/// <summary>
/// Constructor
/// </summary>
/// <param name="samplingRate"></param>
/// <param name="featureCount"></param>
/// <param name="frameDuration"></param>
/// <param name="hopDuration"></param>
/// <param name="filterbankSize"></param>
/// <param name="lowFreq"></param>
/// <param name="highFreq"></param>
/// <param name="fftSize"></param>
/// <param name="filterbank"></param>
/// <param name="lifterSize"></param>
/// <param name="preEmphasis"></param>
/// <param name="includeEnergy"></param>
/// <param name="dctType">"1", "1N", "2", "2N", "3", "3N", "4", "4N"</param>
/// <param name="nonLinearity"></param>
/// <param name="spectrumType"></param>
/// <param name="window"></param>
/// <param name="logFloor"></param>
public MfccExtractor(int samplingRate,
int featureCount,
double frameDuration = 0.0256 /*sec*/,
double hopDuration = 0.010 /*sec*/,
int filterbankSize = 24,
double lowFreq = 0,
double highFreq = 0,
int fftSize = 0,
float[][] filterbank = null,
int lifterSize = 0,
double preEmphasis = 0,
bool includeEnergy = false,
string dctType = "2N",
NonLinearityType nonLinearity = NonLinearityType.Log10,
SpectrumType spectrumType = SpectrumType.Power,
WindowTypes window = WindowTypes.Hamming,
float logFloor = float.Epsilon)
: base(samplingRate, frameDuration, hopDuration, preEmphasis)
{
FeatureCount = featureCount;
_lowFreq = lowFreq;
_highFreq = highFreq;
if (filterbank == null)
{
_blockSize = fftSize > FrameSize ? fftSize : MathUtils.NextPowerOfTwo(FrameSize);
var melBands = FilterBanks.MelBands(filterbankSize, _blockSize, SamplingRate, _lowFreq, _highFreq);
FilterBank = FilterBanks.Triangular(_blockSize, SamplingRate, melBands, mapper: Scale.HerzToMel); // HTK/Kaldi-style
}
else
{
FilterBank = filterbank;
filterbankSize = filterbank.Length;
_blockSize = 2 * (filterbank[0].Length - 1);
Guard.AgainstExceedance(FrameSize, _blockSize, "frame size", "FFT size");
}
_fft = new RealFft(_blockSize);
_window = window;
_windowSamples = Window.OfType(_window, FrameSize);
_lifterSize = lifterSize;
_lifterCoeffs = _lifterSize > 0 ? Window.Liftering(FeatureCount, _lifterSize) : null;
_includeEnergy = includeEnergy;
// setup DCT: ============================================================================
_dctType = dctType;
switch (dctType[0])
{
case '1':
_dct = new Dct1(filterbankSize);
break;
case '2':
_dct = new Dct2(filterbankSize);
break;
case '3':
_dct = new Dct3(filterbankSize);
break;
case '4':
_dct = new Dct4(filterbankSize);
break;
default:
throw new ArgumentException("Only DCT-1, 2, 3 and 4 are supported!");
}
if (dctType.Length > 1 && char.ToUpper(dctType[1]) == 'N')
{
_applyDct = mfccs => _dct.DirectNorm(_melSpectrum, mfccs);
}
else
{
_applyDct = mfccs => _dct.Direct(_melSpectrum, mfccs);
}
// setup spectrum post-processing: =======================================================
_logFloor = logFloor;
_nonLinearityType = nonLinearity;
switch (nonLinearity)
{
case NonLinearityType.Log10:
_postProcessSpectrum = () => FilterBanks.ApplyAndLog10(FilterBank, _spectrum, _melSpectrum, _logFloor);
break;
case NonLinearityType.LogE:
_postProcessSpectrum = () => FilterBanks.ApplyAndLog(FilterBank, _spectrum, _melSpectrum, _logFloor);
break;
case NonLinearityType.ToDecibel:
_postProcessSpectrum = () => FilterBanks.ApplyAndToDecibel(FilterBank, _spectrum, _melSpectrum, _logFloor);
break;
case NonLinearityType.CubicRoot:
_postProcessSpectrum = () => FilterBanks.ApplyAndPow(FilterBank, _spectrum, _melSpectrum, 0.33);
break;
default:
_postProcessSpectrum = () => FilterBanks.Apply(FilterBank, _spectrum, _melSpectrum);
break;
}
_spectrumType = spectrumType;
switch (_spectrumType)
{
case SpectrumType.Magnitude:
_getSpectrum = block => _fft.MagnitudeSpectrum(block, _spectrum, false);
break;
case SpectrumType.Power:
_getSpectrum = block => _fft.PowerSpectrum(block, _spectrum, false);
break;
case SpectrumType.MagnitudeNormalized:
_getSpectrum = block => _fft.MagnitudeSpectrum(block, _spectrum, true);
break;
case SpectrumType.PowerNormalized:
_getSpectrum = block => _fft.PowerSpectrum(block, _spectrum, true);
break;
}
// reserve memory for reusable blocks
_spectrum = new float[_blockSize / 2 + 1];
_melSpectrum = new float[filterbankSize];
}
/// <summary>
/// Constructs extractor from configuration <paramref name="options"/>.
/// </summary>
public MfccExtractor(MfccOptions options) : base(options)
{
FeatureCount = options.FeatureCount;
var filterbankSize = options.FilterBankSize;
if (options.FilterBank is null)
{
_blockSize = options.FftSize > FrameSize ? options.FftSize : MathUtils.NextPowerOfTwo(FrameSize);
var melBands = FilterBanks.MelBands(filterbankSize, SamplingRate, options.LowFrequency, options.HighFrequency);
FilterBank = FilterBanks.Triangular(_blockSize, SamplingRate, melBands, mapper: Scale.HerzToMel); // HTK/Kaldi-style
}
else
{
FilterBank = options.FilterBank;
filterbankSize = FilterBank.Length;
_blockSize = 2 * (FilterBank[0].Length - 1);
Guard.AgainstExceedance(FrameSize, _blockSize, "frame size", "FFT size");
}
_fft = new RealFft(_blockSize);
_lifterSize = options.LifterSize;
_lifterCoeffs = _lifterSize > 0 ? Window.Liftering(FeatureCount, _lifterSize) : null;
_includeEnergy = options.IncludeEnergy;
_logEnergyFloor = options.LogEnergyFloor;
// setup DCT: ============================================================================
_dctType = options.DctType;
switch (_dctType[0])
{
case '1': _dct = new Dct1(filterbankSize); break;
case '3': _dct = new Dct3(filterbankSize); break;
case '4': _dct = new Dct4(filterbankSize); break;
default: _dct = new Dct2(filterbankSize); break;
}
if (_dctType.EndsWith("N", StringComparison.OrdinalIgnoreCase))
{
_applyDct = mfccs => _dct.DirectNorm(_melSpectrum, mfccs);
}
else
{
_applyDct = mfccs => _dct.Direct(_melSpectrum, mfccs);
}
// setup spectrum post-processing: =======================================================
_logFloor = options.LogFloor;
_nonLinearityType = options.NonLinearity;
switch (_nonLinearityType)
{
case NonLinearityType.Log10:
_postProcessSpectrum = () => FilterBanks.ApplyAndLog10(FilterBank, _spectrum, _melSpectrum, _logFloor); break;
case NonLinearityType.LogE:
_postProcessSpectrum = () => FilterBanks.ApplyAndLog(FilterBank, _spectrum, _melSpectrum, _logFloor); break;
case NonLinearityType.ToDecibel:
_postProcessSpectrum = () => FilterBanks.ApplyAndToDecibel(FilterBank, _spectrum, _melSpectrum, _logFloor); break;
case NonLinearityType.CubicRoot:
_postProcessSpectrum = () => FilterBanks.ApplyAndPow(FilterBank, _spectrum, _melSpectrum, 0.33); break;
default:
_postProcessSpectrum = () => FilterBanks.Apply(FilterBank, _spectrum, _melSpectrum); break;
}
_spectrumType = options.SpectrumType;
switch (_spectrumType)
{
case SpectrumType.Magnitude:
_getSpectrum = block => _fft.MagnitudeSpectrum(block, _spectrum, false); break;
case SpectrumType.MagnitudeNormalized:
_getSpectrum = block => _fft.MagnitudeSpectrum(block, _spectrum, true); break;
case SpectrumType.PowerNormalized:
_getSpectrum = block => _fft.PowerSpectrum(block, _spectrum, true); break;
default:
_getSpectrum = block => _fft.PowerSpectrum(block, _spectrum, false); break;
}
// reserve memory for reusable blocks
_spectrum = new float[_blockSize / 2 + 1];
_melSpectrum = new float[filterbankSize];
}
/// <summary>
/// Constructs <see cref="Mdct"/> of given <paramref name="dctSize"/>.
/// </summary>
/// <param name="dctSize">Size of MDCT</param>
/// <param name="dct">Internal DCT transformer (by default, <see cref="Dct4"/>)</param>
public Mdct(int dctSize, IDct dct = null)
{
_dct = dct ?? new Dct4(dctSize);
_temp = new float[dctSize];
}
