Comments on: Question for the Agora: How does Shazam work?

By: The one

The one — Fri, 21 Jan 2011 08:45:56 +0000

Here is an answer, explained for anyone to understand:

http://www.soyoucode.com/2011/how-does-shazam-recognize-song

By: nnylw

nnylw — Tue, 05 Jan 2010 11:52:29 +0000

Dont bite off more than you can chew oxaprozin [url=http://pharmacy-and-pharmacy.com/oxaprozin/]oxaprozin[/url] hycet [url=http://pharmacy-and-pharmacy.com/hycet/]hycet[/url] ismo [url=http://pharmacy-and-pharmacy.com/ismo/]ismo[/url] alimta [url=http://pharmacy-and-pharmacy.com/alimta/]alimta[/url] benzoyl [url=http://pharmacy-and-pharmacy.com/benzoyl/]benzoyl[/url] demerol [url=http://pharmacy-and-pharmacy.com/demerol/]demerol[/url] micardis [url=http://pharmacy-and-pharmacy.com/micardis/]micardis[/url]

By: talhah

talhah — Tue, 22 Sep 2009 07:24:16 +0000

@Steve that is a brilliant comment! The real sound of space. music for the next generation. I love it!!!

By: Ahmed Roshdy

Ahmed Roshdy — Wed, 22 Jul 2009 23:15:13 +0000

Hi,
Actually I found a very nice article explainign how does it work in a very simple way. Hereunder the link:

http://laplacian.wordpress.com/2009/01/10/how-shazam-works/

Ahmed

By: Steve

Steve — Tue, 06 Jan 2009 17:04:15 +0000

Hey, thats really Interesting, how a Audio source is in fact a constellation, so does that mean that we could take a snap shot of what we see in space and translate it into what it sounds like.. the real sound of space?

By: bob

bob — Wed, 31 Dec 2008 14:56:29 +0000

There’s a paper on how Shazam works. More technical than I can comprehend, but interesting to see.
http://www.ee.columbia.edu/~dpwe/papers/Wang03-shazam.pdf

By: Dennis

Dennis — Mon, 29 Dec 2008 20:14:55 +0000

Thanks, that clears it up. Now for the theory of relativity…

By: ari

ari — Sat, 06 Dec 2008 06:50:44 +0000

I also wondered the same thing and from what i can tell, it analyses the song and uses an acoustic fingerprint that it compares to a database to determine a match.

It could generate an acoustic fingerprint using any of the following well known audio features: Fourier coefficients, Mel Frequency Cepstral Coefficients (MFFC), spectral flatness, sharpness, Linear Predictive Coding (LPC) coefficients and others. Also derived quantities such as derivatives, means and variances of audio features could be used. The extracted features are mapped into a more compact representation by using classification algorithms, such as Hidden Markov Models, or quantization…