2 years, 1 month ago
via iphoneqna.com
I understand there's an application for the iPhone called Shazam that recognizes played music. How does it do that?
I was with someone not long ago in a mall. I couldn't remember the name of the song that was playing. She pulled out her iPhone, found an audio speaker in a relatively quiet spot, went into "Shazam" and had the answer within a minute. This is, to me, amazing technology and I want to know how it works. Is it a voice recognition sort of thing? Considering how unintelligible a lot of recording artists are, I don't see how that's possible. Anyway, do you know how Shazam works? It's magic and a mystery to me!
images:
You can leave an optional "tip" with Mahalo's virtual currency, Mahalo Dollars. If you are asking a difficult question that might require some research, or if you'd like a wide variety of feedback, a higher tip often leads to more answers to your question.
M$1 Answer
Shazam has a library of more than 8 million songs. The owners have devised a technique to break down each track into a simple numeric signature; a code that is unique to each track. It's kinda like the fingerprint to the song.
"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."
How does Shazam make these fingerprints?
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 the points that represent the peaks of the graph—notes that contain "higher energy content" than all the other notes around it. In practice, this seems to work out to about three data points per second per song. It uses these data points to create the fingerprint used to ID the songs.
"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."
How does Shazam make these fingerprints?
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 the points that represent the peaks of the graph—notes that contain "higher energy content" than all the other notes around it. In practice, this seems to work out to about three data points per second per song. It uses these data points to create the fingerprint used to ID the songs.
You can leave an optional "tip" with Mahalo's virtual currency, Mahalo Dollars. If you are asking a difficult question that might require some research, or if you'd like a wide variety of feedback, a higher tip often leads to more answers to your question.
M$Report Abuse
