:08
Eh, I'm certain that's a dig.
What did I miss?
 Take a bite of the chocolate coffin. |
| Homers_pet_monkey |
Posted - 01/19/2005 : 03:34:31
I think a point just flew by.
http://www.thefutureheads.co.uk/ |
| ObfuscateByWill |
Posted - 01/19/2005 : 03:03:04
quote:
Polyphonic HMI, which used decades of experience developing artificial intelligence technology for the banking and telecoms industries to create a program that analysed the underlying mathematical patterns in music. It isolated and separated 20 aspects of song construction including melody, harmony, chord progression, beat, tempo and pitch and identifies and maps recurrent patterns in a song, before matching it against a database containing 30 years' worth of Billboard hit singles - 3.5m tunes in all. The program then accords the song a score, which registers, in effect, the likelihood of it being a chart success.
I guess all of the songs share something in common. Don't know if I'd say there seems to be a set standard.
U2 and Beethoven are in the same "cluster"
-
I think this will be a great. (Maybe kinda Orwellian.)
Music we could all agree is catchy/listenable.
-
May even bode well for the indie crowd. The bands you love to support will have their songs analyzed, polished, and cause suffocating recordstore stampedes upon release.
Take a bite of the chocolate coffin. |
| kathryn |
Posted - 01/18/2005 : 19:26:07
Good question: what is the standard of a "hit"? My human preference
has evolved into Frank's music, and we all know how many "hits" he's had.
So what does it all mean?
I still believe in the excellent joy of the Frank |
| Daisy Girl |
Posted - 01/18/2005 : 19:23:15
It is a good idea. People (consumers) get the music they want, musicians get the success they want and everyone is happy. Honestly, I think this is an honest technology unlike lets say... lipsincying.
I have worked with and built less complex models such as this. This is a causal model using muptlipe regression models.
"The key thing to pay attention to is this model is as only good as past data (songs)HSS's crucial design flaw is that it can only look at the past. Those "leftfield", illogical and grassroots-inspired departures from the norm, such as disco or drum and bass, could not have been predicted - but they shift the mainstream and provide the momentum any culture needs to remain fresh. As Smith says, "Art is the one area where people can, and should be able to, make radical statements. Anything that encourages safe, consensus-driven music should be used with caution."
They key ramification is that cutting edge bands-- will have an increasingly more difficult time to sign a major record label.
Many businesses use this type of forecasting-- that's all it's doing.
I do question their assertion that this model is 100% accurate in predicting a hit-- no model, no matter how good it is-- is 100% accurate!
And keep in mind there will be acts that choose not not to create a mega hit given the choice-- they would rather choose to be "indie" anyway.
The next stage in this... the company will trend these 50 or 60 factors that make a hit. They will track them over time and from past movement. From this past movement, or trend, the software company will then decide the precise position a hit should. For example, if a band records a tune today, but wants to release the record in Feb 2006... the forecasters can gauge what attributes to record this song to make it a mega hit in 2006 vs 2005. This technology already exists and has for a long time-- I used it several years ago in business school, it's only a matter of time before it is applied here.
What I am suprised is what they are not selling is the formula to achieve this success-- because they do have it given what they are saying about their model. So eventually, what you will do is plug some variables such as let's say beat and harmony and the rest of the song, minus the lyrics will write it self. It's probably a matter of time, who knows how long where almost anyone could have the capacity of writing a "hit" song on their laptop.
Then, the question begs-- will that still be the standard of a "hit" or will human prefrences evolve into something else? |
| kathryn |
Posted - 01/18/2005 : 17:38:24
I have never been so digusted.
I still believe in the excellent joy of the Frank |
| Homers_pet_monkey |
Posted - 01/18/2005 : 14:09:02
quote:
Originally posted by apl4eris
Pop will eat itself.
My guess is that the computer program is just doing what the execs have done forever, but smarter. Maybe it'll just speed the sickness along to its natural end.
Lon the Fisherman has wooden legs, but real feet.
This was my inititial reaction, but on further reading, there is no doubt that it is even worse. However, I don't think it will be record company's only way to judge a hit. To quote from the article:
"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. Certainly Mike Smith, 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."
Not that the A&R men from majors are much better than a scientific formula (or at all).
You can see how such crap as Norah Jones, Maroon 5, Robbie Williams, Anistasia etc could be judged by a scientific formular. Music with no soul can easily be judged by a machine with no soul (though it may prefer Kraftwerk itself).
As for the music scene Dean, well the mainstream scene is indeed in dire straits, has been for years, though is getting worse it would seem. In reaction to this however, I feel that the underground is growing in it's creativity. The indie/alternative scene is the strongest it has been during my lifetime in my opinion. I honestly believe that, even stronger, on a whole, than the late 80's/early 90's. I have never been so excited!
http://www.thefutureheads.co.uk/ |
| Cult_Of_Frank |
Posted - 01/18/2005 : 12:14:13
Consider it used in my latest project.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| apl4eris |
Posted - 01/18/2005 : 11:45:59
quote:
Originally posted by kathryn
Anybody heard of Clear Channel?
I still believe in the excellent joy of the Frank
AHHHH! Speak not the name of G-D! Creator of all things! My eyes my eyes!
heheh. yeah.
Oh, and thanks Dean. It was your idea really, I just mixed it together with someone else's great idea. Voila! Bundt cake!
Lon the Fisherman has wooden legs, but real feet. |
| kathryn |
Posted - 01/18/2005 : 11:20:42
Anybody heard of Clear Channel?
I still believe in the excellent joy of the Frank |
| Cult_Of_Frank |
Posted - 01/18/2005 : 11:13:57
"The reniassance will not be televised".
If that's not a line from something already, it should be and I will henceforth be using it.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| starmekitten |
Posted - 01/18/2005 : 09:39:32
The guardian is fairly respectable (despite it's terrible reputation for spelling and the like)
I hope this is a fleeting record company whim because if they chose this to rate all predictable hits music will stagnate, if it can only work on looking at the past then nothing new (in the best sense of the word new) will ever get released.
Christ this is depressing. Where's the damn pringles.
you
me
we used to be on fire |
| apl4eris |
Posted - 01/18/2005 : 09:39:14
quote:
Originally posted by Cult_Of_Frank
Yeah, I believe that this sort of thing will precipitate the rise of the next musical renaissance.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)"
Unfortunately, the renaissance will not be televised.
Lon the Fisherman has wooden legs, but real feet. |
| Skatealex1 |
Posted - 01/18/2005 : 09:31:59
AHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH
The Truth Is Out There |
| Cult_Of_Frank |
Posted - 01/18/2005 : 09:20:53
Yeah, I believe that this sort of thing will precipitate the rise of the next musical renaissance.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| apl4eris |
Posted - 01/18/2005 : 09:17:36
Pop will eat itself.
My guess is that the computer program is just doing what the execs have done forever, but smarter. Maybe it'll just speed the sickness along to its natural end.
Lon the Fisherman has wooden legs, but real feet. |
| Cult_Of_Frank |
Posted - 01/18/2005 : 08:44:51
I don't know much about this "Guardian" publication, but nothing like putting a positive spin on something that's so completely wrong that it's painful.
"Join the Cult of Frank 2.0 / And you'll be enlightened (free for 1.x members)" |
| KimStanleyRobinson |
Posted - 01/18/2005 : 08:44:42
Kill Pop Dead.
Neither snow nor rain nor gloom of night shall
stay these couriers from the swift completion
of their appointed rounds
|
| remig |
Posted - 01/18/2005 : 08:35:04
Very good idea. I can't understand why it hasn't been done before.
**************************************************
[ |
| Coldheartofstone |
Posted - 01/18/2005 : 08:18:12
repent. for the end is near.
Damn it feels good to be a gangsta |
|
|
