I mentioned Shazam a while ago with disbelief. Well I guess it’s legit and the brains of the operation is speaking at Stanford. Bob, want to check this out? If I could forward this to you as an event, I would

Avery Wang, distinguished CCRMA and Hearing Seminar graduate and now CTO of
Shazam, will be talking about his audio fingerprint algorithm for
identifying songs. Hold your phone up to the speaker in a pub in England,
and Avery’s technology will identify the song and give you the title.

We had a lot of problems scheduling this talk, but we wanted to do it when
Ton Kalker can also be in attendance. Many of you will remember Ton’s talk
several weeks ago, when he presented a song identification system he
developed for Phillips. It will be fun to have the experts all in one room
for a grand discussion!!!

Who: Avery Wang (Shazam)
What: Audio Fingerprinting
When: Friday June 27th at 2PM **** Today when many of you read this ****
Where: CCRMA Library (Top floor of the knoll)
or possibly the ballroom

Presentation on the Shazam music recognition service
Avery Wang

We have developed and commercially deployed a flexible audio search engine.
The algorithm is noise and distortion resistant, computationally efficient,
and massively scalable, capable of quickly identifying a short segment of
music captured through a cellphone microphone in the presence of foreground
voices and other dominant noise, and through voice codec compression, out of
a database of over a million tracks. The algorithm uses a combinatorially
hashed time-frequency constellation analysis of the audio, yielding unusual
properties such as transparency. Furthermore, for applications such as
radio monitoring, search times on the order of a few milliseconds per query
are attained, even on a massive music database.