The first few bars of that tune you heard on the car radio last night keep ricocheting around and around in your head — but what’s the name and who’s the artist? You don’t know the words and you’re too embarrassed to sing its melody to your friends, but if you can hum it — even poorly — then Silicon Valley firm Melodis has an app for you.
Midomi, offered as a free download for the ubiquitous iPhone, is similar to other music recognition services (namely Shazam, which also works on the BlackBerry), but goes one step further. While Shazam requires the user to record and then transmit a snippet of the actual recording, for example by holding the phone up to a car’s speaker, Melodis users can hum, sing or play the song on a kazoo or other instrument.
Apparently it’s also smart enough to “hear” even the warbling of the tone deaf. Melodis chief executive Keyvan Mohajer said, in a BBC News article, that if ”a song is not in our database, [you can] sing or hum that song and save your voice, then your voice becomes a fingerprint. Next time somebody searches for a song, you match their voice to your voice to find the song.”
And best of all, the app doesn’t laugh at you or tell you how hopeless your sense of melody really is. Like any good software application, it just does its job dutifully and quickly.
Yet another music recognition service called mHashup charts relationships among musical samples. Unlike Midomi, which is aimed at the bubble-gum set, mHashup is more for technically adept musicians and musicologists looking for some professionally relevant information beyond just the track name and artist. The service (not available as an iPhone app but used on the desktop) matches timbre and other more subtle elements. Michela Magas, mHashup’s creator, is quoted in the BBC News article talking about one practical example of its use by Hollywood film composers:
“When they compose and they come up with something which they find is very appropriate for the movie … they cannot tell whether it is something they heard when they were young or whether it’s truly original — and this is a big deal,” she said.
What’s next? Computers that actually create music tailored to our tastes and emotions? Call me jaded, but nothing surprises me anymore (however, a machine will never give us the genius of a Louis Armstrong or a Ludwig Van Beethoven).