[CLAM] ClamExtractorExample LowFreqEnergyRelation

David García Garzón dgarcia at iua.upf.edu
Mon Feb 25 17:37:50 PST 2008

A student at UPF also needed to use MFCC from the ClamExampleExtractor 
descriptors in matlab and we tried the xml toolbox you mention with no luck 
(we were blocked by a missimplementation of XPath standard). Maybe we missed 
something or maybe you opted by xml navigation instead of xpath. We finally 
used a small  Java snippet to get them with XPath and convert it into a 
proper matlab matrix.

I planned to eventually post such matlab/java code on the wiki. Almost sure 
you have that part covered but as you could be still interested I'll hurry 
and ask her the code.


On Monday 25 Febrer 2008, vincenzo.dimattia wrote:
> Dear David thanks a lot for your help. My final project consists on an
> automatic audio segmentation system which I have implemented in matlab
> modifying the Alexander Haubold’s Matlab resources
> [http://www.aquaphoenix.com/research/matlab/]. The modified program
> requires as input the audio file (wav) and the CLAM XML file. In order to
> interface Matlab with CLAM I used an XML parser which is able to extract
> the values of the MFCC descriptor from the CLAM XML file. In particular I
> used XMLTree an XML toolbox for Matlab
> [http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=1
>757&objectType=file]. Thanks again
> Best regards
> Vincenzo
> ---------- Initial Header -----------
> From      : "David García Garzón" dgarcia at iua.upf.edu
> To          : clam at iua.upf.edu
> Cc          : "vincenzo.dimattia" vincenzo.dimattia at libero.it,"clam"
> clam at iua.upf.edu Date      : Mon, 25 Feb 2008 15:16:41 +0100
> Subject : Re: [CLAM] ClamExtractorExample LowFreqEnergyRelation
> > On Monday 25 February 2008 12:25:24 vincenzo.dimattia wrote:
> > > Dear all,I am Vincenzo Dimattia, I am developing my final project, an
> > > automatic segmentation system,and I am using the programm
> > > ClamExtractorExample for the extraction of the audio descriptors . I
> > > would like to know how is calculated the LowFreqEnergyRelation.This
> > > should be higher for low frequency signal and lower for high frequncy
> > > signal. Is it right? Thanks
> > > Vincenzo Dimattia
> >
> > Hi, Vincenzo.
> >
> > There was an error on doxygen description. LowFreqEnergyRelation had the
> > description of MaxMagFreq. I just fixed it on the svn. The description
> > for LowFreqEnergyRelation is now this one:
> >
> > "Ratio between the energy over 0-100 Hz band and the whole spectrum
> > energy. To avoid singularities while keeping descriptor continuity, when
> > the whole spectrum energy drops bellow $10^{-4}$, such value is
> > considered as whole spectrum energy."
> >
> > So you are right with your interpretation. But keep in mind that 0-100 Hz
> > is a very narrow band and it is used to spot bass sounds. If you are
> > interested in locating high frequencies, HighEnergyContent is more
> > appropiated. It is defined as:
> >
> > "Sum of the squared spectrum magnitude multiplied by the wave number of
> > the bin. It is pretty similar to the derivative of the energy, or a high
> > pass filter, which gives higher values for high frequency content."
> >
> > We would be glad if you report back to the mailinglist your progress with
> > your final project :-) And, please, consider also integration of your
> > work into CLAM code base. Integration into a big existing project is
> > often appreciated by evaluators. Just drop us a line if you want to.
> >
> > David.

David García Garzón
(Work) dgarcia at iua dot upf anotherdot es
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part.
URL: <http://lists.clam-project.org/pipermail/clam-users-clam-project.org/attachments/20080226/c5d9e376/attachment.sig>

More information about the clam-users mailing list