Audio Fingerprint: Difference between revisions

From MusicBrainz Wiki
Jump to navigationJump to search
(PUID update (Imported from MoinMoin))
 
(typo (Imported from MoinMoin))
Line 3: Line 3:
Up to early 2006 [[MusicBrainz]] has used Relatable's [[TRM]], which is an algorithm matching files by audio fingerprints. However, we have been [[Getting Rid Of TRM|GettingRidOfTRM]], because we have reached the limits of scalability, and performance is not as good as we would like. Because the server is closed-source, we have no way to fix either of these problems.
Up to early 2006 [[MusicBrainz]] has used Relatable's [[TRM]], which is an algorithm matching files by audio fingerprints. However, we have been [[Getting Rid Of TRM|GettingRidOfTRM]], because we have reached the limits of scalability, and performance is not as good as we would like. Because the server is closed-source, we have no way to fix either of these problems.


For a short while we debated whether we should attempt to build our own open source [[Future Proof Fingerprint 2|FutureProofFingerprint]]<code><nowiki></nowiki></code>ing technology, but nobody was there who couldhave done the work.
For a short while we debated whether we should attempt to build our own open source [[Future Proof Fingerprint|FutureProofFingerPrint]]<code><nowiki></nowiki></code>ing technology, but nobody was there who couldhave done the work.


Since March 2006 [[MusicBrainz]] collaborates with [[MusicIP]] who operate the [[MusicDNS]] service. Their (proprietary but much better) [[PUID]]s are now being integrated into the [[Picard Tagger|PicardTagger]] to create [[Picard With Acoustic Fingerprinting|PicardWithAcousticFingerprinting]] (a beta is available). See [[PUID]] and [[How PUIDs Work|HowPUIDsWork]] for details.
Since March 2006 [[MusicBrainz]] collaborates with [[MusicIP]] who operate the [[MusicDNS]] service. Their (proprietary but much better) [[PUID]]s are now being integrated into the [[Picard Tagger|PicardTagger]] to create [[Picard With Acoustic Fingerprinting|PicardWithAcousticFingerprinting]] (a beta is available). See [[PUID]] and [[How PUIDs Work|HowPUIDsWork]] for details.

Revision as of 16:23, 31 March 2006

Audio fingerprints are identifiers for audio files based on the contained audio data.

Up to early 2006 MusicBrainz has used Relatable's TRM, which is an algorithm matching files by audio fingerprints. However, we have been GettingRidOfTRM, because we have reached the limits of scalability, and performance is not as good as we would like. Because the server is closed-source, we have no way to fix either of these problems.

For a short while we debated whether we should attempt to build our own open source FutureProofFingerPrinting technology, but nobody was there who couldhave done the work.

Since March 2006 MusicBrainz collaborates with MusicIP who operate the MusicDNS service. Their (proprietary but much better) PUIDs are now being integrated into the PicardTagger to create PicardWithAcousticFingerprinting (a beta is available). See PUID and HowPUIDsWork for details.

Known Audio Fingerprinting Systems

Open source systems:

  • The fingerprint in Kurt Rosenfeld's FDMF
  • Freetantrum songprint
  • There is a project called freetantrum on Sourceforge. It seems to be a dead project (it's home page was replaced with an advert for unrelated things in 2001), but it may be worth investigating and resurecting the code they produced.
  • MusicURI, an apparently dead project trying to combine fingerprinting with text based search (Lucene?). The GPL source code is available at SourceForge, while a paper describing the project used to be available at http://semedia.deit.univpm.it/musicuri/ - now loadable from Google's cache.
  • A possible FutureProofFingerPrint algorithm that we could code has been Proposed by Geoff Schmidt, formally of Tuneprint.

Commercial systems:

  • Relatable's TRM
  • The system MusicBrainz originally used. This is going to be phased out as soon as PUIDs work better than TRM.
  • This article compares business models for Philips & Audible Magic
  • Philips (also licensed by SNOCAP)
  • USC
  • Frauenhofer:
  • Shazam have their own proprietary music fingerprinting system, currently offered directly to users over the telephone.
  • And possibly most ridiculously of all: The Song Tapper