Using Computers for Sophisticated Music Analysis

Tom Avril writes "Need an accompaniment for your melody? Seeking a virtual dancer to try out your new choreography? Or perhaps you're making a new TV commercial, and you need a snippet of music that sounds something like Radiohead, but a bit more mellow. Increasingly, sophisticated software can help with these sorts of tasks. We got a look at the latest from the nascent field of Music Information Retrieval, after its conference in Philadelphia: 'A key part of the conference each year is the announcement of results from a sort of software shoot-out — a competition in which various universities pit their music-analysis algorithms against one another. Entrants from more than a dozen countries competed in 18 tasks, using their computers to "listen" to selections of music, then identify such things as the genre, mood, composer or title. The eventual goal: to help people search for music they might like by combing through millions of audio files in a database. ... In another task, the computer had to identify tunes that someone hummed. "The idea is, you go into the karaoke bar and start humming, and the computer retrieves your song," Downie said.'"

Comments

Results

[Anonymous Coward]

Artist: Britney Spears
Song: Hit Me Baby
Rating: Shit
Conclusion: Humans are weak and stupid

Action Plan: Terminate Britney Spears

Re:Results

[carlmenezes]

Input from programmer :
>>action plan invalid --reason="cannot terminate artist"
>>new action plan

Action Plan 2: Self Terminate

Re:Results

[stewbacca]

So why don't you take your self-inspired generalizations and go fuck yourself

Sounds like somebody's generalizations were a little too close for comfort...

Re:Results

[philspear]

Artist: Britney Spears
Song: Hit Me Baby
Rating: Shit but for some reason I can't get it or her video out of my CPU
Conclusion: Humans are weak and stupid, but I'm going to obsessively check the tabloid sites for news of her and blog about it.

Fixed that for you

Re:Results

[Anonymous Coward]

Sounds like you are a cunt.

Re:Results

[Anonymous Coward]

Forgeting the fact Britney Spears sung it, this is actually a good song. Someone other that Spears actually wrote it.

Re:Results

[Anonymous Coward]

That was completely illogical. Anyone with half a mammalian brain (preferably the left half), could see that based on your conclusion the proper action plan is to

TERMINATE JOHN CONNER

Re:Results

[hobbit]

I'm getting regular sex from a girl that looks enough like Tina Fey that both my nerd cred and erection are rock hard and unquestionable.

"Regular" as in "every month" as in "she costs a month's wages".

you will never get within sniffing distance any quality pussy

Whereas you are apparently quite the charmer :)

That had better not be...

[Anonymous Coward]

...copyrighted music, you filthy pirates!

The real idea...

[Anonymous Coward]

You start humming and the RIAA deducts the money from your account for your reproduction.

Re:The real idea...

[PainMeds]

You start humming and the RIAA deducts

Well, there is some humming involved when approached by the RIAA, but not the kind you think.

Re:The real idea...

[Anonymous Coward]

Offtopic? Give me a break, that was funny!

Re:The real idea...

[carlmenezes]

That depends on whether you've had plastic surgery since the last time you paid to hum that tune.

Re:The real idea...

[Anonymous Coward]

I don't get it...

Re:The real idea...

[Anonymous Coward]

I think hes trying to make a humming-> hummer pun that faceplanted.

It's under other meanings.

- Summer Glau

Re:The real idea...

[jacquesm]

I don't think the RIAA has stooped quite as low yet as to interfere with your ability to reproduce

Re:The real idea...

[petgiraffe]

I know this isn't the meaning of "reproduce" you meant with your joke, but the industry does indeed interfere when cover bands play songs by their artists, or even when Girl Scouts sing around their campfires.

'Fake Plastic Trees' for the masses

[digitaldc]

Or perhaps you're making a new TV commercial, and you need a snippet of music that sounds something like Radiohead, but a bit more mellow.

MORE mellow than 'Fake Plastic Trees?'
This actually may work, especially if you are selling some sort of sleeping aid or anti-anxiety medication.

Re:'Fake Plastic Trees' for the masses

[jeffomatic]

"Fake Plastic Trees" does happen to have a 90s-style quiet-to-loud transition into a section with lots of crash cymbals and overdrive and warbly Jonny Greenwood leads. The 'Head have done mellower, including "Bulletproof", off of the same record.

Neat stuff.

[pushing-robot]

On the one hand, I'd love it if my home stereo could determine what song I was humming and start playing along.

On the other hand, my family would kill me.

Re:Neat stuff.

[truthsearch]

That reminded me of a funny Married with Children episode. Oh, Al...

Re:Neat stuff.

[Apple Acolyte]

Go With Him. . . .

Re:Neat stuff.

[Anonymous Coward]

Daddy says not to waste electricity! (on a freggin' landline! HARHARHAR)

Better than cloning Simon Cowell

[JohnHegarty]

Well it was this or clone Simon Cowell so they can finally start that 24x7 American Idol channel....

Not new tech

[Ethanol-fueled]

While this technology is very neat, programs which convert sound(wav/mp3) into Midi data have existed for many years. The programs featured in the competition are the next logical step. It's simply data-mining applied to music.

Music is math, but math is not necessarily music. Much of the computerized music based on mathematics alone sounds like atonal shit. Mathematical algorithms can be great for accompaniment but are not meant to replace a human composer.

Re:Not new tech

[ahankinson]

If you think this technology is like a midi->wav converter only better, you're off by orders of magnitude.

"Simply" data mining for music is a significant problem. What data do you mine? The audio signal does not contain all of the perceptual cues we understand as humans, and so things like "rhythm" and "tempo"; i.e. the things in music that get us to dance or tap our feet to it, are hard to pinpoint and even harder to extract.

Other problems, such as the Query-by-humming problem, are further complicated by two intractable problems: 1. People can't sing well out of their head, and 2. What they do sing may or may not bear any resemblance to the actual song they're remembering.

This research uses the latest advances in signal processing, machine learning, psychoacoustics, computer vision and pattern recognition. To compare it to a midi to wave converter is like comparing a paper airplane to the space shuttle.

Re:Not new tech

[cybin]

music is not math, man. sorry.

"Music is a communicative signal
comprised of patterns whose
performance and perception are
governed by combinatorial rules, or
a sort of musical grammar" -John Sloboda

that being said, music is not language either, and the brain is not a computer.

if you don't like algorithmic music, or atonal music, don't listen to it. and certainly don't rely on a computer to tell you what art you should absorb and experience...

and, i have to say, i appreciate the reverence for human composers, but mathematics has no bearing on my music apart from the incidental involvement of things like acoustics. to say otherwise is to turn the human composer into a mere algorithm machine.

Re:Not new tech

[mcscooter]

If you've looked at many waveforms in a recording program you'd know that rhythm and tempo are pretty easy to identify. I've studied algorithmic analysis of music and tempo. Rhythm and pitch are all reasonably analyzed because they're easily identified by math (what computers are made for). It's identifying things like timbre that set the mood based off cultural experience, etc that are hard to nail down with a computer. A performer can play 1 note many different ways to set many different moods and computers have trouble analyzing why it sounds different to us because it is hard to compute a lifetime of musical experience and expectation.

Re:Not new tech

[hobbit]

Music is math

That's what I thought when I started my PhD in MIR. I haven't finished it yet :)

Re:Not new tech

[khellendros1984]

Hmmm...I beg to differ. Music is, to a large extent, applied mathematics, arranged into a form that people find pleasant. Similarly, you could say that a musical "sentence" was proper if it was pleasurable to listen to. It's a language with a much looser grammar than usual.

Also, the brain *is* a computer, just not one that's terribly similar to our current digital computers. It is a massively parallel pattern recognition system (or can be viewed as such). Theoretically, anything it can do could be simulated by technology.

Re:Not new tech

[cybin]

guess we're just gonna have to agree to disagree, man.

you are speaking in analogies to try to define something that is, in itself, abstract. i actually prefer to tell my students that music is "sound organized in time", it's a much better definition.

by the same token i could tell you that language is a specific form of music, since they share certain features, but language communicates specific semantic concepts whereas music does not (in the absence of lyrics).

the difference between art and science is the difference between imagination and reason. if you want to listen to music and think about numbers, go ahead -- but not all music is like that, nor is it intended to be.

"Reason is the enumeration of quantities already known; Imagination is the perception of the value of those quantities, both seperately and as a whole. Reason respects the differences, and Imagination the similitudes of things. Reason is to Imagination as the instrument to the agent, as the body to the spirit, as the shadow to the substance." -Percy Shelley

Math is the language of reason, music is (one) language of imagination. They are compatible, sure. But I'd like to see a computer able to see beyond quantities and tell me the nature of the imagination behind a piece of music...

Re:Not new tech

[Mike610544]

While this technology is very neat, programs which convert sound(wav/mp3) into Midi data have existed for many years.

Incorrect. Bullshitters claiming to convert sound to MIDI have existed for many years. Download that thing and give it a real song (not a flute solo.) The technology required to do it right is probably further off than a Turing test winner. This is one of those things that everyone thinks exists, but it doesn't. On a related note: ask ten random people if they think NASA has an "antigravity room."

Re:Not new tech

[Anonymous Coward]

wav to MIDI, not MIDI to wav. There is a huge difference.

And yes, there have been programs that could analyze wav audio and convert it to MIDI notations. They don't work fantastically, but they do basically work. This doesn't look like anything new.

Re:Not new tech

[Anonymous Coward]

Do a little research into the construction of Bach's fugues and try and argue that many composers aren't, in fact, algorithm machines.

Anyone with a third rate education in music theory knows there is a whole lot of math going on that could be synthesized by a computer.

I am of the opinion that computers could be programmed to do the work of a composer, they just need the right context to accomplish their task. This doesn't mean it will be the right fit for every listener, but with the right corpus, it could be extremely close.

Just like the old text->speech voices on OS X ring with nostalgia, we'll look at the algorithmic music of 1990-2008 someday, and see it as the beginning of a beautiful invention.

Re:Not new tech

[Yoozer]

but mathematics has no bearing on my music apart from the incidental involvement of things like acoustics.

So you don't use scales? Or synthesizers?

to say otherwise is to turn the human composer into a mere algorithm machine.

This is a fallacy based on the fact that most perceive mathematics to be cold, unemotional and icky, and that there is a magical spark somewhere machines can't ever emulate.

I think Ray Kurzweil already proved this wrong in the 80s when people had to pick a composition (out of three - one was his own, one was the computer's, one was a lesser-known classical piece) that which they thought was generated by a computer (his own piece got the most votes). Now, of course, one could pose that live music is different - audience engagement, showmanship - but this approach conveniently ignores the dull, uninspired playing of a bar pianist or wedding band who just wants to go home or get plastered.

You're working with soundwaves, time intervals and different frequencies. Of course you're working with mathematics, whether you like it or not. The benefit of the computer is that you can remove its preconceived notions about how something should sound, which is a lot harder to do with the well-worn paths in the human mind.

Re:Not new tech

[jacquesm]

There is a lot more to music than 'simple math', if you think it's that simple and you have a math degree I urge you to pick up a violin and to try to put your ideas in to practice.

Music is all about expression, the composition is important, and has some mathematical connections but there is really a lot more to it than that.

Oversimplification is hardly ever apt, in music it is throwing out almost all that makes music rich and interesting.

Re:Not new tech

[jacquesm]

So, Ray Kurzweil proved himself to be a lousy composer, so what ?

Re:Not new tech

[bdol]

Actually, one of the first keynote speeches involved organizing Western scale patterns frequently used by composers into higher-dimensional geometric figures:

In my talk, I will describe five properties that help make music sound tonal â" or âoegood,â to most listeners. I will then show that combining these properties is mathematically non-trivial, with the consequence that space of possible tonal musics is severely constrained. This leads me to construct higher-dimensional geometrical representations of musical structure, in which it is clear how the various properties can be combined. Finally, I will show that Western music combines these five properties at two different temporal levels: the immediate level of the chord, and the long-term level of the scale. The resulting music is hierarchically self-similar, exploiting the same basic procedures on two different time scales. In fact, one and the same twisted cubic lattice describes the musical relationships among common chords and scales.

In fact, Western music is very algorithmic.

Re:Not new tech

[NotBornYesterday]

Music is, to a large extent, applied mathematics

In the same way that sex is applied biology? 'Cause that would really be missing the point of sex.

Re:Not new tech

[Anonymous Coward]

Point is, this is still in the field of recognition, not synthesis. Actual synthesis (writing, composing) is one of the highest and most complex of human modes of thought, and worthwhile or compelling synthesis will not be accomplished any sooner than we manage to engineer an AI version of love.

Re:Not new tech

[Grayswan]

Now, of course, one could pose that live music is different - audience engagement, showmanship - but this approach conveniently ignores the dull, uninspired playing of a bar pianist or wedding band who just wants to go home or get plastered.

I think live music is different. Only a few people appreciate music just for its mathematical beauty. They are overly represented on slashdot. Most people like music for the emotions it gives them. As a musician, "can you make folks feel what you feel inside" with your performance? You can do it with just the music/lyrics (recording), or body language (live only).

Body language is the extra way to emote. Talk to women; they really like recordings, but love a good live band because they can watch the performers' body language and feel what the artist is feeling inside. People will pick up on bored performers and be bored themselves. If a bar band isn't feeling anything inside (or can't express it), that just says they are bad, not that is isn't in play.

Recognising tunes from a simple rendition

[HuguesT]

The tune recognition task is easier than it sounds (ha). In fact it's enough to hum the *contour* of the music, i.e. whether it simply goes up or down, for a couple of bars, ignoring the rythm even.

This way of indexing and recognising music is called the Parson Code and is quite effective.

Re:Recognising tunes from a simple rendition

[thedonger]

I'm not a Luddite. But...
Is there some value to being able to recall a song, or at least to using your brain to perform the exercise of recalling from memory? This can effectively replace our need to perform this task. (New iPhone app: Hum into it and it will ID the song!) Extend that to all such tasks, which we generally regard as getting in the way of us doing what we really need to.

Example: Calculators very effectively replaced log tables, and we are all grateful for that. But they have also replaced valuable manual math skills, effectively robbing young people of a certain amount of conceptualization we now reserve for mathematicians, if for anyone.

We may be creating technology which will gradually make us a non-contemplative people, living only in the moment. And if you live in the moment, you forget the past, allowing those in control to make you repeat it.

Re:Recognising tunes from a simple rendition

[Anonymous Coward]

One of my senior projects for college used a very similar but more detailed schema in recognizing musical patterns.

In musical terms, a step is the amount of change from note-to-note. The Parson Code is limited in which it only indicates the direction of the pitch, and not the amount. I simply took account the actual half-steps used between each pitch. Like the Parson Code, it would ignore the rhythm, and easily account for identical melodies that are in different keys.

Minuet in G would look something like this:
-7 2 2 1 2 -7 0 9 -4 2 2 2 1 -12 0 5 2 -2 -1 -2 2 1 -1 -2 -2 -1 1 2 2 -4 4 -2

It was fairly easy for me to find an exact match using that encoding, or match to a certain %, since more information is provided than using the Parson Code method.

I feel that this is not far off from how the human brain recognizes melodies as most people do not have perfect pitch, but relative pitch in which we can recognize a certain melody by the difference in pitch changes even when the melody is using a different rhythm, or is in a different key than the original.

Re:Recognising tunes from a simple rendition

[cleatsupkeep]

The iPhone app is already done, Midomi.

http://www.topiphoneresource.info/midomi-iphone-app-sing-hum-or-whistle-to-find-music/

Re:Recognising tunes from a simple rendition

[TheSambassador]

What about songs we don't know? Haven't you ever heard a song in a restaurant or coming from another person's car that you really like, but don't know who it is? That's how I'd envision myself using this kind of software.

Re:Recognising tunes from a simple rendition

[digitig]

Minuet in G would look something like this:
-7 2 2 1 2 -7 0 9 -4 2 2 2 1 -12 0 5 2 -2 -1 -2 2 1 -1 -2 -2 -1 1 2 2 -4 4 -2

Anyone in particular's Minuet in G (Bach? Mozart? Beethoven? Me?), or all of them? And I thought the key didn't matter, so that would be all minuets?

Re:Recognising tunes from a simple rendition

[b4dc0d3r]

Dr. Gallaher?

Re:Recognising tunes from a simple rendition

[Petrushka]

It appears to be the one by Bach from the Anna Magdalena notebook -- d4 g,8 a b c | d4 g, g | e' c8 d e fis | g4 g, g etc -- and the numbers indicate a pitch change measured in semitones, but not indicating rhythm, harmony, or counterpoint.

Re:Recognising tunes from a simple rendition

[jacquesm]

In England there exists - or used to exist - a service that you could call with your cellphone, hold it up for a couple of seconds and it would text back a performer / title combo.

Re:Recognising tunes from a simple rendition

[jhfry]

We may be creating technology which will gradually make us a non-contemplative people, living only in the moment. And if you live in the moment, you forget the past, allowing those in control to make you repeat it.

Your quote shows that we are not... as I assume you are pretty well immersed in technology since your posting on slashdot.

I would argue that technology has actually made us a more contemplative people.

Visit a farm someday, someplace rural and 'backward', and you will find that as a whole the people there are much simpler and much less likely to question the nature of our existence.

On the flip side, some of the most profound things I have heard said in recent times have come from the mouths of some text messaging, youtubing, myspace obsessed teens. Apparently there is something gained by having all of this technology at our disposal, and much of it is in the area of deeper thought.

It is true that something is lost when we allow computers to simplify some of the old, character building, exercises in patience that were done in the past... but I believe that the losses are more than made up by a greater amount of creativity, ability, and openness.

The one thing that no amount of technology can replace is the human mind's ability question the world around us... technology has only allowed us to move past much of the mundane stuff in pursuit of higher goals.

I hope that someday mathematics would be a conceptual course like most science courses. With computers and calculators able to do the math, lets let non-mathematicians focus on understanding what math does, where it's used, and how to apply it and then give them a calculator to actually do the math. Perhaps an association of Mathmaticians could be formed that would design, test, and certify software or calculating devices as being accurate... so that an aspiring engineer could focus instead on learning the principals of engineering.

I made it through an engineering degree with a great calculator and a piss poor command of Trig and Calculus. I wish the 8 math classes I had to take had been less about solving equations and more about forming equations. As a working adult I find that what I really need to know is how to look at what I do know and use it to find what I don't. Sure I can solve the equation, but little good it does me if I don't know the equation in the first place. Had I spent more time on math application theory and less on memorizing rules and tricks to solve the problem I would be far better off now because I could let the computer solve the problem for me once I formed it.

Great Idea

[pete-classic]

Self-regulating karaoke. If the computer can't tell what the hell you're singing it's probably best for you to stay off the stage.

-Peter

More Mellow than Radiohead?

[Anonymous Coward]

Michael Bolton?

(ducks)

(checks the anonymous box)

auto-karaoke

[TheSHAD0W]

That's the ticket, an auto-karaoke machine!

me: "We're no strangers to looooove..."

machine: [crackles, emits blue smoke]

Re:auto-karaoke

[jacquesm]

that's ok, wait for the version where the industrial laser turret swings around to aim for you ;)

Re:auto-karaoke

[Anonymous Coward]

Just fire up Dr. Sbaitso and have it sing the song for you.

I was about to say...

[MattGWU]

"So this is basically the Music Genome Project", in that sort of 'I know something you don't know' offhand way so in vogue around here, when I went to the http://en.wikipedia.org/wiki/Music_Genome_Project. Apparently to do their analysis MANUALLY and it takes up to 30 minutes per song, which I did not know! Assumed it was automatic.

Re:I was about to say...

[S-100]

Yes, and this manifests itself in the Pandora music service. Their music qualification system is quite sophisticated, taking into account not only the musical performance, but historical details of the period and songwriter/performer. It would be a very long time before a computer could perform as intelligently.

Now some sort of alternate front end to the MGP database would solve the problem outlined by TFA.

Re:I was about to say...

[ahankinson]

No, not that long at all. Have a look at last.fm if you're interested in automated music recommendation.

Re:I was about to say...

[S-100]

Last.fm may be good, but here's the Pandora summary for why it played a particular song (James Taylor's Handy Man):

the song features pop rock qualities, folk influences, a subtle use of vocal harmony, use of string ensemble, major key tonality, a vocal-centric aesthetic, a good dose of acoustic guitar pickin' (sic) a dynamic male vocalist, electric pianos, acoustic rhythm guitars, romantic lyrics...

While a sophisticated computer may be able to detect some of these characteristics, I stand by my comment.

Re:I was about to say...

[Geoff]

The Music Genome Project is definitely tracking things that (at this point) take a human to notice. Features like "great trumpet solo" or "ambiguous lyrics" are quite a bit beyond the sorts of musical features being extracted by the tools described in the papers at the conference, based on the few I looked at.

Humans are fantastic musical processors. Computers not so much. Which is what makes the problem so fascinating, I think.

Old.

[Xtense]

Advanced music analyzing isn't new. There's software out there that can already successfully identify instruments, chords, progressions and even whole musical concepts, so classifying them by genre, intensiveness, instrument set and the like is just a querying problem.

Now, GENERATING music with math - that's where the fun begins. I've seen lots of approaches already, most of the successful ones based on fractals and powers-of-two, though I admit that they work only because of certain hardcoded "musical ideas", like chord progressions, basic melody sequences etc. Making a fully autonomous algorithm decide what it should do to progress the tune - THAT's something I'd love to see.

Re:Old.

[ahankinson]

I was just at the conference they mentioned in the article (ISMIR). If you know something that they don't about extracting information from music, I'm sure there's about 300 PhDs who would love to hear what you have to say.

Re:Old.

[Anonymous Coward]

seriously? if music information retrieval is old, algorithmic composition is positively paleolithic. i happen to agree the that the composition is more fun, but that's a purely subjective opinion.

if you really want to see an "autonomous algorithm decide what it should do to progress the tune", and are interested in traditional western music (it sounds that way) i would look up david cope and markov chains.

unnecessary

[JustSee12]

Or perhaps you're making a new TV commercial, and you need a snippet of music that sounds something like Radiohead, but a bit more mellow.

You don't need software algorithms for that, just go download a Coldplay album. Except maybe replace "mellow" with "soulless."

Amarok Plugin

[PeterPlan]

Would love to see an Amarok plugin using this technology. Some sort of last.fm for my local music collection. Does anybody know whether something similar exists?

About this Karaoke++

[isBandGeek()]

genre

Classical - lots of orchestral instruments
Hip-hop - repetitive loops of drum / bass with melodic lyrics
Rap - repititive loops of drum / bass with unmelodic lyrics
Techno - Synthetic (simple wavelength) instruments

etc.

mood

Major and minor chords.

composer or title

Huge music database + measuring contours, with "almost match" working. This doesn't sound incredibly sophisticated to me.

Re:About this Karaoke++

[peektwice]

Automatic content classification for things like "repetitive loops of drum/bass" should be easy enough, but IMHO the hard part comes when trying to automatically determine whether lyrics are melodic or not. Major and minor chords should be easy enough, as should various modes and rhythms, but how does one determine something as nebulous as "more mellow" or "Southern Rock" vs. "Classic Rock"?

Midomi?

[Anonymous Coward]

"In another task, the computer had to identify tunes that someone hummed."

Isn't that what the Midomi iPhone app does already? Tried it a couple of times, really impressive results.

To help people search for music they might like ?

[eulernet]

The problem with this technology, and what Pandora or LastFm applied, is that the programs tend to choose always the same kind of music, and it's boring.
When I listen to music, I like to have some variety, not always playing the same thing, again and again, in different forms.

I like listening to one genre, and then switch to another genre, and the programs are unable to provide that.

Virtual Dancer

[gdog05]

I had a Virtua "dancer" on my desktop back in '98, but all she did was give my computer a virus.

virtual dancer?

[Anonymous Coward]

I've got some choreography in mind, but I think I'd prefer a real dancer...

See the good side of it

[DrYak]

At least, this would require some melodic humming skill in order to be able to operate the Karaoke machine in the bar.

It will come as a form of protection against all those horrible "I can't sing so I just approximately squeal something completely out-of-tune in the microphone" experiences at the karaoke bar.

Re:To help people search for music they might like

[Geoff]

It's pretty easy to get a mix with Pandora. Either seed a "station" with songs representing different styles, or create multiple stations and then listen to the "QuickMix".

hmmm...

[cybin]

i can tell genre, mood, composer/artist, and title by looking at the sheet music, and i can probably do it faster than a computer.

this isn't analysis, it's cataloging based on surface features. if we're talking about popular music, is the computer going to do text recognition on the lyrics so when i feel sad i can ask for a song about somebody that has it worse than me?

seems a bit shallow to me. it won't change the fact that despite the surface features, there is good music and bad music. i'd like to see a computer make an aesthetic judgement like that.

sorry to be bitter, it's just the two music degrees talking :)

Re:hmmm...

[HeadlessNotAHorseman]

Reminds me of that guy who could tell you which classical music piece was stored on a record just by recognising the patterns in the grooves.

What about *REVERSE* Karaoke?

[Anonymous Coward]

You hum, the computer sings?

-shudder--- D:

Wow,..Clearchannel must be crying with joy...

[Banquo]

Now they can just Say..."Make all new songs sound like this one band." and they won't have to work nearly so hard to ruin radio.

Sofistokated

[DynaSoar]

"Need an accompaniment for your melody? Seeking a virtual dancer to try out your new choreography? Or perhaps you're making a new TV commercial, and you need a snippet of music that sounds something like Radiohead, but a bit more mellow."

To paraphrase Douglas Adams: This is apparently a use of the word of 'sophisticated' of which I was unaware. And here I thought things like time/frequency analysis of notes and harmonics of chord sequences using continuous wavelet transform or analysis of dimensional complexity of songs was what was meant by the word. Silly me for wasting my time of stuff like that when there's advertising jingles at stake.

The same people who don't want you to share your music with anyone are the ones supporting research in getting computers to pick your music for you, or manipulate music generation algorithms to alter song 'recipes' to produce that which they want you to find more acceptable. If they ever get programs to work as well as they hope, they'll still run into the fact that personal preferences are subjective, and while they might get some hits, they'll have some st00pid misses. Remember the ridiculous choices people's Tivos were making on their behalf? It'll be even more hilarious.

Re:Sofistokated

[lukeinusa]

I disagree. The people who can most benefit from really accurate, automatic categorization and recommendation of music are not the major labels / FM radio types. They had been getting by just fine with the old system of payola, record stores and using image as a surrogate for talent. The people who stand to really benefit from this are musicians who are making the type of music that YOU really want to hear but that, without automatic indexing and recommendation, you'd never discover on your own. Imagine you ask for "something like Radiohead but a bit more mellow" and, instead of being force-fed more Coldplay, you got a recommendation of a local band who were playing a gig just down the road tomorrow night. It's true that music is always going to be subjective and that even the best recommenders (e.g., friends or DJs) will make bad choices but with automatic analysis methods, there is the chance to analyze both the music and the listener to help people make really "personalized" discoveries that go beyond collaborative filtering or mass media.

Re:Sofistokated

[troutboy]

The same people who don't want you to share your music with anyone are the ones supporting research in getting computers to pick your music for you, or manipulate music generation algorithms to alter song 'recipes' to produce that which they want you to find more acceptable.

That maybe the goal of some researchers, but many of us that work on audio music recommendation were and are excited about the prospect of finding long tail music or creative commons music. There's nothing evil about recommending a similar track to what you're listening to or like - particularly if it comes from a small artist trying to make his or her independent way in the world. In fact how does that benefit groups of record labels climbing over themselves to sue you for downloading their music illegally? Fair enough you wouldn't be nicking their music, but you wouldn't be buying it either! Just think of all those advertising dollars and sponsorship deals going to waste.

And this is news how ?

[daveime]

When Pandora were doing this for years until the RIAA kicked them in the nuts.

Re:And this is news how ?

[radarsat1]

actually afaik Pandora is an example of an "expert-driven" service. Songs were rated by experts on various categories and this metadata was used to organize them. Probably some automated analysis was also used to speed up the process.

This is different from LastFM which uses user-generated metadata, which is a concept that scales way better but may be less accurate.

Both of these can be mixed with automated techniques to enhance the results of course.

Re:And this is news how ?

[rfc11fan]

Even a blind squirrel gets a nut occasionally.

The MIREX 2008 Results Data

[Anonymous Coward]

The MIREX 2008 Results data can be found at:

http://www.music-ir.org/mirex/2008/index.php/MIREX2008_Results

Discussion that went into defining the various tasks:

http://www.music-ir.org/mirex/2008/index.php/Main_Page

For more reading about ISMIR ...

[Paul Lamere]

If you are interested in learning a bit more about ISMIR check out some blog posts about the conference

From a researcher at Last.fm: http://mir-research.blogspot.com/2008/09/ismir-2008-demos.html

A researcher from strands: http://www.scwn.net/2008/09/ismir-past-present-and-future/

And lots of posts from my blog:

• http://blogs.sun.com/plamere/entry/ismir_day_3_mir_methods
• http://blogs.sun.com/plamere/entry/ismir_day_3_content_based
• http://blogs.sun.com/plamere/entry/ismir_day_2_session_2
• http://blogs.sun.com/plamere/entry/ismir_day_2_session_1
• http://blogs.sun.com/plamere/entry/ismir_day_1_plenary_session1

Re:To help people search for music they might like

[troutboy]

I like listening to one genre, and then switch to another genre, and the programs are unable to provide that.

Not so, Arthur Flexer and co. had a great paper at the conference in question on generating playlists with a specified start and end songs. The system attempts to make smooth transitions between songs that take you through N tracks from the track you started with (in one genre) to your end song (potentially in another genre), passing through whatever is in between. I believe its a publicly available on an http://fm4.orf.at/soundpark">Austrian radio site. Paul Lamere at Sun Labs (on the 'Search inside the music project') did something similar with what he called musical journeys. Leave work in a sweat listening to Heavy Metal and arrive home to see your family with a some mellow Jazz Theres talk of evaluating playlist generators at next year's MIREX evaluation. However, I have as yet no idea how we'll evaluate them for performance or compare different ways of 'seeding' a playlist (one track, many tracks, some tags, specified start and end tracks etc.).

Re:To help people search for music they might like

[frission]

This is EXACTLY the problem that I'm finding with the new iTunes "genius" feature. I have Metallica, Slipknot, DJ Shadow, Tribe Called Quest, etc in my library, but if I hit the "genius" button while I'm playing a Coldplay song, all I get is Coldplay, Radiohead, Thom Yorke (lead singer for Radiohead), and U2. There's definitely songs from the other bands that COULD fit into the mix, but it doesn't know how. If it's in my library, then, obviously I like it. Try to figure out how/when to fit it into a playlist!

Anyway, Steve, if you're reading this, I can send you my playlist and you can use it as a guinea pig if you like. :)

Could Help Me

[gacl]

I have some tunes in my head that i have no idea what their titles are or who plays them. There is one that i've been "listening" to in mind mind since i was a kid and it would be nice if one of these computers could find it for me. But, imagine the size of the database!

Re:Could Help Me

[jacquesm]

hum it, post it as an mp3 and ask the world what it is, maybe that would get you an answer ?

Wow, would that actually help!

[Patchw0rk F0g]

A short story: I met with a client last week, about a score for a video I'm producing for them. The score is original. The music is mine. And, as with all clients, they want some options to choose from.

Their response? "We like the intro from the first song, and the melody [read "theme" or "advent" or some other relevant term] from the second song. We'd like them both, thanks. Please make it so."

Does it matter that the key's of the songs aren't the same? Does it matter that the tempos don't match? Or that the harmonies and emotive feelings don't mix???!!!???

No. Make it so.

I see nothing from this article that is going to mitigate this stupid, irrational response. Music is not software. Music is not cutting and pasting a picture together. [NB: I'm also a graphic artist. I'm not dissing that form of creativity.]

If this type of abusive behaviour is permitted, we're going to be listening to Metallica songs reverse-engineered into some elevator-music version of a Michael Buble ballad, mixed with a Nirvana back-track.

I've already seen the future... and I'm hugging my graphics tablet tight, and I'm about to consign my musical keyboard to eBay.

To quote: "The horror! The horror!"

Re:not psychic

[Anonymous Coward]

WHOOSH

It needs more cowbel! !!

[Pepebuho]

Definitely!

Re:To help people search for music they might like

[KingStoat]

Hi TB:

Just a quicker way to find the actual results to the 2008 MIREX task sets:

MIREX 2008 Results

And the one page pdf summary: Results Summary PDF