Recordings that sound identical to humans actually have unique psychoacoustical differences. Geoffrey Schmidt, a Massachusetts Institute of Technology (M.I.T.) student, is one of the first to develop an audio fingerprinting algorithm taking advantage of this principle. The audio fingerprint does not change when the sound is compressed, changed to a different file format, broadcast over the radio, passed through an MP3 encoder, re-equalized or played at a different speed. The resulting Tuneprint technology is developing around the tuneprint.com site set up by Schmidt for incubation. Tuneprint utilizes a model of human hearing used to predict how audio will appear after it's been distorted by the human ear, and the parts of neural processing that are understood. This is some of the same information that led to MP3 encoders achieving exceptional audio compression. Characteristics that uniquely identify the track are then identified by picking out the most important, surprising, or significant features of the sound.
Possible distributed audio applications include building netplay popularity
charts based on real time global live play, more capable music search engines,
improvements in musical file sharing (sorting, categorizing, removing
duplicates), digital rights, practical micropayment systems for artists and
enabling record companies to tag a track as copyrighted in real time upon
Date Listed: 02/05/2001