Acoustic fingerprint
An acoustic fingerprint is a unique code generated from an audio waveform. Depending upon the particular algorithm, acoustic fingerprints can be used to automatically categorize or identify an audio sample. Practical uses of acoustic fingerprinting include broadcast monitoring, identification of music and ads being played, peer to peer network monitoring, sound effect library management, and video identification.
An acoustic fingerprint is very different from a hash code which is generated from the binary data contained in a file. A hash code identifies a particular file, an acoustic fingerprint identifies an audio recording.
A robust acoustic fingerprint will be based on the perceptual characteristics of the audio. If two files sound identical to a human listener, even though their binary data differs, their acoustic fingerprints should match. Audio compression techniques (MP3, WMA, Vorbis, etc.) are also generally based on perceptual characteristics, and a robust acoustic fingerprint will allow a recording to be identified after it has gone through such compression, even if the audio quality has been reduced significantly. Robust acoustic fingerprints are also immune to analog transmission artifacts, enabling radio broadcasts to be identified.
Reliable acoustic fingerprints are specific enough to identify a particular performance from among all the recordings of audio that a person or group have made. A reliable acoustic fingerprint is forensic in its accuracy.
Acoustic fingerprinting efforts include:
- All Media Guide's LASSO is a commercial service that uses acoustic fingerprinting, and other techniques, to recognize music.
- Audible Magic Corporation is a commercial venture that provides electronic media identification and copyright management solutions for content owners, publishers, broadcasters, disk replicators, hardware & software developers and IT organizations. They use a proprietary robust acoustic fingerprint, U.S. patent 5,918,223.
- Barcelona Music & Audio Technologies's bStamp is a commercial product for ambience noise robust audio identification based on a proprietary technique. bStamp generates playlists from any kind of audio stream, fast song matching and song database duplicate detection.
- Foosic is an open source project which uses its own free fingerprinting technology named libFooID.
- Gracenote's MusicID is a commercial product that uses acoustic fingerprinting along with other methods to identify music.
- MusicBrainz, an open source project for a music database that uses Open Fingerprint Architecture for fingerprinting and the MusicDNS service for identifying audio files.
- Shazam, an acoustic fingerprint-based service allows for songs to be identified via cell phone.