/// <summary>
/// Make Slaney's filter bank
/// </summary>
/// <param name="filterbankSize"></param>
/// <param name="samplingRate"></param>
/// <param name="fftSize"></param>
/// <param name="frameDuration"></param>
/// <param name="lowFreq"></param>
/// <param name="highFreq"></param>
/// <param name="normalize"></param>
/// <returns></returns>
private static float[][] MakeFilterbank(int filterbankSize,
int samplingRate,
int fftSize,
double frameDuration,
double lowFreq = 0,
double highFreq = 0,
bool normalize = true)
{
var frameSize = (int)(frameDuration * samplingRate);
fftSize = fftSize > frameSize ? fftSize : MathUtils.NextPowerOfTwo(frameSize);
return(FilterBanks.MelBankSlaney(filterbankSize, fftSize, samplingRate, lowFreq, highFreq, normalize));
}
public MfccSlaneyOptions(int samplingRate,
int featureCount,
double frameDuration,
double lowFrequency = 0,
double highFrequency = 0,
int filterbankSize = 40,
int fftSize = 0,
bool normalize = true)
{
var frameSize = (int)(frameDuration * samplingRate);
fftSize = fftSize > frameSize ? fftSize : MathUtils.NextPowerOfTwo(frameSize);
FilterBank = FilterBanks.MelBankSlaney(filterbankSize, fftSize, samplingRate, lowFrequency, highFrequency, normalize);
FilterBankSize = filterbankSize;
FeatureCount = featureCount;
FftSize = fftSize;
SamplingRate = samplingRate;
LowFrequency = lowFrequency;
HighFrequency = highFrequency;
NonLinearity = NonLinearityType.LogE;
}
private void buttonCompute_Click(object sender, EventArgs e)
{
var filterCount = int.Parse(textBoxSize.Text);
var samplingRate = _signal.SamplingRate;
var fftSize = int.Parse(textBoxFftSize.Text);
var lowFreq = float.Parse(textBoxLowFreq.Text);
var highFreq = float.Parse(textBoxHighFreq.Text);
Tuple <double, double, double>[] bands;
float[][] filterbank = null;
VtlnWarper vtln = null;
if (checkBoxVtln.Checked)
{
var alpha = float.Parse(textBoxVtlnAlpha.Text);
var vtlnLow = float.Parse(textBoxVtlnLow.Text);
var vtlnHigh = float.Parse(textBoxVtlnHigh.Text);
vtln = new VtlnWarper(alpha, lowFreq, highFreq, vtlnLow, vtlnHigh);
}
switch (comboBoxFilterbank.Text)
{
case "Mel":
bands = FilterBanks.MelBands(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxOverlap.Checked);
break;
case "Mel Slaney":
bands = FilterBanks.MelBandsSlaney(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxOverlap.Checked);
filterbank = FilterBanks.MelBankSlaney(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxNormalize.Checked, vtln);
break;
case "Bark":
bands = FilterBanks.BarkBands(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxOverlap.Checked);
break;
case "Bark Slaney":
bands = FilterBanks.BarkBandsSlaney(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxOverlap.Checked);
filterbank = FilterBanks.BarkBankSlaney(filterCount, fftSize, samplingRate, lowFreq, highFreq);
break;
case "Critical bands":
bands = FilterBanks.CriticalBands(filterCount, fftSize, samplingRate, lowFreq, highFreq);
break;
case "Octave bands":
bands = FilterBanks.OctaveBands(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxOverlap.Checked);
break;
case "ERB":
bands = null;
filterbank = FilterBanks.Erb(filterCount, fftSize, samplingRate, lowFreq, highFreq);
break;
default:
bands = FilterBanks.HerzBands(filterCount, fftSize, samplingRate, lowFreq, highFreq, checkBoxOverlap.Checked);
break;
}
if (bands != null && filterbank == null)
{
switch (comboBoxShape.Text)
{
case "Triangular":
filterbank = FilterBanks.Triangular(fftSize, samplingRate, bands, vtln, Utils.Scale.HerzToMel);
break;
case "Trapezoidal":
filterbank = FilterBanks.Trapezoidal(fftSize, samplingRate, bands, vtln);
break;
case "BiQuad":
filterbank = FilterBanks.BiQuad(fftSize, samplingRate, bands);
break;
default:
filterbank = FilterBanks.Rectangular(fftSize, samplingRate, bands, vtln);
break;
}
if (checkBoxNormalize.Checked)
{
FilterBanks.Normalize(filterCount, bands, filterbank);
}
}
var spectrumType = (SpectrumType)comboBoxSpectrum.SelectedIndex;
var nonLinearity = (NonLinearityType)comboBoxNonLinearity.SelectedIndex;
var logFloor = float.Parse(textBoxLogFloor.Text);
var mfccExtractor = new MfccExtractor(//samplingRate, 13, 0.025, 0.01,
samplingRate, 13, 512.0 / samplingRate, 0.01,
filterbank: filterbank,
//filterbankSize: 26,
//highFreq: 8000,
//preEmphasis: 0.97,
//lifterSize: 22,
//includeEnergy: true,
spectrumType: spectrumType,
nonLinearity: nonLinearity,
dctType: comboBoxDct.Text,
window: WindowTypes.Hamming,
logFloor: logFloor);
_mfccVectors = mfccExtractor.ComputeFrom(_signal);
//_mfccVectors = mfccExtractor.ComputeFrom(_signal * 32768);
//var mfccVectorsP = mfccExtractor.ParallelComputeFrom(_signal * 32768);
//for (var i = 0; i < _mfccVectors.Count; i++)
//{
// for (var j = 0; j < _mfccVectors[i].Features.Length; j++)
// {
// if (Math.Abs(_mfccVectors[i].Features[j] - mfccVectorsP[i].Features[j]) > 1e-32f)
// {
// MessageBox.Show($"Nope: {i} - {j}");
// return;
// }
// if (Math.Abs(_mfccVectors[i].TimePosition - mfccVectorsP[i].TimePosition) > 1e-32f)
// {
// MessageBox.Show($"Time: {i} - {j}");
// return;
// }
// }
//}
//FeaturePostProcessing.NormalizeMean(_mfccVectors); // optional (but REQUIRED for PNCC!)
//FeaturePostProcessing.AddDeltas(_mfccVectors);
var header = mfccExtractor.FeatureDescriptions;
//.Concat(mfccExtractor.DeltaFeatureDescriptions)
//.Concat(mfccExtractor.DeltaDeltaFeatureDescriptions);
FillFeaturesList(_mfccVectors, header);
mfccListView.Items[0].Selected = true;
melFilterBankPanel.Groups = mfccExtractor.FilterBank;
mfccPanel.Line = _mfccVectors[0].Features;
}
