Acoustic fingerprint
From Wikipedia, the free encyclopedia
An acoustic fingerprint is a condensed digital summary, deterministically generated from an audio signal, that can be used to identify an audio sample or quickly locate similar items in an audio database.
Practical uses of acoustic fingerprinting include identifying songs, records, melodies, tunes, or advertisements; radio broadcast and peer to peer network monitoring; sound effect library management; video file identification; and much more.
Contents |
[edit] Attributes
A robust acoustic fingerprint algorithm must take into account the perceptual characteristics of the audio. If two files sound alike to the human ear, their acoustic fingerprints should be equal or very similar, even if their binary representations are quite different (Therefore, acoustic fingerprints are not really fingerprints in the strict sense of the term --- which must be sensitive to any small changes in the data). Common perceptual characteristics included in audio fingerprints include average zero crossing rate, estimated tempo (in BPM), average spectrum, spectral flatness, prominent tones across a set of bands, and bandwidth.
Most Audio compression techniques (MP3, WMA, Vorbis) will make radical changes to the binary encoding of an audio file without affecting the way it sounds. 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. For use in radio broadcast monitoring, acoustic fingerprints should also be insensitive to analog transmission artifacts.
On the other hand, a good acoustic fingerprint algorithm must be able to identify a particular master recording among all the productions of an artist or group. For use as evidence in a court of law, an acoustic fingerprint method must be forensic in its accuracy.[citation needed]
[edit] Implementations
Acoustic fingerprinting efforts include:
- All Media Guide's LASSO is a commercial service that uses acoustic fingerprinting, and other techniques, to recognize music. (US Patent 7,277,766)
- Audible Magic Corporation is a commercial venture that provides electronic media identification and copyright management solutions using proprietary acoustic fingerprinting technology U.S. Patent 5,918,223 based on original research by Musclefish Consulting [1]
- AudioID is a commercial technology for automatically identifying audio material using acoustic fingerprints. It was developed by the German Fraunhofer Institute.
- Auditude is an online video advertising company. It uses patented Auditude Connect video and audio fingerprinting technology to identify content and serve ads.
- BMAT - Barcelona Music & Audio Technologies's Vericast is a commercial product for acoustic audio identification based on a proprietary technique. Vericast automatically generates content reports from any kind of audio recording of radio and television broadcast, fast song matching for meta data restoration and song database duplicate detection.
- Foosic is a free and open content 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.
- Winamp version 5.5 uses Gracenote to power automatic playlist generation with "Nullsoft Playlist Generator" plugin that comes with the software.
- Last.fm have begun their own method of acoustic fingerprinting via the Fingerprinter application.[2]
- LazyTune is a search engine that uses audio fingerprinting to recognize songs in audio files.[3]
- Mediaguide is a commercial service that uses acoustic fingerprinting to identify broadcast radio music and advertising airplay on over 2500 commercial and noncommerical radio stations spanning over 200 US markets.
- MusicBrainz, a free and open content project for a music database that uses MusicIP's 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.
- Tunatic by Wildbits is an application that allows identifying music while being played, analyzing the songs and comparing with the information on a server
[edit] See also
[edit] References
- ^ "Content-Based Classification, Search, and Retrieval of Audio," IEEE MultiMedia, vol. 3, no. 3, pp. 27-36, Sept., 1996.
- ^ http://blog.last.fm/2007/08/29/audio-fingerprinting-for-clean-metadata Last.fm
- ^ About / LazyTune, Music Specialized Search Engine
[edit] External links
- MetatOGGer is a freeware that uses the MusicDNS service for identifying audio files.
- Audible Magic (audio & video image fingerprinting)
- Auditude Connect technology (audio and video fingerprinting)
- AudioFingerprint at MusicBrainz's wiki
- Philips Content Identification (audio and video fingerprinting)
- A Review of Algorithms for Audio Fingerprinting (P. Cano et al. In International Workshop on Multimedia Signal Processing, US Virgin Islands, December 2002)
This computer science article is a stub. You can help by expanding it. |