Slashdot Mirror
Using Fractals To Classify Music
Brian McLaughlin writes "A company is working on software that can classify music with fractals and make it easier to find the tunes you want on the Web. Apparently, one can detect the type of music (jazz, heavy-metal, in-between, etc.) by detecting fractal patterns in the music."." I'm looking forward to the day when my music can be indexed and crossreferenced every which way: artist, tempo, year, style, similiarity, heck I wanna know when the Beastie Boys sample The Beatles and be notified and give the option to follow up on the samples within the songs. Someday... I hope.
How can you laud this kind of insult to music? I am utterly insulted by the idea that you could reduce a great art form like music to little numbers and digits. So I suppose we can just forget about all the creativity and emotion that are infused into the works of a musician and classify it as something soulless and robotic like math?
Music may have scientific properties, but it is by no means simply a matter of equations and numbers! Music takes passion, emotion, and raw humanity to exist as such, not a series of bits and bytes! I suppose someone is going try to make a arbitrary music writing program based on this info , no? Well, if so, I'd just like to say that music is NOT math. Unlike math, which takes no feeling or creativity whatsoever (rather robotic computational ability, seeing as how our advanced graphing calculators could easily take the place of any well known mathematician), music requires soul and humanity... something which a computer can never create. A program would never compensate for the genius of Mozart or Bach. Leave it to dronelike programmers to try to rob another great art of its soul and wonder by reducing it to a series of computational processes.
Emerson Willowick: Thinker, Writer, Human Being.
ickyickyicky icky pi-tang woop grrlblrlllbburllllll....woop auuwwww ....mumble
When Metallica told Napster to ban 300K users, it was because of a filename which does not infringe on copyright.
Proof please? You need to provide proof to backup this outrageous claim. For starters, they did not prosecute users who were trading concert versions of the songs. If they just searched for keywords, how would they have weeded these out? Please provide proof as a documented source that they used keywords as a sole means of monitoring the users.
Along this line, you could also tell your player to play other songs with similar fractal signatures to the song you are currently listening to, if you want to hear MORE songs like it - or the exact opposite, play songs which have greatly different fractal signatures, if you want a greatly varying selection of music.
Same for most classical, country and pop.
Oh man. This post is documented proof of the failure of America's education system. Wow. Most classical fans can pinpoint the composer and piece (out of a repertoire which is about 100 times as big and diverse as pop/industrial/country/goth/punk/metal conglomerate) in seconds, because the music is so distinctive. The clueless masses just hear a bunch of violins and think it's all the same, because they are not properly educated to differentiate it. Pathetic.
OK, it seems that the sum total of all these posts (aside from the "music is my soul and not math" troll) is that what we all really want is our own personal soundtracks that we don't even want to have to play with. We just want to push a button or two and have the right music come out all the time...
I just gotta ask.... do we REALLY want this? I mean, in our house is one thing, I suppose (although what if you live other people who don't necessarily feel your mood?), but nothing ever stops at the house. Next thing people will want is for it to link to their car stereos, walkmen, etc... a situation which leads me to two consequences
1: Actual human contact will be really annoying. Both of you will have to shout over your respective soundtracks to actually communicate. Or, god forbid, turn them way down, or even off. Plus, imagine the irritation when the guy you nearly ran down honks at you, interrupting your favorite song!
2: It's possible that creativity will be stifled. How? Well, this seems like it would knock music radio way down the charts. After all, why listen to ads or songs you don't like? So that outlet for new music would be gone. Where would people hear new music, then? It would have to travel by word of mouth, and that could take forever...
Anyway, just my $.02. Is this a future that we want, or am I just dreaming? (Gawd, that sounds like one of the awful trolls from the ZDNet authors....)
"Fifty million Americans can't be wrong," said Rep. Billy Tauzin. Gore - 50,999,897 Bush - 50,456,002
Damn straight! I don't know how anyone could claim that all classical music is the same. It just goes to show you how low are society has sunk.
I am not an idiot. Please use my name to email me.
"That's right, I'm quoting myself."
-Upsilon
A fellow named Forte promoted a music classification system based on "tone vectors" during the late 70s and early 80s. While useful, in some people's view, for classifying atonal music, the sytem had an interesting side-effect.
All major modes and all minor modes were classified by the same vector. According to Forte, most western music was the same.
So apparently your judging rap, pop, country, classical, etc... from your limited contact with them via Radio? mp3.com? what...? All music has crap in it, but every style has some gems... a few quick examples Underground Hip Hop (anti pop consortium, mos def) Country music (johnny cash, bob dylan) Pop Music (talking heads/david byrne, Pizzicato 5) Classical (Steve Reich, Phillip Glass, Bartok) whatever... open your mind...
Merzbow
Damn, wish I hadn't posted now, so I could mod this guy up.
I was thinking the same thing.
If you can classify genre and style using fractals, why can't you reverse the process and make a fractal sequencer or drum/rhythm machine?
--The more you know, the less you know.
Mozart did this, actually. Well... not a program, since computers weren't invented yet, but still. What he designed was a set of algorithms -- a dice game -- that one could use to assemble compositions from thematic "primitives".
A number of people have since implemented it in software. I suspect Mozart would be a hacker if he were alive today.
DNA just wants to be free...
This isn't about the generation of music, but about the categorization of music by fractals. Anyway, modern music is more complicated than the simple scales.
Free BeOS, runs from a Linux partition
........but the Beasties did rip off a Beatles guitar lick for "Egg Raid On Mojo", one of their earliest punk songs. It's available on the original PollyWogStew EP, Some Old Bullsh*t, and the sounds of science compilation. One of my favourite Beastie tunes. I remember freaking out when one of my buddies played me the original Beatles tune......very similar, might as well have been sampled.
"Share your knowledge. It's a way to achieve immortality." -- Dalai Lama
I agree, CDDB is kinda neat, but I usually know what CD I'm putting in the drive, so it's not much of a help other than filling in the names of the tracks. On the other hand, if it were to provide information about guests on certain tracks or where samples (if any) were taken from I think it could be a good learning tool for people who are interested, and might help enlighten a few people who otherwise wouldn't really know what they're listening too. Often I hear songs where I recognize things like old BB King samples and what not. I just heard a teeny-pop song yesterday where the entire backing track throughout the whole song is from an old John Melloncamp tune but I'll bet a lot of the target audience won't have a clue what it really is until their parents (gasp!) say, hey that sounds just like...
This way Napster can really be a way of finding new artists, try searching for a symphonic rock band that doesn't sound like Metallica, for instance. Or female pop singers that doesn't sound like Brittney Spears.
This could also be a way to avoid misnamed files. Of course, this probably won't be possible until in a few years, when Napster has been sued into oblivion by the Evil Corporations(TM) anyway.
--
Pokéthulhu
Gotta catch you all!
While the idea itself sounds interesting, how accurate can this really be, given the complexity of music and the quantity of cross-genre stuff being put out? It all seems vaguely reminiscent of the Censorware skin-tone heuristic, if slightly more legit. The question is how long before Metallica, Dr. Dre, etc. will want to use this to screen their music out, or before I can get a napster client that screens out the "crap" genre.
And 'mid this tumult Kubla heard from far
Ancestral voices prophesying war!
What happens if you feed that program disimilar styles of music, say Metalica, Portishead, and Beatovens 9th?
Also, if I feed the same songs in again do I get the same song out the system a second time, or is it just the same song as the first time?
-- Superlame http://catpro.dragonfire.net/joshua/
According to http://www.samplespotter.com: The Beastie Boys sample five Beatles songs in the track "Sounds of Science". They are: Back in the USSR, Seargent Pepper's Lonely Hearts Club Band, Seargent Pepper's Lonely Hearts Club Band (reprise), The End, and When I'm 64.
wrighty.
Touching on the fingerprinting idea, this could be a great tool for setting up some kind of napster-like/micropayment system. Just before you're about to download from someone's computer, a fractal fingerprint (as described in the above post) can be taken of the file and compared to a central (but possibly mirrored) database of fingerprints. A match in the database would initiate a micropayment to take place. So instead of generating micropayments based upon filename (which could be fscked by calling a file Metallika instead of Metallica), you're doing it by the information actually contained in the file.
This assumes that the fingerprints would be unique for each song. To get around making matches, however, a clever fellow might add some noise to the end of the file which would prevent a match/micropayment from being made. To counter this, the artist or a representative of the artist would have to scour this napster-like system for such files and add the fingerprints of those files to the database.
Bill Clinton: Pimp we can believe in. - The Shirt!!!
I wonder what Fourier transforms of music would tell us. I know they are important in image recognition. Let's see:
Music is made up of notes. Notes have pitch (frequency), dynamics (amplitude), and tamber (noise?). Different notes are played at the same time, and so their equations add up. There is also tempo, so these equations are changing with time. A local approximation would easily be made by a Fourier series since the sound is repeating (if I play an `A' on a violin, it will have a continuous sound). This should transfer over fairly well to...oh never mind, let's just fft the whole thing and see what we get.
Sometimes I've believed as many as six impossible things before breakfast.
What happens if you feed that program disimilar styles of music, say Metalica, Portishead, and Beatovens 9th?
It fails to find any kind of meaningful consistency, the ATN's knowledge base becomes underpopulated, and the final product is utterly bland and devoid of content. (Wow, so that's how they compose new songs for Britney Spears records!)
By the way... Beatovens? That's a damned cool name for a band! I've got dibs on it!
Also, if I feed the same songs in again do I get the same song out the system a second time, or is it just the same song as the first time?
No, the generative part of the process is randomised, so you merely get a different song in the same style. Look at the example MIDIs in the EMI web pages; there are a handful of generated Nocturnes in there, IIRC, and they're all different.
To the editors: your English is as bad as your Perl. Please go back to grade school.
Coulnd't believe that race kept requesting the doctor to sing everything. With the rest of the opera singers out there, hes definately on a par with Vanilla Ice.
The ivory tower has never had to reach so h
The art of arranging sounds in time so as to produce a continuous, unified, and evocative composition, as through melody, harmony, rhythm, and timbre.
which dumbed down is manipulation of frequencies and amplitues (et al) so therefore computated labels can be generated.
This will also allow artists to break free from a single label because their various songs will advertantly or inadvertantly fit into their various genres. (as well as correctly label the new mtv shit band forcing them to realize they are in fact shit, manufactured by corporate bigheads looking to destroy the meaning of music: and NO N'Sync, you are NOT the next Beatles mislabled as a boy-band. The Beatles never wore silver, light reflecting, winsheild visors as clothing)
ZEN is a prime number in base-36
Stuff like CDDB could be built upon and used to store meta-inofrmation of this kind. Pretty cool if you ask me. XML will be the tool of choice.
...If you can generate music with fractals, why not classify it? The only question then is how to do smaller differentials - punk vs. ska vs. reggae, ambient vs. jungle vs. rotterdam... I know some people that take this stuff *WAAAAY* too far.
"I'm not even supposed to BE here today!"
Better yet, when a band is making an album of their songs, or a record company is putting together a `best of' type album, this analysis could help make sure compatable songs get put next to each other. For symphonies written in the classical era, there is a set pattern of key changes and such that keep a listener interested by providing new material without having completely contrasting musical ideas thus confusing the listener (like many modern symphonies). I'm sure this already happens in albums (I imagine fast songs are intersperced with slow songs for instance). Perhaps this would do a better job than actually having to think (like listening to MIDI...)
Sometimes I've believed as many as six impossible things before breakfast.
I'm sure that once this gets around, some artists are going to try for odd effects that sound like a mix of heavy-metal and classical or something.
--
Linux MAPI Server!
http://www.openone.com/software/MailOne/
(Exchange Migration HOWTO coming soon)
Of course, they could also use my technique. DL part of the music (~10 seconds worth) & listen to it; if it's what you're looking for, keep DLing. If it isn't, cancel it. They probably know what their recorded music sounds like, so they could listen to that little bit & identify the CD version; heck, if they vary their music, they may even be able to tell which CD it came from (like I can do for some of the music I listen to.
I can't say that I don't give a fuck. I've just run out of fuck to give.
I'm looking forward to the day when my music can be indexed and crossreferenced every which way: artist, tempo, year, style, similiarity, heck I wanna know when the Beastie Boys sample The Beatles and be notified
This is a little disturbing to me. Is it really necessary to reduce music to a series of mathematic calculations? Is that really what the aim is? Besides, after that, how far away are we from randomly generated songs (not midi) based on your preferences? That would totally ruin music as an art form, and stifle real creativity. I think this would increase the problem of people just sticking with what they know and not experiencing radically new types of music.
Of course, having hold of this kind of personal preference data is a record exec's dream, so I doubt this company would have any trouble getting funding. Imagine if you could record a song, instantly check it against the personal taste database of 10 million teenagers, and then adjust the song accordingly. What a nightmare.
- Scott
------
Scott Stevenson
Scott Stevenson
Tree House Ideas
This sounds like a technological urban legend to me.
Note that radio frequencies are in the MILLIONS of cycles per second, wheras acoustic frequencies are TENS to THOUSANDS. The resultant frequency modulations would be almost entirely imperceptible on the scale of the FM band, over many MHz. Indeed, the way modern radio systems encode and decode the signal is through the use of heterodyne techniques; the signal is essentially detected as interference "beats" against a standard frequency reference.
Best,
Bob
Science, like Nature, must also be tamed, with a view turned towards its preservation.
My youngest brother wrote a program to do this, in Z80 Assembler, including a very nicely coded Fast Fourier Transform. It ran on a Sinclair Spectrum, and the music was fed in via the tape interface. This was at least ten years ago. As I remember, Vanilla Fudge was really easy to detect...
The original Doctor Dark.
Somehow I doubt that one can distinguish the fractal differences between two totally different songs taht have similar bass hits... Beethoven's 5th symphony and any deftones song share a bss similarity...
How Jaded Are You?
I sense much NT in you.
NT leads to bluescreen,
bluescreen leads to downtime,
Such Classification could also be used to detect the type of music you want to hear on a mix. For example:
Let's say you make yourself a bunch of mix CDs and stick them into your 200-CD tray (it makes more sense to have an MP3 player, but hey...), and from those CDs you only want to hear techno, or only want classical because your parents are coming for dinner. The auto-detection functions allow for limitless possibilities for music playback.
Maybe this could also be used on TV to filter out stuff you don't want to see? Like a quick auto-seek for a channel that doesn't have a cxommercial running?!
OK, who also clicked on the 'Group Sex' item next to this article??...Only to find out it was to do with gene therapy.
:-)
Well I was dissapointed
No sharp objects, I'm a programmer!
You might find this bit off of #userfriendly funny in the context of pop music...
To within half a percent, pi seconds is a nanocentury. -- Tom Duff
I'd like to see this go even further where computers placed around your home can pick up on your mood, and play the appropriate background music. I can definitely see this happening in a few years... vulgrin the MAD
I sig, therefore I am.
If it walks like a duck, and quacks like a duck...
QED
John
You've never listened closely to Bill Evans, then. He played (jazz piano) in a manner that would be nearly impossible even to get on sheet music, let alone reproduce from the sheet music.
Transcribe a solo by one of the great jazz masters. Doesn't matter who. Bill Evans, Monk, Oscar Peterson, Dizzy Gillespie, Coltrane, Dexter Gordon, Sonny Rollins, Sonny Stitt. Doesn't matter. Now feed it into your nearest MIDI program. Play it alongside the original. Gee, doesn't sound so good now, does it? And that's not just because it's not on a real instrument. It's because it's not played by a real musician.
Chess is, by its nature, not a creative act. It's a logic game with a well-defined objective. What's the objective of music? What are the rules?
"The first tuner to use an oscilloscope for display of information was a tube model, the Marantz Model Ten. Beautiful device, tubes. The designer was Dick Sequerra. Later, he started his own firm, his tuners branded under his last name. They displayed the whole spectrum and were popular with radio stations. They are still being made by another company under the same name. Most expensive model about $10k."
I think this is a photo of it, but I'm not sure. Still looking.
Mixing heavy metal and classical isn't really odd. Yngvie Malmsteen put the mainstream spotlight on it for a while in the 80s, and there was also a big revival of neo-classic metal in the late 90s. Happy Helloween-style power metal fused seamlessly with classical on albums like Rhapsody's "Legendary Tales", and darker heavier more traditional metal (think 80s Metallica or Megadeth) combined very well with classical on Rage's "XIII". Then there's the weirder stuff like Therion or Nightwish who have fused metal with opera, or even middle-eastern folk music. I'm just listing the more popular stuff; this is just the tip of the iceberg.
It has even become so common and popular that some diehards are starting to think of it as being "trendy" so there's some backlash against it now. This only got worse when the mainstream alterna-pop band formerly known as Metallica attempted (poorly) to jump on the bandwagon and follow the trend with their S&M album. (Fortunately they didn't know what they were doing so the damage of the movement's credibility was minimal.)
But anyway, metal and classical go very well together. Some people way Wagner (the "Flight of the Valkyries" guy) was a headbanger at heart. ;-)
---
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
I dont really think that you can make a judgement on an education system based on music education. personally I dont really think that music education is all that important, maybe not in public education anyway, classical music doesn't interest me and anything that I might have been tought in high school I would have forgotten the by now. Music is something that should be left for ones own to figure out...
I do not really understand why I should learn to be able to differentiate between composers and pieces...
How is it really going to help me?
"Alcohol, cause of, and solution to, all of life's problems" -Homer Simpson
Decibels are ratios between two levels, such as the amplitude of sound waves. Here are some relevant links and some excerpts I found using Google. The first explains the meaning in electronics, and the second is more about sound: The decibel, or dB, is a means of expressing the gain of an active device (such as an amplifier) or the loss in a passive device (such as an attenuator or length of cable). It is simply the ratio of output to input expressed in logarithmic form The decibel (abbreviated as dB, and also as db and DB) is a common unit of measurement for the relative loudness of a sound or, in electronics, for the relative difference between two power levels. A decibel is one-tenth of a "Bel", a seldom-used unit named for Alexander Graham Bell, inventor of the telephone. In sound, the difference between two sound levels is ten times the common logarithm of the ratio of their power levels. In sound, decibels measure a scale from the threshold of human hearing, 0 dB, upward towards the threshold of pain, about 120-140 dB. As examples: the sound level in the average residential home is about 40 dB, average conversation is about 60 dB, typical home music listening levels are about 85 dB, a loud rock band about 110 dB, and a jet engine close up is 150dB.
It's based on a book published by G Spencer Brown, the mathematical logician (Laws of Form).
It's not quite the same, but the Ultimate Band List won a Webby award for music and has long been accepted as the One True Oracle for music information. Like IMDB (owned by Amazon) it's now more commercial, with "buy this!" links littered all over the place, but it still has decent information.
For more information, click here.
If you can classify music with fractals, and you can generate music with fractals...
:)
Could you fuse categories of music as well?
That is, if you can detect the unique patterns of, say, hip-hop, or classical music, could you feed that back into a program and get some really funky classical music?
This is all pure speculation on my part, mind you. I'd love to help program something like this, but I wouldn't know where to start. I know something about fractals, but very little about music.
(or at least I'm not any good--whatever program I came up with would compose better than I would!)
---
pb Reply or e-mail; don't vaguely moderate.
pb Reply or e-mail; don't vaguely moderate.
Couldn't the reverse, then be done, to take a fractal "fingerprint" of a type of music (say, jazz), add some variables and come up with original music?
It's 10 PM. Do you know if you're un-American?
Like so many announcements, this one is short on details. But music has lots of interesting features which suggest that fractal analysis is a useful start.
Anyone who has browsed through the various Fractal books which actually give you some of the maths, such as the Science of Fractal Images (pub Springer-Verlag) will have noticed the revelation that almost all music has a 1/f^(1-\beta) power spectrum, which is the what fractal approximations to Fractal Brownian Motion tend to head for.
While fractals are supposed to have self similar detail at all levels, and music, digitised or otherwise clearly cannot have 'detail' at all levels for physical or sampling constraint reasons, this doesn't necessarily invalidate the analysis either. The question therefore is what sorts of characteristics are they using as musical indicators. Distinguishing classical from pop is relatively easy even without fractal analysis - the frequency range visited by classical music can be several octaves greater given some reasonable threshold value. The value of \beta may give some insight between styles - estimates for \beta can be as simple as 'distance' travelled by the actual line divided by time, with appropriate normalisation. Anyone care to suggest others? No reason why we shouldn't try and get something working for say CDDB as someone suggested.
Cheers,
Toby Haynes
Anything I post is strictly my own thoughts and doesn't necessarily have anything to do with the opinions of IBM.
Flamebait?
:)
I'd like to see someone "generate" something like old Neil Young, Violent Femmes, Mark Knopfler, Junior Wells, etc.
On the other hand, I can see this as an accurate description of MIDI.
As a researcher in pattern recognition who also manages a band, this topic holds particular interest for me.
I haven't read the article but it would surprise me if this method was more effective than a frequency/power spectrum (the distribution of sound energy over all frequencies) or even a basic neural net classifier (both mentioned by previous commentors) at stylistic classification of music. Fractal dimension reduces the whole waveform to a single number; a frequency/power spectrum contains a lot more information. (For the fractally challenged: a straight line has a dimension of 1, and a solid plane a dimension of 2; a music waveform has some fractional dimension between 1 and 2... it's roughly a measure of the regular "squiggliness" of the waveform. Fractal dimension is not necessarily a measure of self similarity as is implied by the news brief; it's just that the self similar patterns that we popularly call "fractals" have an interesting fractal dimension, like 2 2/3 or something.)
I think music recognition technology is the key to resolving the conflict between artists who want to make money off their recordings and fans who want to sample a wide variety. It's a tough business folks; Metallica doesn't deserve much sympathy but most bands are extremely exploited by record companies and deserve to make as much money as possible off their art. Someday releasing a record will also entail releasing a host of net-bots that look for unauthorized, publicly available copies of the music.
Stylistic classification is not that hard. Much harder is reliably recognizing a particular piece of music (i.e. creating a bot that scours the net, looking for copies of "Master of Puppets"). It's easy to fool a frequency power spectrum classifier, for example, by tacking on some tones to the end of the track, or reequalizing the track, or adding some low frequency inaudible noise.
This is where AI steps in. The biggest feather in the cap of AI is the technology used in 95% of all speech recognition systems: Hidden Markov Models (they are probabilistic versions of deterministic finite state automata, for those geeks out there who have been subjected to the torture of a class in computer science theory). The same technology can be used to identify pieces of music.
Let your bootay take your mind for a ride.
eek. Ethical dilemma there for a moment. Posted that AC from work, logged in at home and I had mod points. Still, by replying to it I can't mod now.
"I Know You Are But What Am I?"
Those would indeed be very useful, but they're Hard to measure.
The use of not just snippets but large sections of classic songs to be built on is pretty common in hip hop. When it's coming from a major label there is always a release that's been signed and most likely money exchanged.
The Beasties frequently use many little samples from many sources, samples which are too short to get a release for, even if it's readily recognizable to a fan. I could be wrong, they might get releases for even the little ones these days.
Yes, but so what? Even good search engines are bad, but they're still much better than nothing.
Sorry, can't resist:
:)
Were your examples of 'crap' or 'gems'
Eeep!
-~ ~- -~ ~-
__
Arse
I recall seeing on UK television a few years ago a gentleman who could identify the work (and sometimes the actual recording) just by looking a the grooves on the vinyl LP. The presenter handed him a stack of LPs with the label and matrix numbers covered with a sticker, and this man correctly identified every one.
Nic Endo
When he finished, he realized that the comments were much, much longer than the code they attempted to describe.
;) Seriously, even if I expand the above formula to its textual correspondent, it'd still be much shorter than it could be expressed in any algorithmic language, because these are languages for computation, not for mathematical abstraction.
;)
(Oddly enough, I just had a similar discussion in DALNet #perl. I'll be a good programmer, then, and practice code (example) reuse.)
I remember that post on PM too; I disprove it thus.
"This is left as an exercise to the reader": write a Perl module Math::MB, such that, after
use Math::MB;
tie($m, 'Math::MB');
$t contains the Mandelbrot set. The length of Math::MB must be strictly smaller than the following description of the Mandelbrot set:
Definition. Let Z_1_(c) = 1, Z_n_(c) = Z_n-1_(c)^2 + c; then M = { c e |C | lim_n->oo_ Z_n_(c) * oo }.
(_foo_ denotates a subscript; oo denotates infinity.)
(Thus it is proved that, however concise Perl may be, mathematics is even more so.
My point is that the same thing applies to poetry. It shouldn't be described in terms of the pure textual size of its written form, but in terms of the "size" of the symbolic structure that the reader gathers from reading it. Perl can represent, e.g., pattern-matching, array looping and I/O, concisely because that's all that a Perl program does; there's no additional level of significance to the "text" that is Perl code, so the issue is merely one of Perl syntax vs. English syntax. However, ideas that are easily expressed in a "real" language like English, to a human, such as the concept of limits, the concept of a set, and the concept of a logic variable, have no reasonable equivalent in Perl programming.
Thus, Perl may be beautiful, but it's no poetry.
To the editors: your English is as bad as your Perl. Please go back to grade school.
Thanks for the link! I have a copy of Oersted, but that's the only recording of his I could get hold of.
So does this mean that soon we will be able to browse a library of songs, and pick one based on what it looks like? I wonder if the faces of songs will be like the faces of girls, in that no matter how nice she looks, you still never know what you're getting yourself into.... mbc
Uuuuuuuurgh. Stupid Slashdot and its lack of Unicode support. Where it says lim_n->oo_ Z_n_(c) * oo, it's not *, but a =/= character.
To the editors: your English is as bad as your Perl. Please go back to grade school.
From what I gather from the article, I don't see
how this is very new. Looks like most of this
was done in some degree 20 years ago.
But, past that, I don't believe that fractal
analysis is enough to do that good of a job at
discriminating between different types of music.
You really have to move to multifractals if you
want to do that type of classification properly.
Fractals by themselves don't pay enough attention
to finer details and two pieces of music (I think
someone mention Beethoven's 5th and another
piece) could give very similar fractal results
even though they are very different types of
music. This is because the similar dominant
structures in both pieces of music will give
nearly identical fractal dimensions. Hence,
using multifractals is much better suited.
Actually, I would move towards using relative
multifractals, as introduced in my PhD thesis,
since this will give another level of being
able to compare two pieces of music to check
their similarities.
I thought your sig said Sheep A completely inadequate substitute for caffeine. Need more coffee.
Sig it.
In the mid-1970's, an even more general mathematical study of music was performed by Richard F. Voss and John Clarke at the University of California. This time, rather than studying the structure of the music as it is written, the researchers decided to study the actual audio physical sound of the music as it is played. This was accomplished by analyzing the audio signal which, in a stereo system, would correspond to the voltage used to drive the speakers. The signal was fed through a PDP-11 computer, which then measured a quality called the spectral density.
Spectral density is often used in the analysis of random signals or noise, and is a useful characterization of the average behavior of any quantity varying in time. In technical terms, the spectral density Sv of a quantity V(t) fluctuating with time t is a measure of the squared variation V^2 in a unit bandwidth centered on the frequency f. The average is usually taken over at least 30 periods. Another quality, called the autocorrelation function, measures how the fluctuations in the signal are related to previous fluctuations.
The concepts of spectral density and autocorrelation are a bit difficult to grasp mathematically, but can be understood intuitively; Benoit Mandelbrot explains them in the following manner. If one takes a tape recorder and records a sound, then plays it faster or slower than normal, the character of the sound often changes considerably. Some sounds, however, will sound exactly the same as before if they are played at a different speed; one only has to adjust the volume to make it sound the same. These sounds are called "scaling sounds."
M$: "We're #2!"
Actually, this could be used to shoot down the popular "filename says sandman, but is not metallica" arguments. When Metallica told Napster to ban 300K users, it was because of a filename which does not infringe on copyright. Now a band can say, "Hey, not only does it have a suspicious filename, but it follows the pattern of our hit song exactly.
This is cool technology though...maybe someday we will be able to prove for certain that Vanilla Ice did use David Bowie and Queen's 'Under Pressure' in 'Ice Ice Baby'. Hmmm
They've changed their name to Gracenote. This is mainly just a way to relaunch their brand since they now work on more than CD's - hence the old name is too restrictive...
why cant we just classify music as waht we like and don't?? and how does this effect musicians?? we'll get more sampling and stupid remixing. i think this just might hamper creativity. also, the record industry will (again) make a killing through popular fractals and shoving us with more N'sync crap. (actually intended for preteens!)
It's actually not that difficult. The algorithim (that I know) is a fairly straightforward neural network. I took an Intro to AI class while I was in college - had a friend who's final project was a system that could determine the type of music on a CD that was currently in his CDROM drive.
He trained it first, with 2 CDs from each genre from his collection. He then went through and had the system analyze and 'guess' the type of music. From his collection of ~100 CDs, it correctly identified the different types about 95% of the time.
Now, I don't know the constraints that these folks are putting on their software. But if Erik could code up a working model for a 200 level AI class, I'd hope that this company can handle details.
JJ
What is WITH all this crap? Don't these people have an IRC channel they can go be annoying in or something? I mean, we're trying to have an intelligent discussion about HOT GRITS here...Christ people...what would Natalie Portman say anyway?
ASCII art of naked men, the personal 800 numbers of your ex-girlfriends, Stallman quotes, lead-nowhere viagra ads...go play in the road, kiddies.
If it ain't about crappy southern U.S. traditional food, tight-assed young actresses with cheekbones that wrap around the back of their heads, pictures of stretched assholes, or Columbus-ian (not to be confused with "post-Columbine") First Post declarations, then shut the hell up and go DDOS Hotmail or something (now that they made it easier for you).
Leave the joke posts to the adults. After all, Slashdot has proven that we can be amused by *ANYTHING* after sixteen straight hours of coding with no external sensory inputs except the taste of that last flat, warm mouthful of Jolt cola left at the bottom of the bottle.
"Sweet creeping zombie Jesus!"
-The Professor, Futurama
I think, this will work kind of like recognizing handwriting. You have to train it, until it recognizes the music you probably like the most.
--- If OS were buildings, then the first woodpecker to come around would erase 95 % of civilization.
My favourite music is Einstuerzende Neubauten, and anything else just isn't noise.
Any music which you are not familiar with will sound "all the same" until you are familiar with it. People have said that about jazz, pop, classical, heavy metal, techno, hip hop, punk - anything in existence. If you think any genre "sounds all the same", I submit that you are not familiar enough with it to be able to understand what the different artists are trying to achieve. I would say that you need to be familiar with at least 100 recordings of a genre, and have read several books about it, before you are qualified to even begin considering judging it.
...) are no different.
Something like country is tremendously diverse, and is also one of the oldest recorded musics. Few music lovers don't love older country to begin with, and when you add things like alt.country and bluegrass and contry-folk (each of which have a bunch of different sub-genres), you have a tremedously respectable music, and inarguarbly one of American's two or three finest traditions.
Of course, if all you've heard is Shania Twain and whatever else they play on the radio, you've missed out. Like any genre, the best country music is not played on the radio. Judging country music by Garth Brooks makes about as much sense as judging jazz by hearing only Kenny G, metal by only Bon Jovi, rap by only Snoop Dogg, and classical only by Charlotte Church. For any genre you need to dig deeper than the tunes played on the radio, and country (and hip-hop, and jazz, and
Based on what the article says, I'd expect Torn and Eno to be lumped in with Yanni and Tesh. The "amplitude fractals"--or whatever they're calling them--would be about the same.
But, if they combined the amplitude analysis with something that could determine harmonic relationships between simultaneously occurring tones, they might spot the difference (Eno and Torn being "uglier" to most people's ears, because they use more complex, close-on-the-scale voicings, generally). But it still wouldn't know the difference between the new Deftones album and the second Sunny Day Real Estate record, based on that.
So, if you can hear the difference between, say, John Fahey and Roy Clark, something like this would be useless to you. Probably a near-"true AI" problem, if they were bothering to get it right (like, identifying the guys in Birdsongs as members of Mission of Burma based on their styles). Which they aren't. They're just whoring for VCs by using obfuscatory tech-talk to hide the uselessness of their allegedly existing product.
Your mouth is like Columbus Day.
I was skeptical but it actually works quite well. Even better, they're an open source shop through and through: Apache, mod_perl, mysql, etc.
Advertisers, psychologists, neurologists, and pharmacists have all learned ways to manipulate the brain in very mechanical ways, getting very machine-line responses.
It's romantic to think we each have a "soul" and I wish I could believe it. But as science progresses, the concept of the soul starts to look more an more like just another archaic model for explaining processes that we used to not understand.
Music is going to be demystified some day, and the torch will be passed from the artists who do it intuitively, to engineers who do it very consciously. Then they will write computer programs to generate it and machines that are made out of meat will listen to it and smile predictably.
Sometimes I hope that by the time it happens, I will be dust. It seems as if understanding humans will dehumanize them. In a few hundred years, whenever someone mentions the old terms "dignity" or "free will", people will chuckle and say "those are relics of an outmoded belief system."
---
As copyright owner of this comment, I authorize everyone to defeat any technological measure which limits access to it.
To be completely honest, all music (in theory) can be reduced down to some sort of mathematical expression, but the expression of the artist cant be grasped by numbers and equations. Sometimes it seems like this is a valid argument against any recorded music at all. The source of the music on a cd or an mp3 file is mathematics, and although reproductions of the performance can be made, it will never rival the real thing. Im the magical man, from happy land, in a gumdrop house on lollipop lane.
I await the results of the catagorisations where it is proven that Bon Jovi is FALSE METAL :-) Muahahahah!
FatPhil
Also FatPhil on SoylentNews, id 863
Computer, take away two of the wrong answers, leaving only one wrong answer and the correct answer.
For more information, click here.
I had a hell of a time creating a database for my pornography collection. It had grown far beyond using Perl to scan a flat file full of descriptions to build a list of matching images, and the taxonomy started getting hairy enough to justify a normalized database full of nouns and verbs describing who was doing what to whom, but it started getting exponentially sticky when classifying "group" photos where there was a whole lot of shaking going on in the foreground and background both. When Oracle finally shipped their RDBMS on Linux I was thrilled but after spending countless hours installing it, importing all the BLOBs, building my lookup tables and description/narration/commentary tables and writing a batch thumbnailer in Perl and putting together a fairly comprehensive front end in Python, I realized that a fairly straightforward project had deteriorated into, well, wanking.
So my question is, can the type of fractal analysis being applied to identify and classify music be used to classify other types of data to the point of doing useful fuzzy matching for the purpose of identifying thematically related JPEGs?
Also, I think it would be really cool if you were listening to a song and decided you really liked it and could just instruct some sort of fractal music search agent that "hey, I really like this song. Could you find me some more songs like it?" and it would go find them for you. You could make a really kickass DJ out of such an agent by having it transition from song to song based on thematic similarities between them.
--
This is not my sandwich.
it definately won't be able to recognize good music over bad. But a (broad) categorization should be possible:
- rock: includes punk, hardrock, speedmetal
- techno: includes trance, gabber
etc.
Obviously a lot of people are going to be unhappy, getting 'their' music lumped up in 1 category. But it could still be a useful tool.
//rdj
No one can understand the truth until he drinks of coffee's frothy goodness.
--Sheikh Abd-Al-Kadir, 1587
Your favorite type of music is the only real music around, and everything else is just noise.
luckman
luckman
I don't involve myself with flames, much less know how to bait one.
Sure you can. You can define something as intensely personal as feelings through somethign as crude and impersonal as words. They'll be able to write an algorithm that will contain what's different about X piece of music from Y piece of music. Do that for a while, and do it well, and you'll have a lot of useful and interesting data to correlate.
You can reduce a piece of music to a generic set of characteristics by writing it out in SHEET MUSIC. It isn't that hard. I doubt that an algorithm would always categorize things the same way as you would, but I bet it could still do a good job, or come up with some insights.
For any further dissenters: the "humans are intrinsically superior because we are human" crowd said the same thing about chess. Where are they now? Oh, they just jumped to a new topic.
Jeez. If you're not going to contribute, but just want to sit on the sidelines and talk about how people shouldn't be able to do WHAT THEY ARE DOING, shut the hell up and go somewhere else.
---
pb Reply or e-mail; don't vaguely moderate.
pb Reply or e-mail; don't vaguely moderate.
You know I'd say your right :-) I always think about this stuff simply by thinking of dynamic range and the fact that everything goes from -100 to 0db (CD-audio if I recollect correctly) is a bit silly to me.
Never underestimate the dark side of the Source
Congratulations! You've just managed to insult half the /. readership in one post!
BTW, as someone experienced in both mahtematics and programming, I'd just like to say you are full to overflowing with bullsh*t. Both mathematics and programming have a great deal of room for creativity, and most of the folks I know [being geeks;)] would find a good deal of beauty in elegantly written code, and a succinct mathematical proof. So I'm affraid I must take exception to your classification of math and computer science as 'soulless'.
-={(Astynax)}=-
-={(Astynax)}=-
"Darkness beyond Twilight"
i suppose that rhythm would carry more weight than harmony in that kind of analysis... like straight ahead jazz can be recognized by swing eith notes, whereas fusion wouldn't swing but would still be modal. or, what is the difference between a three chord ac/dc and alot of the punk stuff... probably tempo and tightness. interesting to ponder....
Go French researchers ;-)
Well, this is nice, but what would be really needed (what I really want, anyway) is a search engine where you would be able to say "electronic music" and ( "like Kevin Saunderson" and "unlike Derrick May" ) or ( "almost like ken ishii" ). This would allow for discovering new fish in the huge digital sea of music, that I will probably like, if my current kind of music is this or that.
This would take more than fractal search tho :O
I think you're afraid that this might work, that science might invade the realm of art. What you don't realise is that science and art are two ways of expressing the same truth.
If a mathematical mechanism can produce art, it doesn't mean that art is fundamentally ugly. It means that mathematics is fundamentally beautiful.
----
After having spent countless hours arguing over genres and classifications, I've come to the conclusion that if no two human beings can aggree to what genre certain artists belong to, how is one guy making a program going to be able to make a definitive judgement?
It's all subjective.
As a (pointless) note, the Beastie Boys sample the Beatles 'The End' off Abbey Road in 'The Sounds Of Science' off Pauls Boutique which was produced by the Dust Brothers, who coincidentally, also made the soundtrack to Fight Club, which starred Brad Pitt, who starred in Sleapers with... Kevin Bacon!
Using fractals to find simalarities in music should allow us to prove that there is only one rap song and that it is just being re-recorded by everyone with a microphone. Same for most classical, country and pop.
I'm looking forward to the day when my music can be indexed and crossreferenced every which way: artist, tempo, year, style, similiarity, heck I wanna know when the Beastie Boys sample The Beatles and be notified and give the option to follow up on the samples within the songs. Someday... I hope.
As much as all of you hate watermarking, stuff like this is really what's it's MADE for. The same watermark being used by SDMI right now is actually more concerned with track id and related info than copy control. Pervasive use of watermarking on the production side of things would essentially put id3 tags in all music =)
The plan is even to have a system in place such that data about the song that you JUST HEARD on the radio will be available to you near-instantly, without you having to have a decoder. It's neat stuff =)
Whether the potential to cause sound quality problems with this outweights the benefits is another discussion altogether.
Enlgish Link here
German site
I recommend Verehrt und Angespien to anyone who appeciates the musical site of metal.
Isnt this a reverse version of the Metasynth program with the focus on amplitude only? Im curious.
I recall there being a high-end, all-analog radio tuner that used a special wide-screen, green phospor, cathode-ray tube to display the entire FM radio spectrum at once. The nice part is, it allowed you to tune to the center of what was being broadcast. (Those big transmitters did drift.) And it totally fit with the analog-only mindset of being forced to listen to a digitally/decimally perfect frequency.
The long-time users of those systems said they could tell what type of music the station was playing by the frequency distribution, and frequency energies being used. Some said, for their favorite station, they could even tell what period of music was being played, or if it was one of their favorite composers.
wouldn't this get confusing when say a hip-hop song samples a beatles song over and over? Wouldn't it just think that it was a rock song? Or what about rock songs that have classical sounding intros? Is this really possible?
-thinkpol
If you've seen interviews with many artists, you've probably noticed how most of them hate to be classified. If this really works, it would kill a lot of pretension. I can see it now:
Reporter: Despite the fact that you're considered a rock artist, you seem to be having a great deal of success amongst the country and even R+B fans. Why do you think that is?
Artist: Well I don't really think of myself as a rcok musician. People are always trying to classify my music as pop, or hard rock, or soft rock, or whatever. But I don't restrict myself to those terms, I just think of myself as an artist, and I think my work really defies being simply classified as rock.
[Reporter looks down at a laptop, hits a few keys]
Reporter: No, the computer says it's clearly rock music. Not country, not big-band, not funk, not innovative-genre-transcending-art, just rock music.
Artist: Well, yes, but it's really-
Reporter: That's all the time we have for now. Tune in tomorrow as I interview another popular rock band.
luckman
luckman
I don't involve myself with flames, much less know how to bait one.
Would be using this software to analyse what I currently listen to when i'm doing certain tasks on my PC. Then it could download/compose/stream/remix music on the fly to suit my tastes all day long.
:)
No longer would I sit at napster wondering which (unsigned) artist I should download today
The mathematical study of music is certainly nothing new, dating back to ancient Greece. Around the 5th century BC, the Pythagoreans formulated a scientific approach to music, expressing musical intervals as numeric proportions. This was probably done by observing the tones produced by plucked strings of different lengths; for example, the tone produced by a string held at the middle is an octave higher than that of the whole string. They went on to calculate the intervals for several different scales, including the chromatic and diatonic scales. Archytas of Tarentum, a Pythagorean mathematician who lived around 400-350 BC, was even able to work out the relationships between notes in the enharmonic scale, which includes quarter tones.
M$: "We're #2!"
I hope it's better than the BAIR system for recognising naughty pictures (http://slashdot.org/article.pl?sid=00/07/21/1516
</skeptical>
Mike.
Tales from behind the Lagom Curtain
That is the shortest story I think I have ever seen on slashdot!
I can't myself see how much detail can be garnered from the amplitude alone of the notes in a musical piece. I can see how heavy metal and jazz would be quite different, but how about jazz and drum'n'bass, they are incredibly similar forms that would be distiguishable by the underlying beat rythms (or perhaps more likely through the persistance of instruments). Would a fractal based on note amplitude grab this? I can imagine it might, but if you threw it the whole gamut of dance music (acid, trance, acid-trance, garage, girly garage, ambient, techno.....need I continue) I am sure it would fall apart as the large scale use of compression alone would bring these musical forms incredibly close together in terms of amplitude (if everything is at 100db post-compression as often happens with dance music).
Another useful bow in the arrow of anyone interested in categorising music, but I feel that a full quiver of tools is always going to be needed to even come close to trying to do this job.
Never underestimate the dark side of the Source
This could create one hell of a visualization plugin for Winamp...
Sleep: A completely inadequate substitute for caffeine.
detected porn by skin tones.
Oh, wait a minute. That didn't actually work.
http://www.angelfire.com/ca3/marlowe Better a smartass than a dumbass.
There is a strong correlation between average spectral usage and genre, particularly between genres such as classical (which looks fairly symmetric, as a good symphony uses the whole spectral range) and more beat/vocal heavy types such as electronic, which are dominated by low frequencies. For song level identification, however, you need to include additonal features, such as sonic energy, which gives a unique (across my test sets at least) fingerprint of music. But, based on those sonic signatures you can realise that track1.mp3 is really Metallica's Unforgiven (which is useful if you didn't know that it was ;).
I love the smell of vaporware in the morning...
Things you think are in the Constitution, but are not.
you may find similar stylistic soundings, but
this relies on gross differences rather than
differentiation based on subtlety. each order
of subtlety takes an order of magnitude more
genius, so to get 80% of the way there is easy,
but to get to that last 20% is the hardest part.
query -- what programmer here would say that the code produced by a 'code generator' has anywhere near the elegance of human hand-tweaked code? a code generator or a chopin-style emulator can hitch onto the 'sequence of pattern runs' that give a style a distinctive flourish (just like tokenizing byte runs in LWZ compression), but if you compare intelligently written code with the output from a code generator, or music created and sequenced in a particular order by a human as a result of their experiences of life emotion, it is clear that there is art in programming just as there is in music.
"Perfection (in design) is achieved
not when there is nothing more to add,
but rather when there is nothing more
to take away." (Antoine de Saint-Exupery)
regards,
john.
http://home.earthlink.net/~johnrpenner
Perhaps by "follow up", he means to check out the original song? I listen to a lot of Industrial and would often like to know where the samples came from.
heck I wanna know when the Beastie Boys sample The Beatles and be notified and give the option to follow up on the samples within the songs.
As someone who routinely beats samples into a whir of unrecognizable sound, and would prefer not to pay any "sample clearance fees" whenver I sample anything. You want a rights issue, TacoBoy? You are NOT free to sample anything you want to. Maybe you might want to read what negativland has to say about Intellectual Property.
Bad things often happen to good people,
It is up to them to see that they remain good.
http://slashdot.org/comments.pl?sid=00%2F08%2F0
you may find similar stylistic soundings, but
this relies on gross differences rather than
differentiation based on subtlety. each order
of subtlety takes an order of magnitude more
genius, so to get 80% of the way there is easy,
but to get to that last 20% is the hardest part.
query -- what programmer here would say that the code produced by a 'code generator' has anywhere near the elegance of human hand-tweaked code? a code generator or a chopin-style emulator can hitch onto the 'sequence of pattern runs' that give a style a distinctive flourish (just like tokenizing byte runs in LWZ compression), but if you compare intelligently written code with the output from a code generator, or music created and sequenced in a particular order by a human as a result of their experiences of life emotion, it is clear that there is art in programming just as there is in music.
"Perfection (in design) is achieved
not when there is nothing more to add,
but rather when there is nothing more
to take away." (Antoine de Saint-Exupery)
regards,
john.
http://home.earthlink.net/~johnrpenner
They examine the amplitude of the songs to determine the "type" of the music. That can work for music with big differences, like jazz and heavy-metal, but to distinguish between different types of rock is near impossible right now. Songs that don't fit into the genre are probably not easy to identify either. I'm surprised that it's taken scientists so long to even look at the amplitude..that's always been a quick way to learn things about a song from it's waveform.
nWo 4 Life
I'm currently listening to "Pulse Piece", by Birdsongs of the Mesozoic. Layers of distorted piano, organ, and percussion, with a pulse-like beat. I wonder what this clever technology would make of that? Rock? Jazz? Techno? (It predates techno by a good ten years)
Hell, i wonder what it would make of half the stuff i have ripped to mp3 here at work... Steve Tibbetts, David Torn, Erik Satie, Brian Eno, Jean-Michel Jarre, Klezmatics, Last Exit, Nordic stuff, Sonic Youth, etc...
--
Hand me that airplane glue and I'll tell you another story.
Amplitude is the only signal sent to any analog speaker. Recorded music (wav, mp3, anything with a live waveform that has been recorded) only stores the amplitude of the wave at each point depending on the sampling frequency. That's why something recorded at 44.1KHz (CD quality) sounds so much better than something recorded at 8000 Hz (analog phone line quality). Because you have a better resolution on the wave.
You can't tell a speaker "play this note for this long." You generate the note by modulating the amplitude of the speaker cone's vibration. Frequency is not included in the data - it is only a byproduct (technically speaking, anyway).
In post-9/11 America, the CIA interrogates YOU!
Wouldn't it be nice if Slashdot could use this technology to eliminate the overload of spam and trolls? If it can work for music, it can work for spam. Just my 2 cents as an honest AC. [Don't blame ACs for spam, now the fashion is for spammers to take a nom-de-fume -- I won't dignify them by mentioning their names.]
Surely you can't define something as intensely personal as music through something as crude and impersonal as a mathematical algorithm? I'm all for the advancement of science, but I can't see that they're ever be able to write an algorithm that was capture the "essence" of a good piece of music, which is essentially what they're talking about.
By reducing a piece of music to a generic set of characteristics they are going to miss out on all of the subtleties that define music. There are genres of music where I can tell the difference when I'm listening to it, but I'd be hard pushed to define those differences. No algorithm is going to be able to do the same, whether it uses fractals or topology or whatever.
See Cantametrix for a company building tools to search music based on sound models.