
That Tune, NamedHow does the music-identifying app Shazam work its magic?
Posted Monday, Oct. 19, 2009, at 5:14 PM ET
Shazam is the closest a cell phone can come to magic. Say you're in a restaurant, a song comes on, and you can't quite place the tune. In the past, your options were limited; you could try asking your spouse or the waiter for a clue, but that approach risked revealing your ignorance. (That's "Sex Machine," dumb ass.) Shazam—which launched in the United Kingdom in 2002 as a call-in service and became widely known in the United States last year when it hit the iPhone—solves the dilemma in a few clicks. Press a button on your phone, and in seconds you'll get the artist and song title. Other than playing video games, it's the most useful thing you can do on your phone.
Last week, Shazam announced that more than 50 million people worldwide have used the service—up from 35 million at the start of the year. The company also said that it's received an undisclosed investment from the fabled Silicon Valley venture-capital firm KPCB. Shazam's success seems justified—it's the one app you can show to iPhone skeptics to get them to reconsider their position (though Shazam is also available on Android, BlackBerry, Windows Mobile, and pretty much any other phone). Yet for all the acclaim it garners, Shazam's inner workings are pretty mysterious. How does it actually ID your song? How does the company make money? (Here's one hint: iPhone users should expect to see a pay version soon.) And what are the long-term prospects for a firm whose sole purpose is satisfying an acute, very occasional need?
First, a short explanation of how Shazam works. The company has a library of more than 8 million songs, and it has devised a technique to break down each track into a simple numeric signature—a code that is unique to each track. "The main thing here is creating a 'fingerprint' of each performance," says Andrew Fisher, Shazam's CEO. When you hold your phone up to a song you'd like to ID, Shazam turns your clip into a signature using the same method. Then it's just a matter of pattern-matching—Shazam searches its library for the code it created from your clip; when it finds that bit, it knows it's found your song.
OK, but how does Shazam make these fingerprints? As Avery Wang, Shazam's chief scientist and one of its co-founders, explained to Scientific American in 2003, the company's approach was long considered computationally impractical—there was thought to be too much information in a song to compile a simple signature. But as he wrestled with the problem, Wang had a brilliant idea: What if he ignored nearly everything in a song and focused instead on just a few relatively "intense" moments? Thus Shazam creates a spectrogram for each song in its database—a graph that plots three dimensions of music: frequency vs. amplitude vs. time. The algorithm then picks out just those points that represent the peaks of the graph—notes that contain "higher energy content" than all the other notes around it, as Wang explained in an academic paper he published to describe how Shazam works (PDF). In practice, this seems to work out to about three data points per second per song.
Slate Editors Spent All Day Arguing About Cancer Screenings and Health Care Rationing
What a Meal of Beef Stomach and Duck Throats Taught Me About the New China
The Blind Side: Illegal Use of Sandra Bullock
Train, Plane, or Automobile? What's the Greenest Way to Travel for Thanksgiving?
The Two Craziest Men in Hollywood Teamed Up To Make This Movie
Did Easy Rider's Predictions About America Come True?












Many businesses, restaurants, etc play illegal material to their customers... illegal, that is, in the eyes of the recording industry. 'For private use only' material is supposedly not for public performances, which is why Muzak has a stranglehold on big businesses that need to be by the books for their hundreds of locations. It is basically a licensing service.
Well, it used to be hard to know if the bar or whatever was playing a CD or the radio without a proper license... but now we could have millions of iPhone snoops. They could be sending information to the copyright enforcement people about the location and the song - with a bit of a recording - and those self-same could cooperate with the licensing companies like Muzak to know whether that song 'should' have been playing at that location. While this iPhone evidence may not be 'enough' in the first instance, a few people, or a tip for a more professional 'checkup' might serve well enough.
And then, the whole world will have yet another reason to want to burn record company execs in effigy, tar and feather them, rewrite copyright law, and give their big estates to unknown artists.
-- BenK
(To reply, click here)
I don't think you've got it right. My understanding is that it is unlawful to make money off recordings, but not to simply play them. If that were the case, every jukebox in every dive bar and diner going back 50 years would have been breaking the law.
The industry has gone after illegal downloading, but that's because there are copies being traded for ownership; it's not the same thing as listening to a song on a stereo in a coffee shop.
-- BritBailey
(To reply, click here)
ASCAP/RIAA takes the position that bar owners must pay license fees to play music in their establishment to attract the public. Whether or not they enforce it is a different matter - a lot of places play the radio or CDs without paying a dime, but the OP is right. Bar owners who "do it right" pay license fees for the music played on the jukebox.
-- Naptowner
(To reply, click here)