| Comments (3) | Misc
Dwallach pointed me at Shazam, an iPhone app which does a nice job of music identification. You start up the app, it listens for a sec, thinks for a while, and then tells you what you're listening to; not just the song but also the album, etc. I ran it on a not-so-random selection of songs from the radio and my CD collection (Ice Cube, Murder City Devils, Rolling Stones...) and it nailed all of them. Only objection is that it's fairly slow, but presumably that's a matter of CPU power... Anyway, pretty cool.


Almost no CPU power being used on the iPhone at all. It's just recording a snippet, then it sends it up to the mothership which reports back with the song info. CPU usage on the analysis side (server side with the iPhone app I think) is not huge either.

There are lots of college students programming similar systems, and from what I can see, they do most of the processing when the song is added to the database. When you send your sound query, it is reduced to a sequence of pitch changes. They don't track absolute pitch, they basically record "did they frequency go up a lot, down a lot, or stay about the same?" Not a lot of processing required, followed by a simple database search against the string of pitch changes.

I assume you've heard Dead Low Tide... which combines two favorites (the MCD and Godheadsilo).

Leave a comment