public List <bool[]> CreateFingerprintsFromAudioSamples(float[] samples, WorkUnitParameterObject param, out double[][] logSpectrogram)
{
IFingerprintingConfiguration configuration = param.FingerprintingConfiguration;
AudioServiceConfiguration audioServiceConfiguration = new AudioServiceConfiguration
{
LogBins = configuration.LogBins,
LogBase = configuration.LogBase,
MaxFrequency = configuration.MaxFrequency,
MinFrequency = configuration.MinFrequency,
Overlap = configuration.Overlap,
SampleRate = configuration.SampleRate,
WindowSize = configuration.WindowSize,
NormalizeSignal = configuration.NormalizeSignal,
UseDynamicLogBase = configuration.UseDynamicLogBase
};
// store the log spectrogram in the out variable
logSpectrogram = AudioService.CreateLogSpectrogram(
samples, configuration.WindowFunction, audioServiceConfiguration);
return(this.CreateFingerprintsFromLogSpectrum(
logSpectrogram,
configuration.Stride,
configuration.FingerprintLength,
configuration.Overlap,
configuration.TopWavelets));
}
/// <summary>
/// Get logarithmically spaced indices
/// </summary>
/// <param name="configuration">
/// The configuration for log frequencies
/// </param>
/// <returns>
/// Log indexes
/// </returns>
private int[] GenerateLogFrequencies(AudioServiceConfiguration configuration)
{
if (configuration.UseDynamicLogBase)
{
return(GenerateLogFrequenciesDynamicBase(configuration));
}
return(GenerateStaticLogFrequencies(configuration));
}
private int[] GenerateLogFrequenciesDynamicBase(AudioServiceConfiguration configuration)
{
double logBase =
Math.Exp(
Math.Log((double)configuration.MaxFrequency / configuration.MinFrequency) / configuration.LogBins);
double mincoef = (double)configuration.WindowSize / configuration.SampleRate * configuration.MinFrequency;
int[] indexes = new int[configuration.LogBins + 1];
for (int j = 0; j < configuration.LogBins + 1; j++)
{
int start = (int)((Math.Pow(logBase, j) - 1.0) * mincoef);
int end = (int)((Math.Pow(logBase, j + 1.0f) - 1.0) * mincoef);
indexes[j] = start + (int)mincoef;
}
return(indexes);
}
private int[] GenerateStaticLogFrequencies(AudioServiceConfiguration configuration)
{
double logMin = Math.Log(configuration.MinFrequency, configuration.LogBase);
double logMax = Math.Log(configuration.MaxFrequency, configuration.LogBase);
double delta = (logMax - logMin) / configuration.LogBins;
int[] indexes = new int[configuration.LogBins + 1];
double accDelta = 0;
for (int i = 0; i <= configuration.LogBins /*32 octaves*/; ++i)
{
double freq = (double)Math.Pow(configuration.LogBase, logMin + accDelta);
accDelta += delta; // accDelta = delta * i
/*Find the start index in array from which to start the summation*/
indexes[i] = FreqToIndex(freq, configuration.SampleRate, configuration.WindowSize);
}
return(indexes);
}
public double[][] CreateLogSpectrogram(
float[] samples, IWindowFunction windowFunction, AudioServiceConfiguration configuration)
{
DbgTimer t = new DbgTimer();
t.Start();
if (configuration.NormalizeSignal)
{
NormalizeInPlace(samples);
}
int width = (samples.Length - configuration.WindowSize) / configuration.Overlap; /*width of the image*/
double[][] frames = new double[width][];
int[] logFrequenciesIndexes = GenerateLogFrequencies(configuration);
double[] window = windowFunction.GetWindow();
for (int i = 0; i < width; i++)
{
double[] complexSignal = new double[2 * configuration.WindowSize]; /*even - Re, odd - Img, thats how Exocortex works*/
// take 371 ms each 11.6 ms (2048 samples each 64 samples, samplerate 5512)
// or 256 ms each 16 ms (8192 samples each 512 samples, samplerate 32000)
for (int j = 0; j < configuration.WindowSize; j++)
{
// Weight by Hann Window
complexSignal[2 * j] = window[j] * samples[(i * configuration.Overlap) + j];
// need to clear out as fft modifies buffer (phase)
complexSignal[(2 * j) + 1] = 0;
}
lomonFFT.TableFFT(complexSignal, true);
frames[i] = ExtractLogBins(complexSignal, logFrequenciesIndexes, configuration.LogBins);
}
Dbg.WriteLine("Create Log Spectrogram - Execution Time: {0} ms", t.Stop().TotalMilliseconds);
return(frames);
}
public double[][] CreateLogSpectrogram(string pathToFile, IWindowFunction windowFunction, AudioServiceConfiguration configuration)
{
float[] samples = ReadMonoFromFile(pathToFile, configuration.SampleRate, 0, 0);
return(CreateLogSpectrogram(samples, windowFunction, configuration));
}
