public void TestSpectrograms()
{
var recordingPath = PathHelper.ResolveAsset("Recordings", "SM304264_0+1_20160421_004539_47-48min.wav"); // "SM304264_0+1_20160421_094539_37-38min.wav"
var resultDir = PathHelper.ResolveAssetPath("SpectrogramTestResults");
var outputAmpSpecImagePath = Path.Combine(resultDir, "AmplitudeSpectrogram.bmp");
var outputDecibelSpecImagePath = Path.Combine(resultDir, "DecibelSpectrogram.bmp");
var outputEnergySpecImagePath = Path.Combine(resultDir, "EnergySpectrogram.bmp");
var outputLogEnergySpecImagePath = Path.Combine(resultDir, "LogEnergySpectrogram.bmp");
var outputLinScaImagePath = Path.Combine(resultDir, "LinearScaleSpectrogram.bmp");
var outputMelScaImagePath = Path.Combine(resultDir, "MelScaleSpectrogram.bmp");
var outputNormalizedImagePath = Path.Combine(resultDir, "NormalizedSpectrogram.bmp");
var outputNoiseReducedImagePath = Path.Combine(resultDir, "NoiseReducedSpectrogram.bmp");
var outputLogPsdImagePath = Path.Combine(resultDir, "Psd.bmp");
var recording = new AudioRecording(recordingPath);
int nyquist = recording.Nyquist; // 11025;
int frameSize = 1024;
int finalBinCount = 512; //256; //128; // 100; // 40; // 200; //
int hertzInterval = 1000;
//FreqScaleType scaleType = FreqScaleType.Linear;
var scaleType = FreqScaleType.Mel;
//var freqScale = new FrequencyScale(scaleType, nyquist, frameSize, finalBinCount, hertzInterval);
//var fst = freqScale.ScaleType;
var settings = new SpectrogramSettings()
{
WindowSize = frameSize,
WindowOverlap = 0.1028,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
MelBinCount = 256, //(scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
//NoiseReductionType = NoiseReductionType.Median,
};
//settings.NoiseReductionParameter = 0.0; // backgroundNeighbourhood noise reduction in dB
settings.SourceFileName = recording.BaseName;
//var sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
var sonogram = new EnergySpectrogram(settings, recording.WavReader);
sonogram.Data = MatrixTools.Matrix2LogValues(sonogram.Data);
var attributes = new SpectrogramAttributes()
{
NyquistFrequency = sonogram.Attributes.NyquistFrequency,
Duration = sonogram.Attributes.Duration,
};
Image image = DecibelSpectrogram.DrawSpectrogramAnnotated(sonogram.Data, settings, attributes);
//image.Save(outputLogEnergySpecImagePath, ImageFormat.Bmp);
//var logSonogramData = MatrixTools.Matrix2LogValues(sonogram.Data);
//var dbSpectrogram = new DecibelSpectrogram(settings, recording.WavReader);
//dbSpectrogram.DrawSpectrogram(outputMelScaImagePath);
//var energySpectro = new EnergySpectrogram(settings, recording.WavReader);
//var image = SpectrogramTools.GetImage(sonogram.Data, nyquist, settings.DoMelScale);
//var specImage = SpectrogramTools.GetImageFullyAnnotated(image, "MELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations, settings.Duration);
//var logSonogramData = MatrixTools.Matrix2LogValues(sonogram.Data);
//var image = SpectrogramTools.GetImage(logSonogramData, nyquist, settings.DoMelScale);
//var specImage = SpectrogramTools.GetImageFullyAnnotated(image, "MELSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations, sonogram.Attributes.Duration);
//specImage.Save(outputMelScaImagePath);
//specImage.Save(outputAmpSpecImagePath);
// DO RMS NORMALIZATION
//sonogram.Data = SNR.RmsNormalization(sonogram.Data);
//energySpectro.Data = SNR.RmsNormalization(energySpectro.Data);
//dbSpectrogram.DrawSpectrogram(outputNormalizedImagePath);
//var image2 = SpectrogramTools.GetImage(dbSpectrogram.Data, nyquist, settings.DoMelScale);
//var normImage = SpectrogramTools.GetImageFullyAnnotated(image2, "NORMALIZEDSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations, sonogram.Attributes.Duration);
//normImage.Save(outputNormalizedImagePath);
// DO NOISE REDUCTION
sonogram.Data = PcaWhitening.NoiseReduction(sonogram.Data);
//dbSpectrogram.DrawSpectrogram(outputNoiseReducedImagePath);
//var image3 = SpectrogramTools.GetImage(dbSpectrogram.Data, nyquist, settings.DoMelScale);
//var noiseReducedImage = SpectrogramTools.GetImageFullyAnnotated(image3, "NOISEREDUCEDSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations, sonogram.Attributes.Duration);
//noiseReducedImage.Save(outputNoiseReducedImagePath);
Image image2 = DecibelSpectrogram.DrawSpectrogramAnnotated(sonogram.Data, settings, attributes);
//image2.Save(outputNoiseReducedImagePath, ImageFormat.Bmp);
//energySpectro.DrawLogPsd(outputLogPsdImagePath);
/*
* var fst = FreqScaleType.Linear;
* var freqScale = new FrequencyScale(fst);
* var recording = new AudioRecording(recordingPath);
*
* var sonoConfig = new SonogramConfig
* {
* WindowSize = freqScale.FinalBinCount * 2,
* WindowOverlap = 0.2,
* SourceFName = recording.BaseName,
* NoiseReductionType = NoiseReductionType.None,
* NoiseReductionParameter = 0.0,
* };
*
* // GENERATE AMPLITUDE SPECTROGRAM
* var amplitudeSpectrogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
* amplitudeSpectrogram.Configuration.WindowSize = freqScale.WindowSize;
*
* var image = amplitudeSpectrogram.GetImageFullyAnnotated(amplitudeSpectrogram.GetImage(), "AmplitudeSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* image.Save(outputAmpSpecImagePath);
*
* // DO RMS NORMALIZATION
* amplitudeSpectrogram.Data = SNR.RmsNormalization(amplitudeSpectrogram.Data);
* var normImage = amplitudeSpectrogram.GetImageFullyAnnotated(amplitudeSpectrogram.GetImage(), "NORMAmplitudeSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* normImage.Save(outputNormAmpImagePath);
*
* // CONVERT NORMALIZED AMPLITUDE SPECTROGRAM TO dB SPECTROGRAM
* var sonogram = new SpectrogramStandard(amplitudeSpectrogram);
* var standImage = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "LinearScaleSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* standImage.Save(outputLinScaImagePath);
*
* // DO NOISE REDUCTION
* sonogram.Data = PcaWhitening.NoiseReduction(sonogram.Data);
* //SNR.NoiseReduce_Standard(sonogram.Data);
* var noiseReducedImage = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "NOISEREDUCEDSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
* noiseReducedImage.Save(outputNoiseReducedImagePath);
*/
}
public static void GenerateSpectrograms()
{
var recordingDir = @"M:\Liz\SupervisedPatchSamplingSet\Recordings\";
var resultDir = @"M:\Liz\SupervisedPatchSamplingSet\";
// check whether there is any file in the folder/subfolders
if (Directory.GetFiles(recordingDir, "*", SearchOption.AllDirectories).Length == 0)
{
throw new ArgumentException("The folder of recordings is empty...");
}
int frameSize = 1024;
int finalBinCount = 256;
FreqScaleType scaleType = FreqScaleType.Mel;
var settings = new SpectrogramSettings()
{
WindowSize = frameSize,
// the duration of each frame (according to the default value (i.e., 1024) of frame size) is 0.04644 seconds
// The question is how many single-frames (i.e., patch height is equal to 1) should be selected to form one second
// The "WindowOverlap" is calculated to answer this question
// each 24 single-frames duration is equal to 1 second
// note that the "WindowOverlap" value should be recalculated if frame size is changed
// this has not yet been considered in the Config file!
WindowOverlap = 0.10725204,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
foreach (string filePath in Directory.GetFiles(recordingDir, "*.wav"))
{
FileInfo fileInfo = filePath.ToFileInfo();
// process the wav file if it is not empty
if (fileInfo.Length != 0)
{
var recording = new AudioRecording(filePath);
settings.SourceFileName = recording.BaseName;
var amplitudeSpectrogram = new AmplitudeSpectrogram(settings, recording.WavReader);
var decibelSpectrogram = new DecibelSpectrogram(amplitudeSpectrogram);
// DO NOISE REDUCTION
decibelSpectrogram.Data = PcaWhitening.NoiseReduction(decibelSpectrogram.Data);
// draw the spectrogram
var attributes = new SpectrogramAttributes()
{
NyquistFrequency = decibelSpectrogram.Attributes.NyquistFrequency,
Duration = decibelSpectrogram.Attributes.Duration,
};
Image image = DecibelSpectrogram.DrawSpectrogramAnnotated(decibelSpectrogram.Data, settings, attributes);
string pathToSpectrogramFiles = Path.Combine(resultDir, "Spectrograms", settings.SourceFileName + ".bmp");
image.Save(pathToSpectrogramFiles);
// write the matrix to a csv file
string pathToMatrixFiles = Path.Combine(resultDir, "Matrices", settings.SourceFileName + ".csv");
Csv.WriteMatrixToCsv(pathToMatrixFiles.ToFileInfo(), decibelSpectrogram.Data);
}
}
}
public void PowerSpectrumDensityTest()
{
var inputPath = @"C:\Users\kholghim\Mahnoosh\Liz\TrainSet\";
var resultPsdPath = @"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\train_LogPSD.bmp";
var resultNoiseReducedPsdPath = @"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\train_LogPSD_NoiseReduced.bmp";
//var inputPath =Path.Combine(inputDir, "TrainSet"); // directory of the one-min recordings of one day (21 and 23 Apr - Black Rail Data)
// check whether there is any file in the folder/subfolders
if (Directory.GetFiles(inputPath, "*", SearchOption.AllDirectories).Length == 0)
{
throw new ArgumentException("The folder of recordings is empty...");
}
// get the nyquist value from the first wav file in the folder of recordings
int nq = new AudioRecording(Directory.GetFiles(inputPath, "*.wav")[0]).Nyquist;
int nyquist = nq; // 11025;
int frameSize = 1024;
int finalBinCount = 512; //256; //
int hertzInterval = 1000;
FreqScaleType scaleType = FreqScaleType.Linear;
//var freqScale = new FrequencyScale(scaleType, nyquist, frameSize, finalBinCount, hertzInterval);
//var fst = freqScale.ScaleType;
//var fst = FreqScaleType.Linear;
//var freqScale = new FrequencyScale(fst);
var settings = new SpectrogramSettings()
{
WindowSize = frameSize,
WindowOverlap = 0.1028,
//DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
//MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
//DoMelScale = false,
MelBinCount = 256,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
//MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var attributes = new SpectrogramAttributes()
{
NyquistFrequency = nyquist,
Duration = TimeSpan.FromMinutes(1440),
};
List <double[]> psd = new List <double[]>();
foreach (string filePath in Directory.GetFiles(inputPath, "*.wav"))
{
FileInfo fileInfo = filePath.ToFileInfo();
// process the wav file if it is not empty
if (fileInfo.Length != 0)
{
var recording = new AudioRecording(filePath);
//var sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
//var amplitudeSpectrogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// save the matrix
// skip normalisation
// skip mel
settings.SourceFileName = recording.BaseName;
var spectrogram = new EnergySpectrogram(settings, recording.WavReader);
//var sonogram = new AmplitudeSpectrogram(settings, recording.WavReader);
//var energySpectrogram = new EnergySpectrogram(sonoConfig, amplitudeSpectrogram.Data);
//var energySpectrogram = new EnergySpectrogram(sonoConfig, recording.WavReader);
//var energySpectrogram = new EnergySpectrogram(settings, recording.WavReader);
// square the FFT coefficients to get an energy spectrogram
// double[,] energySpectrogram = PowerSpectrumDensity.GetEnergyValues(amplitudeSpectrogram.Data);
// RMS NORMALIZATION
//double[,] normalizedValues = SNR.RmsNormalization(energySpectro.Data);
//energySpectro.Data = SNR.RmsNormalization(energySpectro.Data);
// Median Noise Reduction
//spectrogram.Data = PcaWhitening.NoiseReduction(spectrogram.Data);
//spectrogram.Data = SNR.NoiseReduce_Standard(spectrogram.Data);
//double[] psd = PowerSpectralDensity.GetPowerSpectrum(noiseReducedValues);
//psd.Add(energySpectro.GetLogPsd());
psd.Add(MatrixTools.GetColumnAverages(spectrogram.Data));
//psd.Add(SpectrogramTools.CalculateAvgSpectrumFromEnergySpectrogram(normalizedValues));
//psd.Add(PowerSpectralDensity.GetPowerSpectrum(normalizedValues));
}
}
// writing psd matrix to csv file
//Csv.WriteMatrixToCsv(new FileInfo(@"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\psd.csv"), psd.ToArray().ToMatrix());
//Image imagePsd = DecibelSpectrogram.DrawSpectrogramAnnotated(psd.ToArray().ToMatrix(), settings, attributes);
//imagePsd.Save(resultPsdPath, ImageFormat.Bmp);
var psdMatrix = psd.ToArray().ToMatrix();
// calculate the log of matrix
var logPsd = MatrixTools.Matrix2LogValues(psdMatrix);
Csv.WriteMatrixToCsv(new FileInfo(@"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\logPsd.csv"), logPsd);
var image = DecibelSpectrogram.DrawSpectrogramAnnotated(logPsd, settings, attributes);
image.Save(resultPsdPath);
var noiseReducedLogPsd = PcaWhitening.NoiseReduction(logPsd); //SNR.NoiseReduce_Standard(logPsd); //SNR.NoiseReduce_Mean(logPsd, 0.0);//SNR.NoiseReduce_Median(logPsd, 0.0); //
Csv.WriteMatrixToCsv(new FileInfo(@"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\logPsd_NoiseReduced.csv"), logPsd);
var image2 = DecibelSpectrogram.DrawSpectrogramAnnotated(noiseReducedLogPsd, settings, attributes);
image2.Save(resultNoiseReducedPsdPath);
//ImageTools.DrawMatrix(psd.ToArray().ToMatrix(), resultPath);
//ImageTools.DrawReversedMatrix(psd.ToArray().ToMatrix(), resultPath);
//var data = MatrixTools.Matrix2LogValues(psd.ToArray().ToMatrix());
//Image image = ImageTools.DrawReversedMatrixWithoutNormalisation(data);
//Image image = ImageTools.DrawReversedMatrixWithoutNormalisation(logPsd);
}
