[Clam-devel] residual spectrum line segment approximation?
roumbaba
roumbaba at gmail.com
Sun Jun 8 15:39:59 PDT 2008
Thanks, so I am trying to add a Do method in SpectralEnvelopeExtract
that takes a spectrum an not an array of peaks.
I have something working but I seem to be able to only call my Do
function function once. It crashes on the second time I call it. I
don't see what it is I am doing wrong or not doing.
Here is my code so far:
in spectralEnvelopeExtract.cxx (based on the original Do function
that takes a peak array as input):
bool SpectralEnvelopeExtract::Do(const Spectrum& input, Spectrum&
output)
{
output.SetScale(input.GetScale());
TSize nBins=input.GetSize();
if (nBins<4) return false; //cannot extract an envelope out of only
3 peaks!
CheckOutputType(output);
DataArray& magBuffer=input.GetMagBuffer();
DataArray& phaseBuffer=input.GetPhaseBuffer();
// DataArray& freqBuffer=input.GetFreqBuffer();
Array<Point>& magPointArray=output.GetMagBPF().GetPointArray();
Array<Point>& phasePointArray=output.GetPhaseBPF().GetPointArray();
//Max number of points allowed: should be a config param
magPointArray.Resize(mConfig.GetMaxPeaks());
magPointArray.SetSize(mConfig.GetMaxPeaks());
phasePointArray.Resize(mConfig.GetMaxPeaks());
phasePointArray.SetSize(mConfig.GetMaxPeaks());
TData curBinFreq = 0;
for(int i=0;i<nBins;i++)
{
curBinFreq = input.GetSpectralRange()*i/
(float)nBins;
magPointArray[i+1].SetX(curBinFreq);
magPointArray[i+1].SetY(magBuffer[i]);
phasePointArray[i+1].SetX(curBinFreq);
phasePointArray[i+1].SetY(phaseBuffer[i]);
}
//todo: a lot of duplicated code, should extract in different
functions
if(input.GetScale()==EScale::eLog)
{
//we now set first point (maybe we should do the same as with last
point?)
magPointArray[0].SetX(0);
magPointArray[0].SetY(magBuffer[0]-3);
phasePointArray[0].SetX(0);
phasePointArray[0].SetY(0);
nBins++;
/* we keep adding points to bpf until magnitude is insignificant
(note that we add points outside the spectral range) */
curBinFreq = (nBins-2)*input.GetSpectralRange
()/(float)nBins; /*note: I compute the current bin's frequency
instead of the peakArray'sfreqBuffer */
TData lastFreq = curBinFreq; //freqBuffer[nBins-2];
curBinFreq = (nBins-3)*input.GetSpectralRange
()/(float)nBins;
TData freqGap = lastFreq-curBinFreq; //freqBuffer[nBins-3];
TData currentFreq=lastFreq+freqGap;
TData currentMag=magBuffer[nBins-2];
while(currentMag>-200)
{
currentMag-=(currentFreq/lastFreq-1)*12;
magPointArray[nBins].SetY(currentMag);
magPointArray[nBins].SetX(currentFreq);
phasePointArray[nBins].SetY(0);
phasePointArray[nBins].SetX(currentFreq);
currentFreq+=freqGap;
nBins++;
if(nBins==mConfig.GetMaxPeaks()) break;
}
//we resize arrays to final size
magPointArray.Resize(nBins);
magPointArray.SetSize(nBins);
phasePointArray.Resize(nBins);
phasePointArray.SetSize(nBins);
}
else
{
//we now set first point (maybe we should do the same as with last
point?)
magPointArray[0].SetX(0);
magPointArray[0].SetY(magBuffer[0]*0.5);
phasePointArray[0].SetX(0);
phasePointArray[0].SetY(0);
nBins++;
/* we keep adding points to bpf until magnitude is insignificant
(note that we add points outside the spectral range) */
curBinFreq = (nBins-2)*input.GetSpectralRange
()/(float)nBins;
TData lastFreq = curBinFreq;//freqBuffer[nBins-2];
curBinFreq = (nBins-3)*input.GetSpectralRange
()/(float)nBins;
TData freqGap=lastFreq-curBinFreq;//freqBuffer[nBins-3];
TData currentFreq=lastFreq+freqGap;
TData currentMag=magBuffer[nBins-2];
while(currentMag<0.0000000001)
{
currentMag*=CLAM_pow(0.06,(double)(currentFreq/lastFreq-1.0));
magPointArray[nBins].SetY(currentMag);
magPointArray[nBins].SetX(currentFreq);
phasePointArray[nBins].SetY(0);
phasePointArray[nBins].SetX(currentFreq);
currentFreq+=freqGap;
nBins++;
if(nBins==mConfig.GetMaxPeaks()) break;
}
//we resize arrays to final size
magPointArray.Resize(nBins); //!!! (note 1) This is where the
crash seem to happen on the second time I call this Do method (see
error messsage below)
magPointArray.SetSize(nBins);
phasePointArray.Resize(nBins);
phasePointArray.SetSize(nBins);
}
output.SetSize(nBins);
output.GetMagBPF().UpdateSplineTable();
return true;
}
and this is how I try to use it in my program:
void SMSStdio::PrintSpectrum(std::string inputXMLFileName)
{
TIndex i,j;
TData m1, m2;
int nbOfFrames = 0;
LoadConfig(inputXMLFileName);
LoadAnalysis(mGlobalConfig.GetInputAnalysisFile());
if(!GetState().GetHasTransformation())
{
CopySegmentExceptAudio(mOriginalSegment,mTransformedSegment);
GetState().SetHasTransformation(true);
}
mTransformedSegment.mCurrentFrameIndex=0;
nbOfFrames = mTransformedSegment.GetnFrames();
SpectralEnvelopeExtract spectralEnvelopeExtract;
Spectrum outputEnvSpec;
Spectrum inputSpec;
SpecTypeFlags f;
Frame inputFrame;
for( i=0; i < nbOfFrames; i++)
{
inputFrame = mTransformedSegment.GetFrame
( mTransformedSegment.mCurrentFrameIndex++ );
inputSpec = inputFrame.GetResidualSpec();
//Change inputSpec's type from Complex to MagPhase
inputSpec.GetType(f);
if( !f.bMagPhase )
{
f.bMagPhase = true;
inputSpec.SetTypeSynchronize(f);
}
//Set outputSpectrum's type To BPF
outputEnvSpec.GetType(f);
if( !f.bMagPhaseBPF )
{
f.bMagPhaseBPF = true;
outputEnvSpec.SetType(f); //set spectrum to be a BPF
}
spectralEnvelopeExtract.Do( inputSpec,
outputEnvSpec ); // !!!!!this is where I always get the crash on the
second time i hit this line see error message below and note 1 above
}
// outputEnvSpec.BPF2MagPhase();
// outputEnvSpec.MagPhase2Complex();
/*
for ( j = 0; j < 10; j++ )
{
m1 = inputSpec.GetMag( j );//myFrame.GetResMag(j);
m2 = outputEnvSpec.GetMag( j );
fprintf( stderr, "m1 = %f m2 = %f", m1 , m2);
}
fprintf( stderr, "\n");
*/
return;
}
This is the error I get:
SMSConsole(18690,0xa000ed88) malloc: *** error for object 0xd98d600:
incorrect checksum for freed object - object was probably modified
after being freed, break at szone_error to debug
SMSConsole(18690,0xa000ed88) malloc: *** set a breakpoint in
szone_error to debug
Program received signal EXC_BAD_ACCESS, Could not access memory.
Reason: KERN_INVALID_ADDRESS at address: 0x3fe7984a
0x900074d8 in szone_free ()
Any idea of what I am doing wrong?
Thanks.
On 27 mai 08, at 14:25, Xavier Amatriain wrote:
> Hi Roumbaba,
>
> In the paper you cite it says "you can", which does not mean "you
> have to" :-) Doing an approximation of the residual model is indeed
> an interesting thing to do, especially if you want to reduce the
> amount of data in your transformed signal, however it is not a must.
> Note that there are many other ways to model the residual apart
> from the one mentioned in that paper.
>
> So far, in CLAM we are using the residual as is, with no modeling
> or approximation. The "only" downside is that the transformed
> signal (SMS Data) is in fact larger than the original audio when it
> could be much smaller with not much loss in quality. If for
> whatever reason you do need to do the residual modeling you can
> look at the SpectralEnvelopeExtract processing. This processing
> generates a spectral approximation (spectrum in bpf format) but
> from an array of peaks, it would not be hard to modify it to work
> with an input spectrum.
>
> X
>
>
> roumbaba wrote:
>> Hi all,
>>
>> I am trying to understand how the residual spectrum gets modeled
>> in clam/SMS. I have read the Serra/Smith 1990 CMJ paper and as I
>> understand it it describes two steps:
>> 1- substract the harmonic spectrum from the original spectrum
>> 2- perform a line-segment approximation of the residual spectrum
>> obtained in 1
>>
>> I have stepped through clam and SMS code and I think I can see
>> where step 1 gets performed:
>>
>> SMSAnalysisCore::Do()
>> {
>>
>> mSinSpectralAnalysis.Do();
>> mResSpectralAnalysis.Do();
>> ...
>> ...
>> ...
>> mSynthSineSpectrum.Do();
>> mSpecSubstracter.Do(); /* step 1 gets performed here I think*/
>>
>> }
>>
>>
>> but I cannot find where step 2 (line approximation) gets
>> performed. Where should I look in the code?
>>
>> Thank you very much,
>> Cheers,
>>
>> Roumbaba
>>
>> ps:
>>
>> Here is a quote from the paper I mentionned above:
>>
>> "Approximation of the Spectral Residual
>>
>> Assuming the the residual signal is quasi-stochastic, each
>> magnitude-spectrum residual can be approximated by its envelope
>> since only its shape contributes to the sound characteristics.
>> [...] The particular line-segment approximation performed here is
>> done by stepping through the magnitude spectrum and finding local
>> maxima in every section, ..."
>>
>>
>> _______________________________________________
>> Clam-devel mailing list
>> Clam-devel at llistes.projectes.lafarga.org
>> https://llistes.projectes.lafarga.org/cgi-bin/mailman/listinfo/
>> clam-devel
>
>
> _______________________________________________
> Clam-devel mailing list
> Clam-devel at llistes.projectes.lafarga.org
> https://llistes.projectes.lafarga.org/cgi-bin/mailman/listinfo/clam-
> devel
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.clam-project.org/pipermail/clam-devel-clam-project.org/attachments/20080608/77943c45/attachment-0003.htm>
More information about the clam-devel
mailing list