[CLAM] Audio Fingerprinting

David García Garzón dgarcia at iua.upf.edu
Wed Apr 18 11:21:12 PDT 2007

On Dimecres 18 Abril 2007, jn jn wrote:
> Hello,
> I'm new to CLAM, and my interest on audio has been increasing in the last
> months, mainly because of my interest in MPEG-7 and in audio
> fingerprinting. And so I was wondering if CLAM has been coded taking in
> care what is written in the MPEG-7 audio standard and also if it supports
> audio fingerprinting (by itself).

One of the examples on the Annotator extracts most of the Mpeg7 low level 
descriptors. Most of the Mpeg7 descriptors has been review against the 
standard and some of them are not what the are intendeded (notably Spectral 
Kurtosis and Skew). You'll find an accurate documentation on Anyway when they 
fail to implement the standard it is clearly noticed on the doxygen 
documetation. We didn't remove them because even thought they are not the 
standard, they has been proven useful in some contexts.

About fingerprinting, i would suggest to use musicbrainz library. If you want 
to implement such a system in CLAM you are wellcome. Anyway if you explain 
better your goals maybe i could answer you more accuratelly. 

You can browse what do we have by checking some of those classes:

David García Garzón
(Work) dgarcia at iua dot upf anotherdot es
(Home) vokimon at telefonica adot net
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
URL: <http://lists.clam-project.org/pipermail/clam-users-clam-project.org/attachments/20070418/0b48ed2f/attachment.sig>

More information about the clam-users mailing list