public void SonogramDecibelMethodsAreEquivalent()
{
var recording = new AudioRecording(PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav"));
// specfied linear scale
var freqScale = new FrequencyScale(nyquist: 11025, frameSize: 1024, hertzGridInterval: 1000);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.FinalBinCount * 2,
WindowOverlap = 0.2,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
// Method 1
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
var expectedDecibelSonogram = MFCCStuff.DecibelSpectra(sonogram.Data, sonogram.Configuration.WindowPower, sonogram.SampleRate, sonogram.Configuration.epsilon);
// Method 2: make sure that the decibel spectrum is the same no matter which path we take to calculate it.
var actualDecibelSpectrogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
CollectionAssert.That.AreEqual(expectedDecibelSonogram, actualDecibelSpectrogram.Data, EnvelopeAndFftTests.Delta);
}
public static Image <Rgb24> GetLcnSpectrogram(
SonogramConfig sonoConfig,
AudioRecording recordingSegment,
string sourceRecordingName,
double neighbourhoodSeconds,
double lcnContrastLevel)
{
BaseSonogram sonogram = new AmplitudeSonogram(sonoConfig, recordingSegment.WavReader);
int neighbourhoodFrames = (int)(sonogram.FramesPerSecond * neighbourhoodSeconds);
LoggedConsole.WriteLine("LCN: FramesPerSecond (Prior to LCN) = {0}", sonogram.FramesPerSecond);
LoggedConsole.WriteLine("LCN: Neighbourhood of {0} seconds = {1} frames", neighbourhoodSeconds, neighbourhoodFrames);
// subtract the lowest 20% of frames. This is first step in LCN noise removal. Sets the baseline.
const int lowPercentile = 20;
sonogram.Data =
NoiseRemoval_Briggs.NoiseReduction_byLowestPercentileSubtraction(sonogram.Data, lowPercentile);
sonogram.Data =
NoiseRemoval_Briggs.NoiseReduction_byLCNDivision(sonogram.Data, neighbourhoodFrames, lcnContrastLevel);
//Matrix normalisation
//MatrixTools.PercentileCutoffs(sonogram.Data, 10.0, 90, out double minCut, out double maxCut);
//NoiseRemoval_Briggs.NoiseReduction_byLowestPercentileSubtraction(sonogram.Data, lowPercentile);
var image = sonogram.GetImageFullyAnnotated(
"AMPLITUDE SPECTROGRAM with freq bin Local Contrast Normalization - " + sourceRecordingName,
ImageTags[AmplitudeSpectrogramLocalContrastNormalization]);
return(image);
}
public void TestDecibelSpectrogram()
{
var recording = new AudioRecording(PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav"));
// specfied linear scale
var freqScale = new FrequencyScale(nyquist: 11025, frameSize: 1024, hertzGridInterval: 1000);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.FinalBinCount * 2,
WindowOverlap = 0.2,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
// DO EQUALITY TEST on the AMPLITUDE SONGOGRAM DATA
// Do not bother with the image because this is only an amplitude spectrogram.
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// DO FILE EQUALITY TEST on the DECIBEL SONGOGRAM DATA
// Do not bother with the image because this has been tested elsewhere.
var decibelSonogram = MFCCStuff.DecibelSpectra(sonogram.Data, sonogram.Configuration.WindowPower, sonogram.SampleRate, sonogram.Configuration.epsilon);
var expectedFile = PathHelper.ResolveAsset("StandardSonograms", "BAC2_20071008_DecibelSonogramData.EXPECTED.bin");
// run this once to generate expected test data
// uncomment this to update the binary data. Should be rarely needed
// AT: Updated 2017-02-15 because FFT library changed in 864f7a491e2ea0e938161bd390c1c931ecbdf63c
//Binary.Serialize(expectedFile, decibelSonogram);
var expected = Binary.Deserialize <double[, ]>(expectedFile);
CollectionAssert.That.AreEqual(expected, decibelSonogram, EnvelopeAndFftTests.Delta);
}
/// <summary>
/// This method takes an audio recording and returns an octave scale spectrogram.
/// At the present time it only works for recordings with 64000 sample rate and returns a 256 bin sonogram.
/// TODO: generalise this method for other recordings and octave scales.
/// </summary>
public static BaseSonogram ConvertRecordingToOctaveScaleSonogram(AudioRecording recording, FreqScaleType fst)
{
var freqScale = new FrequencyScale(fst);
double windowOverlap = 0.75;
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = windowOverlap,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
// Generate amplitude sonogram and then conver to octave scale
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// THIS IS THE CRITICAL LINE.
// TODO: SHOULD DEVELOP A SEPARATE UNIT TEST for this method
sonogram.Data = ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
sonogram.Data = dataMatrix;
int windowSize = freqScale.FinalBinCount * 2;
sonogram.Configuration.WindowSize = windowSize;
sonogram.Configuration.WindowStep = (int)Math.Round(windowSize * (1 - windowOverlap));
return(sonogram);
}
public void TestFreqScaleOnArtificialSignal1()
{
int sampleRate = 22050;
double duration = 20; // signal duration in seconds
int[] harmonics = { 500, 1000, 2000, 4000, 8000 };
int windowSize = 512;
var freqScale = new FrequencyScale(sampleRate / 2, windowSize, 1000);
var outputImagePath = Path.Combine(this.outputDirectory.FullName, "Signal1_LinearFreqScale.png");
var recording = DspFilters.GenerateTestRecording(sampleRate, duration, harmonics, WaveType.Cosine);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.0,
SourceFName = "Signal1",
NoiseReductionType = NoiseReductionType.Standard,
NoiseReductionParameter = 0.12,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// pick a row, any row
var oneSpectrum = MatrixTools.GetRow(sonogram.Data, 40);
oneSpectrum = DataTools.filterMovingAverage(oneSpectrum, 5);
var peaks = DataTools.GetPeaks(oneSpectrum);
for (int i = 5; i < peaks.Length - 5; i++)
{
if (peaks[i])
{
LoggedConsole.WriteLine($"bin ={freqScale.BinBounds[i, 0]}, Herz={freqScale.BinBounds[i, 1]}-{freqScale.BinBounds[i + 1, 1]} ");
}
}
foreach (int h in harmonics)
{
LoggedConsole.WriteLine($"Harmonic {h}Herz should be in bin {freqScale.GetBinIdForHerzValue(h)}");
}
// spectrogram without framing, annotation etc
var image = sonogram.GetImage();
string title = $"Spectrogram of Harmonics: {DataTools.Array2String(harmonics)} SR={sampleRate} Window={windowSize}";
image = sonogram.GetImageFullyAnnotated(image, title, freqScale.GridLineLocations);
image.Save(outputImagePath);
// Check that image dimensions are correct
Assert.AreEqual(861, image.Width);
Assert.AreEqual(310, image.Height);
Assert.IsTrue(peaks[11]);
Assert.IsTrue(peaks[22]);
Assert.IsTrue(peaks[45]);
Assert.IsTrue(peaks[92]);
Assert.IsTrue(peaks[185]);
}
public static void TestMethod_GenerateSignal1()
{
int sampleRate = 22050;
double duration = 20; // signal duration in seconds
int[] harmonics = { 500, 1000, 2000, 4000, 8000 };
int windowSize = 512;
var freqScale = new FrequencyScale(sampleRate / 2, windowSize, 1000);
string path = @"C:\SensorNetworks\Output\Sonograms\UnitTestSonograms\SineSignal1.png";
var recording = GenerateTestRecording(sampleRate, duration, harmonics, WaveType.Cosine);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.0,
SourceFName = "Signal1",
NoiseReductionType = NoiseReductionType.Standard,
NoiseReductionParameter = 0.12,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// pick a row, any row
var oneSpectrum = MatrixTools.GetRow(sonogram.Data, 40);
oneSpectrum = DataTools.normalise(oneSpectrum);
var peaks = DataTools.GetPeaks(oneSpectrum, 0.5);
for (int i = 2; i < peaks.Length - 2; i++)
{
if (peaks[i])
{
LoggedConsole.WriteLine($"bin ={freqScale.BinBounds[i, 0]}, Herz={freqScale.BinBounds[i, 1]}-{freqScale.BinBounds[i + 1, 1]} ");
}
}
if (peaks[11] && peaks[22] && peaks[45] && peaks[92] && peaks[185])
{
LoggedConsole.WriteSuccessLine("Spectral Peaks found at correct places");
}
else
{
LoggedConsole.WriteErrorLine("Spectral Peaks found at INCORRECT places");
}
foreach (int h in harmonics)
{
LoggedConsole.WriteLine($"Harmonic {h}Herz should be in bin {freqScale.GetBinIdForHerzValue(h)}");
}
// spectrogram without framing, annotation etc
var image = sonogram.GetImage();
string title = $"Spectrogram of Harmonics: {DataTools.Array2String(harmonics)} SR={sampleRate} Window={windowSize}";
image = sonogram.GetImageFullyAnnotated(image, title, freqScale.GridLineLocations);
image.Save(path);
}
public void SonogramDecibelMethodsAreEquivalent()
{
// Method 1
var sonogram = new AmplitudeSonogram(this.sonoConfig, this.recording.WavReader);
var expectedDecibelSonogram = MFCCStuff.DecibelSpectra(sonogram.Data, sonogram.Configuration.WindowPower, sonogram.SampleRate, sonogram.Configuration.epsilon);
// Method 2: make sure that the decibel spectrum is the same no matter which path we take to calculate it.
var actualDecibelSpectrogram = new SpectrogramStandard(this.sonoConfig, this.recording.WavReader);
CollectionAssert.That.AreEqual(expectedDecibelSonogram, actualDecibelSpectrogram.Data, EnvelopeAndFftTests.Delta);
}
/// <summary>
/// METHOD TO CHECK IF Octave FREQ SCALE IS WORKING
/// Check it on standard one minute recording, SR=22050.
/// </summary>
public static void TESTMETHOD_OctaveFrequencyScale1()
{
var recordingPath = @"G:\SensorNetworks\WavFiles\LewinsRail\FromLizZnidersic\Lewinsrail_TasmanIs_Tractor_SM304253_0151119_0640_1minMono.wav";
var outputDir = @"C:\SensorNetworks\Output\LewinsRail\LewinsRail_ThreeCallTypes".ToDirectoryInfo();
//var recordingPath = @"C:\SensorNetworks\SoftwareTests\TestRecordings\BAC\BAC2_20071008-085040.wav";
//var outputDir = @"C:\SensorNetworks\SoftwareTests\TestFrequencyScale".ToDirectoryInfo();
//var expectedResultsDir = Path.Combine(outputDir.FullName, TestTools.ExpectedResultsDir).ToDirectoryInfo();
var outputImagePath = Path.Combine(outputDir.FullName, "octaveFrequencyScale1NoNoiseReduciton.png");
//var opFileStem = "Lewinsrail_TasmanIs_Tractor";
var recording = new AudioRecording(recordingPath);
// default octave scale
var fst = FreqScaleType.Linear125Octaves6Tones30Nyquist11025;
var freqScale = new FrequencyScale(fst);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.75,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
// Generate amplitude sonogram and then conver to octave scale
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
//var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
//sonogram.Data = dataMatrix;
sonogram.Configuration.WindowSize = freqScale.WindowSize;
var image = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "SPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image.Save(outputImagePath);
// DO FILE EQUALITY TEST
//string testName = "test1";
//var expectedTestFile = new FileInfo(Path.Combine(expectedResultsDir.FullName, "FrequencyOctaveScaleTest1.EXPECTED.json"));
//var resultFile = new FileInfo(Path.Combine(outputDir.FullName, opFileStem + "FrequencyOctaveScaleTest1Results.json"));
//Acoustics.Shared.Csv.Csv.WriteMatrixToCsv(resultFile, freqScale.GridLineLocations);
//TestTools.FileEqualityTest(testName, resultFile, expectedTestFile);
LoggedConsole.WriteLine("Completed Octave Frequency Scale test 1");
Console.WriteLine("\n\n");
}
public static Image GetLcnSpectrogram(SonogramConfig sonoConfig, AudioRecording recordingSegment, string sourceRecordingName, double neighbourhoodSeconds, double lcnContrastLevel)
{
BaseSonogram sonogram = new AmplitudeSonogram(sonoConfig, recordingSegment.WavReader);
int neighbourhoodFrames = (int)(sonogram.FramesPerSecond * neighbourhoodSeconds);
LoggedConsole.WriteLine("LCN: FramesPerSecond (Prior to LCN) = {0}", sonogram.FramesPerSecond);
LoggedConsole.WriteLine("LCN: Neighbourhood of {0} seconds = {1} frames", neighbourhoodSeconds, neighbourhoodFrames);
const int lowPercentile = 20;
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLowestPercentileSubtraction(sonogram.Data, lowPercentile);
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLCNDivision(sonogram.Data, neighbourhoodFrames, lcnContrastLevel);
var image = sonogram.GetImageFullyAnnotated("AMPLITUDE SPECTROGRAM with freq bin Local Contrast Normalization - " + sourceRecordingName);
return(image);
}
public void TestAmplitudeSonogram()
{
// DO EQUALITY TEST on the AMPLITUDE SONGOGRAM DATA
// Do not bother with the image because this is only an amplitude spectrogram.
var sonogram = new AmplitudeSonogram(this.sonoConfig, this.recording.WavReader);
var expectedFile = PathHelper.ResolveAsset("StandardSonograms", "BAC2_20071008_AmplSonogramData.EXPECTED.bin");
// run this once to generate expected test data
// uncomment this to update the binary data. Should be rarely needed
// AT: Updated 2017-02-15 because FFT library changed in 864f7a491e2ea0e938161bd390c1c931ecbdf63c
//Binary.Serialize(expectedFile, sonogram.Data);
var expected = Binary.Deserialize <double[, ]>(expectedFile);
CollectionAssert.That.AreEqual(expected, sonogram.Data, EnvelopeAndFftTests.Delta);
}
/// <summary>
/// METHOD TO CHECK IF Octave FREQ SCALE IS WORKING
/// Check it on MARINE RECORDING from JASCO, SR=64000.
/// 24 BIT JASCO RECORDINGS from GBR must be converted to 16 bit.
/// ffmpeg -i source_file.wav -sample_fmt s16 out_file.wav
/// e.g. ". C:\Work\Github\audio-analysis\Extra Assemblies\ffmpeg\ffmpeg.exe" -i "C:\SensorNetworks\WavFiles\MarineRecordings\JascoGBR\AMAR119-00000139.00000139.Chan_1-24bps.1375012796.2013-07-28-11-59-56.wav" -sample_fmt s16 "C:\SensorNetworks\Output\OctaveFreqScale\JascoeMarineGBR116bit.wav"
/// ffmpeg binaries are in C:\Work\Github\audio-analysis\Extra Assemblies\ffmpeg
/// </summary>
public static void TESTMETHOD_OctaveFrequencyScale2()
{
var recordingPath = @"C:\SensorNetworks\SoftwareTests\TestRecordings\MarineJasco_AMAR119-00000139.00000139.Chan_1-24bps.1375012796.2013-07-28-11-59-56-16bit.wav";
var outputDir = @"C:\SensorNetworks\SoftwareTests\TestFrequencyScale".ToDirectoryInfo();
var expectedResultsDir = Path.Combine(outputDir.FullName, TestTools.ExpectedResultsDir).ToDirectoryInfo();
var outputImagePath = Path.Combine(outputDir.FullName, "JascoMarineGBR1.png");
var opFileStem = "JascoMarineGBR1";
var recording = new AudioRecording(recordingPath);
var fst = FreqScaleType.Linear125Octaves7Tones28Nyquist32000;
var freqScale = new FrequencyScale(fst);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.2,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
sonogram.Data = dataMatrix;
sonogram.Configuration.WindowSize = freqScale.WindowSize;
var image = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "SPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image.Save(outputImagePath);
// DO FILE EQUALITY TEST
string testName = "test2";
var expectedTestFile = new FileInfo(Path.Combine(expectedResultsDir.FullName, "FrequencyOctaveScaleTest2.EXPECTED.json"));
var resultFile = new FileInfo(Path.Combine(outputDir.FullName, opFileStem + "FrequencyOctaveScaleTest2Results.json"));
Acoustics.Shared.Csv.Csv.WriteMatrixToCsv(resultFile, freqScale.GridLineLocations);
TestTools.FileEqualityTest(testName, resultFile, expectedTestFile);
LoggedConsole.WriteLine("Completed Octave Frequency Scale " + testName);
Console.WriteLine("\n\n");
}
public void PcaWhiteningDefault()
{
var recordingPath = PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav");
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 spectrogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
spectrogram.Configuration.WindowSize = freqScale.WindowSize;
// DO RMS NORMALIZATION
spectrogram.Data = SNR.RmsNormalization(spectrogram.Data);
// CONVERT NORMALIZED AMPLITUDE SPECTROGRAM TO dB SPECTROGRAM
var sonogram = new SpectrogramStandard(spectrogram);
// DO NOISE REDUCTION
var dataMatrix = PcaWhitening.NoiseReduction(sonogram.Data);
sonogram.Data = dataMatrix;
// DO PCA WHITENING
var whitenedSpectrogram = PcaWhitening.Whitening(sonogram.Data);
// DO UNIT TESTING
// check if the dimensions of the reverted spectrogram (second output of the pca whitening) is equal to the input matrix
Assert.AreEqual(whitenedSpectrogram.Reversion.GetLength(0), sonogram.Data.GetLength(0));
Assert.AreEqual(whitenedSpectrogram.Reversion.GetLength(1), sonogram.Data.GetLength(1));
}
public void OctaveFrequencyScale2()
{
var recordingPath = PathHelper.ResolveAsset(@"Recordings\MarineJasco_AMAR119-00000139.00000139.Chan_1-24bps.1375012796.2013-07-28-11-59-56-16bit-60sec.wav");
var opFileStem = "JascoMarineGBR1";
var outputDir = this.outputDirectory;
var outputImagePath = Path.Combine(this.outputDirectory.FullName, "Octave2ScaleSonogram.png");
var recording = new AudioRecording(recordingPath);
var fst = FreqScaleType.Linear125Octaves7Tones28Nyquist32000;
var freqScale = new FrequencyScale(fst);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.2,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
sonogram.Data = dataMatrix;
sonogram.Configuration.WindowSize = freqScale.WindowSize;
var image = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "SPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image.Save(outputImagePath, ImageFormat.Png);
// DO FILE EQUALITY TESTS
// Check that freqScale.OctaveBinBounds are correct
var stemOfExpectedFile = opFileStem + "_Octave2ScaleBinBounds.EXPECTED.json";
var stemOfActualFile = opFileStem + "_Octave2ScaleBinBounds.ACTUAL.json";
var expectedFile1 = PathHelper.ResolveAsset("FrequencyScale\\" + stemOfExpectedFile);
if (!expectedFile1.Exists)
{
LoggedConsole.WriteErrorLine("An EXPECTED results file does not exist. Test will fail!");
LoggedConsole.WriteErrorLine(
$"If ACTUAL results file is correct, move it to dir `{PathHelper.TestResources}` and change its suffix to <.EXPECTED.json>");
}
var resultFile1 = new FileInfo(Path.Combine(outputDir.FullName, stemOfActualFile));
Json.Serialise(resultFile1, freqScale.BinBounds);
FileEqualityHelpers.TextFileEqual(expectedFile1, resultFile1);
// Check that freqScale.GridLineLocations are correct
stemOfExpectedFile = opFileStem + "_Octave2ScaleGridLineLocations.EXPECTED.json";
stemOfActualFile = opFileStem + "_Octave2ScaleGridLineLocations.ACTUAL.json";
var expectedFile2 = PathHelper.ResolveAsset("FrequencyScale\\" + stemOfExpectedFile);
if (!expectedFile2.Exists)
{
LoggedConsole.WriteErrorLine("An EXPECTED results file does not exist. Test will fail!");
LoggedConsole.WriteErrorLine(
$"If ACTUAL results file is correct, move it to dir `{PathHelper.TestResources}` and change its suffix to <.EXPECTED.json>");
}
var resultFile2 = new FileInfo(Path.Combine(outputDir.FullName, stemOfActualFile));
Json.Serialise(resultFile2, freqScale.GridLineLocations);
FileEqualityHelpers.TextFileEqual(expectedFile2, resultFile2);
// Check that image dimensions are correct
Assert.AreEqual(201, image.Width);
Assert.AreEqual(310, image.Height);
}
public void OctaveFrequencyScale1()
{
var recordingPath = PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav");
var opFileStem = "BAC2_20071008";
var outputDir = this.outputDirectory;
var outputImagePath = Path.Combine(outputDir.FullName, "Octave1ScaleSonogram.png");
var recording = new AudioRecording(recordingPath);
// default octave scale
var fst = FreqScaleType.Linear125Octaves6Tones30Nyquist11025;
var freqScale = new FrequencyScale(fst);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.75,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
// Generate amplitude sonogram and then conver to octave scale
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// THIS IS THE CRITICAL LINE. COULD DO WITH SEPARATE UNIT TEST
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
sonogram.Data = dataMatrix;
sonogram.Configuration.WindowSize = freqScale.WindowSize;
var image = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "SPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image.Save(outputImagePath, ImageFormat.Png);
// DO FILE EQUALITY TESTS
// Check that freqScale.OctaveBinBounds are correct
var stemOfExpectedFile = opFileStem + "_Octave1ScaleBinBounds.EXPECTED.json";
var stemOfActualFile = opFileStem + "_Octave1ScaleBinBounds.ACTUAL.json";
var expectedFile1 = PathHelper.ResolveAsset("FrequencyScale\\" + stemOfExpectedFile);
if (!expectedFile1.Exists)
{
LoggedConsole.WriteErrorLine("An EXPECTED results file does not exist. Test will fail!");
LoggedConsole.WriteErrorLine(
$"If ACTUAL results file is correct, move it to dir `{PathHelper.TestResources}` and change its suffix to <.EXPECTED.json>");
}
var resultFile1 = new FileInfo(Path.Combine(outputDir.FullName, stemOfActualFile));
Json.Serialise(resultFile1, freqScale.BinBounds);
FileEqualityHelpers.TextFileEqual(expectedFile1, resultFile1);
// Check that freqScale.GridLineLocations are correct
stemOfExpectedFile = opFileStem + "_Octave1ScaleGridLineLocations.EXPECTED.json";
stemOfActualFile = opFileStem + "_Octave1ScaleGridLineLocations.ACTUAL.json";
var expectedFile2 = PathHelper.ResolveAsset("FrequencyScale\\" + stemOfExpectedFile);
if (!expectedFile2.Exists)
{
LoggedConsole.WriteErrorLine("An EXPECTED results file does not exist. Test will fail!");
LoggedConsole.WriteErrorLine(
$"If ACTUAL results file is correct, move it to dir `{PathHelper.TestResources}` and change its suffix to <.EXPECTED.json>");
}
var resultFile2 = new FileInfo(Path.Combine(outputDir.FullName, stemOfActualFile));
Json.Serialise(resultFile2, freqScale.GridLineLocations);
FileEqualityHelpers.TextFileEqual(expectedFile2, resultFile2);
// Check that image dimensions are correct
Assert.AreEqual(645, image.Width);
Assert.AreEqual(310, image.Height);
}
public void TestPcaWhitening()
{
var recordingPath = PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav");
var outputDir = this.outputDirectory;
var outputImagePath = Path.Combine(outputDir.FullName, "ReconstrcutedSpectrogram.png");
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 spectrogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
spectrogram.Configuration.WindowSize = freqScale.WindowSize;
// DO RMS NORMALIZATION
spectrogram.Data = SNR.RmsNormalization(spectrogram.Data);
// CONVERT NORMALIZED AMPLITUDE SPECTROGRAM TO dB SPECTROGRAM
var sonogram = new SpectrogramStandard(spectrogram);
// DO NOISE REDUCTION
var dataMatrix = PcaWhitening.NoiseReduction(sonogram.Data);
sonogram.Data = dataMatrix;
// Do Patch Sampling
int rows = sonogram.Data.GetLength(0);
int columns = sonogram.Data.GetLength(1);
int patchWidth = columns;
int patchHeight = 1;
int numberOfPatches = (rows / patchHeight) * (columns / patchWidth);
var sequentialPatches = PatchSampling.GetPatches(sonogram.Data, patchWidth, patchHeight, numberOfPatches, PatchSampling.SamplingMethod.Sequential);
double[,] sequentialPatchMatrix = sequentialPatches.ToMatrix();
// DO PCA WHITENING
var whitenedSpectrogram = PcaWhitening.Whitening(sequentialPatchMatrix);
// reconstructing the spectrogram from sequential patches and the projection matrix obtained from random patches
var projectionMatrix = whitenedSpectrogram.ProjectionMatrix;//whitenedSpectrogram.projectionMatrix;
var eigenVectors = whitenedSpectrogram.EigenVectors;
var numComponents = whitenedSpectrogram.Components;
double[,] reconstructedSpec = PcaWhitening.ReconstructSpectrogram(projectionMatrix, sequentialPatchMatrix, eigenVectors, numComponents);
sonogram.Data = PatchSampling.ConvertPatches(reconstructedSpec, patchWidth, patchHeight, columns);
var reconstructedSpecImage = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "RECONSTRUCTEDSPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
reconstructedSpecImage.Save(outputImagePath, ImageFormat.Png);
// DO UNIT TESTING
Assert.AreEqual(spectrogram.Data.GetLength(0), sonogram.Data.GetLength(0));
Assert.AreEqual(spectrogram.Data.GetLength(1), sonogram.Data.GetLength(1));
}
public static void Main(Arguments arguments)
{
// 1. set up the necessary files
FileInfo sourceRecording = arguments.Source;
FileInfo configFile = arguments.Config.ToFileInfo();
DirectoryInfo opDir = arguments.Output;
opDir.Create();
if (arguments.StartOffset.HasValue ^ arguments.EndOffset.HasValue)
{
throw new InvalidStartOrEndException("If StartOffset or EndOffset is specified, then both must be specified");
}
var offsetsProvided = arguments.StartOffset.HasValue && arguments.EndOffset.HasValue;
// set default offsets - only use defaults if not provided in argments list
TimeSpan?startOffset = null;
TimeSpan?endOffset = null;
if (offsetsProvided)
{
startOffset = TimeSpan.FromSeconds(arguments.StartOffset.Value);
endOffset = TimeSpan.FromSeconds(arguments.EndOffset.Value);
}
const string Title = "# MAKE A SONOGRAM FROM AUDIO RECORDING and do OscillationsGeneric activity.";
string date = "# DATE AND TIME: " + DateTime.Now;
LoggedConsole.WriteLine(Title);
LoggedConsole.WriteLine(date);
LoggedConsole.WriteLine("# Input audio file: " + sourceRecording.Name);
string sourceName = Path.GetFileNameWithoutExtension(sourceRecording.FullName);
// 2. get the config dictionary
Config configuration = ConfigFile.Deserialize(configFile);
// below three lines are examples of retrieving info from Config config
// string analysisIdentifier = configuration[AnalysisKeys.AnalysisName];
// bool saveIntermediateWavFiles = (bool?)configuration[AnalysisKeys.SaveIntermediateWavFiles] ?? false;
// scoreThreshold = (double?)configuration[AnalysisKeys.EventThreshold] ?? scoreThreshold;
// Resample rate must be 2 X the desired Nyquist. Default is that of recording.
var resampleRate = configuration.GetIntOrNull(AnalysisKeys.ResampleRate) ?? AppConfigHelper.DefaultTargetSampleRate;
var configDict = new Dictionary <string, string>(configuration.ToDictionary());
// #NOISE REDUCTION PARAMETERS
//string noisereduce = configDict[ConfigKeys.Mfcc.Key_NoiseReductionType];
configDict[AnalysisKeys.NoiseDoReduction] = "false";
configDict[AnalysisKeys.NoiseReductionType] = "NONE";
configDict[AnalysisKeys.AddAxes] = configuration[AnalysisKeys.AddAxes] ?? "true";
configDict[AnalysisKeys.AddSegmentationTrack] = configuration[AnalysisKeys.AddSegmentationTrack] ?? "true";
configDict[ConfigKeys.Recording.Key_RecordingCallName] = sourceRecording.FullName;
configDict[ConfigKeys.Recording.Key_RecordingFileName] = sourceRecording.Name;
configDict[AnalysisKeys.AddTimeScale] = configuration[AnalysisKeys.AddTimeScale] ?? "true";
configDict[AnalysisKeys.AddAxes] = configuration[AnalysisKeys.AddAxes] ?? "true";
configDict[AnalysisKeys.AddSegmentationTrack] = configuration[AnalysisKeys.AddSegmentationTrack] ?? "true";
// ####################################################################
// print out the sonogram parameters
LoggedConsole.WriteLine("\nPARAMETERS");
foreach (KeyValuePair <string, string> kvp in configDict)
{
LoggedConsole.WriteLine("{0} = {1}", kvp.Key, kvp.Value);
}
LoggedConsole.WriteLine("Sample Length for detecting oscillations = {0}", SampleLength);
// 3: GET RECORDING
FileInfo tempAudioSegment = new FileInfo(Path.Combine(opDir.FullName, "tempWavFile.wav"));
// delete the temp audio file if it already exists.
if (File.Exists(tempAudioSegment.FullName))
{
File.Delete(tempAudioSegment.FullName);
}
// This line creates a temporary version of the source file downsampled as per entry in the config file
MasterAudioUtility.SegmentToWav(sourceRecording, tempAudioSegment, new AudioUtilityRequest()
{
TargetSampleRate = resampleRate
});
// 1) get amplitude spectrogram
AudioRecording recordingSegment = new AudioRecording(tempAudioSegment.FullName);
SonogramConfig sonoConfig = new SonogramConfig(configDict); // default values config
BaseSonogram sonogram = new AmplitudeSonogram(sonoConfig, recordingSegment.WavReader);
Console.WriteLine("FramesPerSecond = {0}", sonogram.FramesPerSecond);
// remove the DC bin
sonogram.Data = MatrixTools.Submatrix(sonogram.Data, 0, 1, sonogram.FrameCount - 1, sonogram.Configuration.FreqBinCount);
// ###############################################################
// DO LocalContrastNormalisation
//int fieldSize = 9;
//sonogram.Data = LocalContrastNormalisation.ComputeLCN(sonogram.Data, fieldSize);
// LocalContrastNormalisation over frequency bins is better and faster.
int neighbourhood = 15;
double contrastLevel = 0.5;
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLCNDivision(sonogram.Data, neighbourhood, contrastLevel);
// ###############################################################
// lowering the sensitivity threshold increases the number of hits.
if (configDict.ContainsKey(AnalysisKeys.OscilDetection2014SensitivityThreshold))
{
Oscillations2014.DefaultSensitivityThreshold = double.Parse(configDict[AnalysisKeys.OscilDetection2014SensitivityThreshold]);
}
if (configDict.ContainsKey(AnalysisKeys.OscilDetection2014SampleLength))
{
Oscillations2014.DefaultSampleLength = int.Parse(configDict[AnalysisKeys.OscilDetection2014SensitivityThreshold]);
}
var list1 = new List <Image>();
//var result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, 64, "Autocorr-FFT");
//list1.Add(result.FreqOscillationImage);
var result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, "Autocorr-FFT");
list1.Add(result.FreqOscillationImage);
result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, "Autocorr-SVD-FFT");
list1.Add(result.FreqOscillationImage);
result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, "Autocorr-WPD");
list1.Add(result.FreqOscillationImage);
Image compositeOscImage1 = ImageTools.CombineImagesInLine(list1.ToArray());
// ###############################################################
// init the sonogram image stack
var sonogramList = new List <Image>();
var image = sonogram.GetImageFullyAnnotated("AMPLITUDE SPECTROGRAM");
sonogramList.Add(image);
//string testPath = @"C:\SensorNetworks\Output\Sonograms\amplitudeSonogram.png";
//image.Save(testPath, ImageFormat.Png);
Image envelopeImage = ImageTrack.DrawWaveEnvelopeTrack(recordingSegment, image.Width);
sonogramList.Add(envelopeImage);
// 2) now draw the standard decibel spectrogram
sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
// ###############################################################
list1 = new List <Image>();
//result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, 64, "Autocorr-FFT");
//list1.Add(result.FreqOscillationImage);
result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, "Autocorr-FFT");
list1.Add(result.FreqOscillationImage);
result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, "Autocorr-SVD-FFT");
list1.Add(result.FreqOscillationImage);
result = Oscillations2014.GetFreqVsOscillationsDataAndImage(sonogram, "Autocorr-WPD");
list1.Add(result.FreqOscillationImage);
Image compositeOscImage2 = ImageTools.CombineImagesInLine(list1.ToArray());
// ###############################################################
//image = sonogram.GetImageFullyAnnotated("DECIBEL SPECTROGRAM");
//list.Add(image);
// combine eight images
list1 = new List <Image>();
list1.Add(compositeOscImage1);
list1.Add(compositeOscImage2);
Image compositeOscImage3 = ImageTools.CombineImagesVertically(list1.ToArray());
string imagePath3 = Path.Combine(opDir.FullName, sourceName + "_freqOscilMatrix.png");
compositeOscImage3.Save(imagePath3, ImageFormat.Png);
Image segmentationImage = ImageTrack.DrawSegmentationTrack(
sonogram,
EndpointDetectionConfiguration.K1Threshold,
EndpointDetectionConfiguration.K2Threshold,
image.Width);
sonogramList.Add(segmentationImage);
// 3) now draw the noise reduced decibel spectrogram
sonoConfig.NoiseReductionType = NoiseReductionType.Standard;
sonoConfig.NoiseReductionParameter = configuration.GetDoubleOrNull(AnalysisKeys.NoiseBgThreshold) ?? 3.0;
sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
image = sonogram.GetImageFullyAnnotated("NOISE-REDUCED DECIBEL SPECTROGRAM");
sonogramList.Add(image);
// ###############################################################
// deriving osscilation graph from this noise reduced spectrogram did not work well
//Oscillations2014.SaveFreqVsOscillationsDataAndImage(sonogram, sampleLength, algorithmName, opDir);
// ###############################################################
Image compositeSonogram = ImageTools.CombineImagesVertically(sonogramList);
string imagePath2 = Path.Combine(opDir.FullName, sourceName + ".png");
compositeSonogram.Save(imagePath2, ImageFormat.Png);
LoggedConsole.WriteLine("\n##### FINISHED FILE ###################################################\n");
}
public static AudioToSonogramResult GenerateFourSpectrogramImages(
FileInfo sourceRecording,
FileInfo path2SoxSpectrogram,
Dictionary <string, string> configDict,
bool dataOnly = false,
bool makeSoxSonogram = false)
{
var result = new AudioToSonogramResult();
if (dataOnly && makeSoxSonogram)
{
throw new ArgumentException("Can't produce data only for a SoX sonogram");
}
if (makeSoxSonogram)
{
SpectrogramTools.MakeSonogramWithSox(sourceRecording, configDict, path2SoxSpectrogram);
result.Path2SoxImage = path2SoxSpectrogram;
}
else if (dataOnly)
{
var recordingSegment = new AudioRecording(sourceRecording.FullName);
var sonoConfig = new SonogramConfig(configDict); // default values config
// disable noise removal
sonoConfig.NoiseReductionType = NoiseReductionType.None;
Log.Warn("Noise removal disabled!");
var sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
result.DecibelSpectrogram = sonogram;
}
else
{
// init the image stack
var list = new List <Image>();
// IMAGE 1) draw amplitude spectrogram
var recordingSegment = new AudioRecording(sourceRecording.FullName);
var sonoConfig = new SonogramConfig(configDict); // default values config
// disable noise removal for first two spectrograms
var disabledNoiseReductionType = sonoConfig.NoiseReductionType;
sonoConfig.NoiseReductionType = NoiseReductionType.None;
BaseSonogram sonogram = new AmplitudeSonogram(sonoConfig, recordingSegment.WavReader);
// remove the DC bin if it has not already been removed.
// Assume test of divisible by 2 is good enough.
int binCount = sonogram.Data.GetLength(1);
if (!binCount.IsEven())
{
sonogram.Data = MatrixTools.Submatrix(sonogram.Data, 0, 1, sonogram.FrameCount - 1, binCount - 1);
}
//save spectrogram data at this point - prior to noise reduction
var spectrogramDataBeforeNoiseReduction = sonogram.Data;
const double neighbourhoodSeconds = 0.25;
int neighbourhoodFrames = (int)(sonogram.FramesPerSecond * neighbourhoodSeconds);
const double lcnContrastLevel = 0.001;
LoggedConsole.WriteLine("LCN: FramesPerSecond (Prior to LCN) = {0}", sonogram.FramesPerSecond);
LoggedConsole.WriteLine("LCN: Neighbourhood of {0} seconds = {1} frames", neighbourhoodSeconds, neighbourhoodFrames);
const int lowPercentile = 20;
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLowestPercentileSubtraction(sonogram.Data, lowPercentile);
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLCNDivision(sonogram.Data, neighbourhoodFrames, lcnContrastLevel);
//sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLowestPercentileSubtraction(sonogram.Data, lowPercentile);
var image = sonogram.GetImageFullyAnnotated("AMPLITUDE SPECTROGRAM + Bin LCN (Local Contrast Normalisation)");
list.Add(image);
//string path2 = @"C:\SensorNetworks\Output\Sonograms\dataInput2.png";
//Histogram.DrawDistributionsAndSaveImage(sonogram.Data, path2);
// double[,] matrix = sonogram.Data;
double[,] matrix = ImageTools.WienerFilter(sonogram.Data, 3);
double ridgeThreshold = 0.25;
byte[,] hits = RidgeDetection.Sobel5X5RidgeDetectionExperiment(matrix, ridgeThreshold);
hits = RidgeDetection.JoinDisconnectedRidgesInMatrix(hits, matrix, ridgeThreshold);
image = SpectrogramTools.CreateFalseColourAmplitudeSpectrogram(spectrogramDataBeforeNoiseReduction, null, hits);
image = sonogram.GetImageAnnotatedWithLinearHerzScale(image, "AMPLITUDE SPECTROGRAM + LCN + ridge detection");
list.Add(image);
Image envelopeImage = ImageTrack.DrawWaveEnvelopeTrack(recordingSegment, image.Width);
list.Add(envelopeImage);
// IMAGE 2) now draw the standard decibel spectrogram
sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
result.DecibelSpectrogram = (SpectrogramStandard)sonogram;
image = sonogram.GetImageFullyAnnotated("DECIBEL SPECTROGRAM");
list.Add(image);
Image segmentationImage = ImageTrack.DrawSegmentationTrack(
sonogram,
EndpointDetectionConfiguration.K1Threshold,
EndpointDetectionConfiguration.K2Threshold,
image.Width);
list.Add(segmentationImage);
// keep the sonogram data for later use
double[,] dbSpectrogramData = (double[, ])sonogram.Data.Clone();
// 3) now draw the noise reduced decibel spectrogram
// #NOISE REDUCTION PARAMETERS - restore noise reduction ##################################################################
sonoConfig.NoiseReductionType = disabledNoiseReductionType;
sonoConfig.NoiseReductionParameter = double.Parse(configDict[AnalysisKeys.NoiseBgThreshold] ?? "2.0");
// #NOISE REDUCTION PARAMETERS - MARINE HACK ##################################################################
//sonoConfig.NoiseReductionType = NoiseReductionType.FIXED_DYNAMIC_RANGE;
//sonoConfig.NoiseReductionParameter = 80.0;
sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
image = sonogram.GetImageFullyAnnotated("DECIBEL SPECTROGRAM + Lamel noise subtraction");
list.Add(image);
// keep the sonogram data for later use
double[,] nrSpectrogramData = sonogram.Data;
// 4) A FALSE-COLOUR VERSION OF SPECTROGRAM
// ########################### SOBEL ridge detection
ridgeThreshold = 3.5;
matrix = ImageTools.WienerFilter(dbSpectrogramData, 3);
hits = RidgeDetection.Sobel5X5RidgeDetectionExperiment(matrix, ridgeThreshold);
// ########################### EIGEN ridge detection
//double ridgeThreshold = 6.0;
//double dominanceThreshold = 0.7;
//var rotatedData = MatrixTools.MatrixRotate90Anticlockwise(dbSpectrogramData);
//byte[,] hits = RidgeDetection.StructureTensorRidgeDetection(rotatedData, ridgeThreshold, dominanceThreshold);
//hits = MatrixTools.MatrixRotate90Clockwise(hits);
// ########################### EIGEN ridge detection
image = SpectrogramTools.CreateFalseColourDecibelSpectrogram(dbSpectrogramData, nrSpectrogramData, hits);
image = sonogram.GetImageAnnotatedWithLinearHerzScale(image, "DECIBEL SPECTROGRAM - Colour annotated");
list.Add(image);
// 5) TODO: ONE OF THESE YEARS FIX UP THE CEPTRAL SONOGRAM
////SpectrogramCepstral cepgram = new SpectrogramCepstral((AmplitudeSonogram)amplitudeSpg);
////var mti3 = SpectrogramTools.Sonogram2MultiTrackImage(sonogram, configDict);
////var image3 = mti3.GetImage();
////image3.Save(fiImage.FullName + "3", ImageFormat.Png);
// 6) COMBINE THE SPECTROGRAM IMAGES
result.CompositeImage = ImageTools.CombineImagesVertically(list);
}
return(result);
}
public void OctaveFrequencyScale2()
{
var recordingPath = PathHelper.ResolveAsset("Recordings", "MarineJasco_AMAR119-00000139.00000139.Chan_1-24bps.1375012796.2013-07-28-11-59-56-16bit-60sec.wav");
var opFileStem = "JascoMarineGBR1";
var outputDir = this.outputDirectory;
var outputImagePath = Path.Combine(this.outputDirectory.FullName, "Octave2ScaleSonogram.png");
var recording = new AudioRecording(recordingPath);
var fst = FreqScaleType.Linear125Octaves7Tones28Nyquist32000;
var freqScale = new FrequencyScale(fst);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.2,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
sonogram.Data = dataMatrix;
sonogram.Configuration.WindowSize = freqScale.WindowSize;
var image = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "SPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image.Save(outputImagePath);
// DO FILE EQUALITY TESTS
// Check that freqScale.OctaveBinBounds are correct
var expectedBinBoundsFile = PathHelper.ResolveAsset("FrequencyScale", opFileStem + "_Octave2ScaleBinBounds.EXPECTED.json");
var expectedBinBounds = Json.Deserialize <int[, ]>(expectedBinBoundsFile);
Assert.That.MatricesAreEqual(expectedBinBounds, freqScale.BinBounds);
// Check that freqScale.GridLineLocations are correct
var expected = new[, ]
{
{ 34, 125 },
{ 62, 250 },
{ 89, 500 },
{ 117, 1000 },
{ 145, 2000 },
{ 173, 4000 },
{ 201, 8000 },
{ 229, 16000 },
{ 256, 32000 },
};
Assert.That.MatricesAreEqual(expected, freqScale.GridLineLocations);
// Check that image dimensions are correct
Assert.AreEqual(201, image.Width);
Assert.AreEqual(310, image.Height);
}
public void OctaveFrequencyScale1()
{
var recordingPath = PathHelper.ResolveAsset("Recordings", "BAC2_20071008-085040.wav");
var opFileStem = "BAC2_20071008";
var outputDir = this.outputDirectory;
var outputImagePath = Path.Combine(outputDir.FullName, "Octave1ScaleSonogram.png");
var recording = new AudioRecording(recordingPath);
// default octave scale
var fst = FreqScaleType.Linear125Octaves6Tones30Nyquist11025;
var freqScale = new FrequencyScale(fst);
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.75,
SourceFName = recording.BaseName,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
// Generate amplitude sonogram and then conver to octave scale
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// THIS IS THE CRITICAL LINE. COULD DO WITH SEPARATE UNIT TEST
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// DO NOISE REDUCTION
var dataMatrix = SNR.NoiseReduce_Standard(sonogram.Data);
sonogram.Data = dataMatrix;
sonogram.Configuration.WindowSize = freqScale.WindowSize;
var image = sonogram.GetImageFullyAnnotated(sonogram.GetImage(), "SPECTROGRAM: " + fst.ToString(), freqScale.GridLineLocations);
image.Save(outputImagePath);
#pragma warning disable SA1500 // Braces for multi-line statements should not share line
var expectedBinBounds = new[, ]
{
{ 0, 0 }, { 1, 3 }, { 2, 5 }, { 3, 8 }, { 4, 11 }, { 5, 13 }, { 6, 16 }, { 7, 19 }, { 8, 22 },
{ 9, 24 }, { 10, 27 }, { 11, 30 }, { 12, 32 }, { 13, 35 }, { 14, 38 }, { 15, 40 }, { 16, 43 },
{ 17, 46 }, { 18, 48 }, { 19, 51 }, { 20, 54 }, { 21, 57 }, { 22, 59 }, { 23, 62 }, { 24, 65 },
{ 25, 67 }, { 26, 70 }, { 27, 73 }, { 28, 75 }, { 29, 78 }, { 30, 81 }, { 31, 83 }, { 32, 86 },
{ 33, 89 }, { 34, 92 }, { 35, 94 }, { 36, 97 }, { 37, 100 }, { 38, 102 }, { 39, 105 }, { 40, 108 },
{ 41, 110 }, { 42, 113 }, { 43, 116 }, { 44, 118 }, { 45, 121 }, { 46, 124 }, { 47, 127 }, { 48, 129 },
{ 49, 132 }, { 50, 135 }, { 51, 137 }, { 52, 140 }, { 53, 143 }, { 55, 148 }, { 56, 151 }, { 57, 153 },
{ 58, 156 }, { 59, 159 }, { 61, 164 }, { 62, 167 }, { 63, 170 }, { 65, 175 }, { 66, 178 }, { 68, 183 },
{ 69, 186 }, { 71, 191 }, { 72, 194 }, { 74, 199 }, { 75, 202 }, { 77, 207 }, { 79, 213 }, { 80, 215 },
{ 82, 221 }, { 84, 226 }, { 86, 231 }, { 88, 237 }, { 89, 240 }, { 91, 245 }, { 93, 250 }, { 95, 256 },
{ 97, 261 }, { 100, 269 }, { 102, 275 }, { 104, 280 }, { 106, 285 }, { 109, 293 }, { 111, 299 },
{ 113, 304 }, { 116, 312 }, { 118, 318 }, { 121, 326 }, { 124, 334 }, { 126, 339 }, { 129, 347 },
{ 132, 355 }, { 135, 363 }, { 138, 371 }, { 141, 380 }, { 144, 388 }, { 147, 396 }, { 150, 404 },
{ 153, 412 }, { 157, 423 }, { 160, 431 }, { 164, 441 }, { 167, 450 }, { 171, 460 }, { 175, 471 },
{ 178, 479 }, { 182, 490 }, { 186, 501 }, { 190, 511 }, { 194, 522 }, { 199, 536 }, { 203, 546 },
{ 208, 560 }, { 212, 571 }, { 217, 584 }, { 221, 595 }, { 226, 608 }, { 231, 622 }, { 236, 635 },
{ 241, 649 }, { 247, 665 }, { 252, 678 }, { 258, 694 }, { 263, 708 }, { 269, 724 }, { 275, 740 },
{ 281, 756 }, { 287, 773 }, { 293, 789 }, { 300, 807 }, { 306, 824 }, { 313, 842 }, { 320, 861 },
{ 327, 880 }, { 334, 899 }, { 341, 918 }, { 349, 939 }, { 356, 958 }, { 364, 980 }, { 372, 1001 },
{ 380, 1023 }, { 388, 1044 }, { 397, 1069 }, { 406, 1093 }, { 415, 1117 }, { 424, 1141 }, { 433, 1165 },
{ 442, 1190 }, { 452, 1217 }, { 462, 1244 }, { 472, 1270 }, { 482, 1297 }, { 493, 1327 }, { 504, 1357 },
{ 515, 1386 }, { 526, 1416 }, { 537, 1445 }, { 549, 1478 }, { 561, 1510 }, { 573, 1542 }, { 586, 1577 },
{ 599, 1612 }, { 612, 1647 }, { 625, 1682 }, { 639, 1720 }, { 653, 1758 }, { 667, 1795 }, { 682, 1836 },
{ 697, 1876 }, { 712, 1916 }, { 728, 1960 }, { 744, 2003 }, { 760, 2046 }, { 776, 2089 }, { 793, 2134 },
{ 811, 2183 }, { 829, 2231 }, { 847, 2280 }, { 865, 2328 }, { 884, 2379 }, { 903, 2431 }, { 923, 2484 },
{ 943, 2538 }, { 964, 2595 }, { 985, 2651 }, { 1007, 2710 }, { 1029, 2770 }, { 1051, 2829 },
{ 1074, 2891 }, { 1098, 2955 }, { 1122, 3020 }, { 1146, 3085 }, { 1172, 3155 }, { 1197, 3222 },
{ 1223, 3292 }, { 1250, 3365 }, { 1278, 3440 }, { 1305, 3513 }, { 1334, 3591 }, { 1363, 3669 },
{ 1393, 3749 }, { 1424, 3833 }, { 1455, 3916 }, { 1487, 4002 }, { 1519, 4089 }, { 1552, 4177 },
{ 1586, 4269 }, { 1621, 4363 }, { 1657, 4460 }, { 1693, 4557 }, { 1730, 4657 }, { 1768, 4759 },
{ 1806, 4861 }, { 1846, 4969 }, { 1886, 5076 }, { 1928, 5190 }, { 1970, 5303 }, { 2013, 5418 },
{ 2057, 5537 }, { 2102, 5658 }, { 2148, 5782 }, { 2195, 5908 }, { 2243, 6037 }, { 2292, 6169 },
{ 2343, 6307 }, { 2394, 6444 }, { 2446, 6584 }, { 2500, 6729 }, { 2555, 6877 }, { 2610, 7025 },
{ 2668, 7181 }, { 2726, 7337 }, { 2786, 7499 }, { 2847, 7663 }, { 2909, 7830 }, { 2973, 8002 },
{ 3038, 8177 }, { 3104, 8355 }, { 3172, 8538 }, { 3242, 8726 }, { 3313, 8917 }, { 3385, 9111 },
{ 3459, 9310 }, { 3535, 9515 }, { 3612, 9722 }, { 3691, 9935 }, { 3772, 10153 }, { 3855, 10376 },
{ 3939, 10602 }, { 4026, 10837 }, { 4095, 11022 },
{ 4095, 11022 },
};
#pragma warning restore SA1500 // Braces for multi-line statements should not share line
Assert.That.MatricesAreEqual(expectedBinBounds, freqScale.BinBounds);
// Check that freqScale.GridLineLocations are correct
var expected = new[, ]
{
{ 46, 125 },
{ 79, 250 },
{ 111, 500 },
{ 143, 1000 },
{ 175, 2000 },
{ 207, 4000 },
{ 239, 8000 },
};
Assert.That.MatricesAreEqual(expected, freqScale.GridLineLocations);
// Check that image dimensions are correct
Assert.AreEqual(645, image.Width);
Assert.AreEqual(310, image.Height);
}
public static void Execute(Arguments arguments)
{
// this is a generic command for testing
// input should be only one-minute wav file
// read in the config file
// pass the config to the algorithm
// output the results
var configPath = @"SpectralPeakTrackingConfig.yml";
var recordingPath = @"";
var imagePath = @"";
var configFile = configPath.ToFileInfo();
if (configFile == null)
{
throw new FileNotFoundException("No config file argument provided");
}
else if (!configFile.Exists)
{
throw new ArgumentException($"Config file {configFile.FullName} not found");
}
var configuration = ConfigFile.Deserialize <SpectralPeakTrackingConfig>(configFile);
var recording = new AudioRecording(recordingPath);
// get the nyquist value from the recording
int nyquist = new AudioRecording(recordingPath).Nyquist;
int frameSize = configuration.FrameWidth;
double frameOverlap = configuration.FrameOverlap;
int finalBinCount = 512;
var hertzPerFreqBin = nyquist / finalBinCount;
FreqScaleType scaleType = FreqScaleType.Linear;
var sonoConfig = new SonogramConfig
{
WindowSize = frameSize,
WindowOverlap = frameOverlap,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
};
//var sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
var amplitudeSpectrogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// Broken in merge b7e03070a9cd72ab0632789a3412967a6cc54cd6
//var energySpectrogram = new EnergySpectrogram(amplitudeSpectrogram);
var decibelSpectrogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
double frameStepSize = sonoConfig.GetFrameOffset();
double stepDuration = frameStepSize / (nyquist * 2);
// Noise Reduction to be added
//var output = SpectralPeakTracking2018.SpectralPeakTracking(energySpectrogram.Data, configuration.SptSettings, hertzPerFreqBin);
// draw the local peaks
//double[,] hits = SpectralPeakTracking2018.MakeHitMatrix(energySpectrogram.Data, output.TargetPeakBinsIndex, output.BandIndex);
//var image = SpectralPeakTracking2018.DrawSonogram(decibelSpectrogram, hits);
//image.Save(imagePath, ImageFormat.Bmp);
}
public static void Execute(Arguments arguments)
{
if (arguments == null)
{
throw new InvalidOperationException();
}
string title = "# DETECT FROG RIBBIT.";
string date = "# DATE AND TIME: " + DateTime.Now;
Log.WriteLine(title);
Log.WriteLine(date);
// SET VERBOSITY
Log.Verbosity = 1;
//i: Set up the file names
//string outputDir = Path.GetDirectoryName(iniPath) + "\\";
//ii: READ PARAMETER VALUES FROM INI FILE
//var config = new Configuration(iniPath);
//Dictionary<string, string> dict = config.GetTable();
//string sourceFile = dict[FeltTemplate_Create.key_SOURCE_RECORDING];
//string sourceDir = dict[FeltTemplate_Create.key_SOURCE_DIRECTORY];
//double dB_Threshold = Double.Parse(dict[FeltTemplate_Create.key_DECIBEL_THRESHOLD]);
//double maxTemplateIntensity = Double.Parse(dict[FeltTemplate_Create.key_TEMPLATE_MAX_INTENSITY]);
//int neighbourhood = Int32.Parse(dict[FeltTemplate_Create.key_DONT_CARE_NH]); //the do not care neighbourhood
//int lineLength = Int32.Parse(dict[FeltTemplate_Create.key_LINE_LENGTH]);
//double templateThreshold = dB_Threshold / maxTemplateIntensity;
//int bitmapThreshold = (int)(255 - (templateThreshold * 255));
//IMPORTANT NOTE:
// You must determine a value for the variable maxOscilScore. This is used to normalize the oscillation scores so that lie in 0,1.
// The default Value = 60.0; but it must be determined for each species.
// This is obtained from the score on training data.
// Find the relevant commented Code in the FrogRibbitRecognizer() method.
string frogName; //, filterName;
//double windowDuration, windowOverlap, dctDuration, dctThreshold,
int midBandFreq; //, minOscilRate, maxOscilRate;
//bool normaliseDCT = false;
//i: GET RECORDING
AudioRecording recording = new AudioRecording(arguments.Source.FullName);
var scores = new List <double[]>();
Log.WriteLine("# Scan Audio Recording: " + arguments.Source.FullName);
//############### Buffo sp. - CANE TOAD #########################################################################
frogName = "Cane_toad";
Log.WriteLine("# Do Recognizer:- " + frogName);
midBandFreq = 640; // middle of freq band of interest
//Default windowDuration = 5.0 milliseconds - NOTE: 128 samples @ 22.050kHz = 5.805ms.
Tuple <double[], AudioRecording, double[], double[]> results = FrogRibbitRecognizer(
recording,
"Chebyshev_Lowpass_1000",
midBandFreq,
windowDuration: 10.0,
dctDuration: 0.5,
minOscilRate: 11,
maxOscilRate: 17,
maxOscilScore: 30.0);
scores.Add(results.Item1);
//############### Litoria rothii - Laughing tree Frog #########################################################################
frogName = "Litoria_rothii";
Log.WriteLine("# Do Recognizer:- " + frogName);
midBandFreq = 1850; // middle of freq band of interest
results = FrogRibbitRecognizer(recording, "Chebyshev_Lowpass_3000", midBandFreq, dctDuration: 0.5, minOscilRate: 9, maxOscilRate: 11, maxOscilScore: 30.0);
scores.Add(results.Item1);
//############### Rheobatrachus silus - GASTRIC BROODING FROG #########################################################################
frogName = "Rheobatrachus silus";
Log.WriteLine("# Do Recognizer:- " + frogName);
midBandFreq = 1550; // middle of freq band of interest
results = FrogRibbitRecognizer(recording, "Chebyshev_Lowpass_3000", midBandFreq, dctDuration: 0.2, minOscilRate: 55, maxOscilRate: 65, maxOscilScore: 60.0);
scores.Add(results.Item1);
//############### Lymnodynastes peronii - TOCK FROG related to POBBLEBONK ##########################################################
//WARNING####!!!!!! THIS IS NOT A RIBBIT FROG
//frogName = "Lymnodynastes_peronii";
//Log.WriteLine("# Do Recognizer:- " + frogName);
//midBandFreq = 1500; // middle of freq band of interest
//results = FrogRibbitRecognizer(recording, "Chebyshev_Lowpass_3000", midBandFreq, dctDuration:0.2, minOscilRate:55, maxOscilRate:75, maxOscilScore:60.0);
//scores.Add(results.Item1);
//########################################################################################################
//########################################################################################################
//vii: MAKE SONOGRAM
Log.WriteLine("# Make sonogram.");
SonogramConfig sonoConfig = new SonogramConfig(); //default values config
sonoConfig.SourceFName = recording.BaseName;
sonoConfig.WindowSize = SonogramConfig.DEFAULT_WINDOW_SIZE;
sonoConfig.WindowOverlap = 0.5; // set default value
sonoConfig.DoMelScale = false;
sonoConfig.NoiseReductionType = NoiseReductionType.None;
//sonoConfig.NoiseReductionType = NoiseReductionType.STANDARD;
var filteredRecording = results.Item2;
//AmplitudeSonogram basegram = new AmplitudeSonogram(sonoConfig, recording.GetWavReader());
AmplitudeSonogram basegram = new AmplitudeSonogram(sonoConfig, filteredRecording.WavReader);
SpectrogramStandard sonogram = new SpectrogramStandard(basegram); //spectrogram has dim[N,257]
//viii WRITE FILTERED SIGNAL IF NEED TO DEBUG
//write the signal: IMPORTANT: ENSURE VALUES ARE IN RANGE -32768 to +32768
//int bitRate = 16;
//WavWriter.WriteWavFile(filteredRecording.GetWavReader().Samples, filteredRecording.SampleRate, bitRate, recordingPath + "filtered.wav");
// ix: DRAW SONOGRAM AND SCORES
string imagePath = arguments.Source.Name + ".png";
var dBarray = results.Item3;
var miscell = results.Item4;
DrawSonogram(sonogram, imagePath, dBarray, miscell, scores);
Log.WriteLine("# Finished everything!");
}
public static AudioToSonogramResult GenerateSpectrogramImages(FileInfo sourceRecording, Dictionary <string, string> configDict, DirectoryInfo outputDirectory)
{
// the source name was set up in the Analyse() method. But it could also be obtained directly from recording.
string sourceName = configDict[ConfigKeys.Recording.Key_RecordingFileName];
sourceName = Path.GetFileNameWithoutExtension(sourceName);
var result = new AudioToSonogramResult();
// init the image stack
var list = new List <Image>();
// 1) draw amplitude spectrogram
var recordingSegment = new AudioRecording(sourceRecording.FullName);
// default values config except disable noise removal for first two spectrograms
SonogramConfig sonoConfig = new SonogramConfig(configDict)
{
NoiseReductionType = NoiseReductionType.None
};
BaseSonogram sonogram = new AmplitudeSonogram(sonoConfig, recordingSegment.WavReader);
// remove the DC bin
sonogram.Data = MatrixTools.Submatrix(sonogram.Data, 0, 1, sonogram.FrameCount - 1, sonogram.Configuration.FreqBinCount);
// save spectrogram data at this point - prior to noise reduction
double[,] spectrogramDataBeforeNoiseReduction = sonogram.Data;
const int lowPercentile = 20;
const double neighbourhoodSeconds = 0.25;
int neighbourhoodFrames = (int)(sonogram.FramesPerSecond * neighbourhoodSeconds);
const double lcnContrastLevel = 0.25;
////LoggedConsole.WriteLine("LCN: FramesPerSecond (Prior to LCN) = {0}", sonogram.FramesPerSecond);
////LoggedConsole.WriteLine("LCN: Neighbourhood of {0} seconds = {1} frames", neighbourhoodSeconds, neighbourhoodFrames);
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_ShortRecordings_SubtractAndLCN(sonogram.Data, lowPercentile, neighbourhoodFrames, lcnContrastLevel);
// draw amplitude spectrogram unannotated
FileInfo outputImage1 = new FileInfo(Path.Combine(outputDirectory.FullName, sourceName + ".amplitd.bmp"));
ImageTools.DrawReversedMatrix(MatrixTools.MatrixRotate90Anticlockwise(sonogram.Data), outputImage1.FullName);
// draw amplitude spectrogram annotated
var image = sonogram.GetImageFullyAnnotated("AMPLITUDE SPECTROGRAM + Bin LCN (Local Contrast Normalisation)");
list.Add(image);
////string path2 = @"C:\SensorNetworks\Output\Sonograms\dataInput2.png";
////Histogram.DrawDistributionsAndSaveImage(sonogram.Data, path2);
// 2) A FALSE-COLOUR VERSION OF AMPLITUDE SPECTROGRAM
double ridgeThreshold = 0.20;
double[,] matrix = ImageTools.WienerFilter(sonogram.Data, 3);
byte[,] hits = RidgeDetection.Sobel5X5RidgeDetectionExperiment(matrix, ridgeThreshold);
hits = RidgeDetection.JoinDisconnectedRidgesInMatrix(hits, matrix, ridgeThreshold);
image = SpectrogramTools.CreateFalseColourAmplitudeSpectrogram(spectrogramDataBeforeNoiseReduction, null, hits);
image = sonogram.GetImageAnnotatedWithLinearHerzScale(image, "AMPLITUDE SPECTROGRAM + LCN + ridge detection");
list.Add(image);
Image envelopeImage = ImageTrack.DrawWaveEnvelopeTrack(recordingSegment, image.Width);
list.Add(envelopeImage);
// 3) now draw the standard decibel spectrogram
sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
// remove the DC bin
sonogram.Data = MatrixTools.Submatrix(sonogram.Data, 0, 1, sonogram.FrameCount - 1, sonogram.Configuration.FreqBinCount);
// draw decibel spectrogram unannotated
FileInfo outputImage2 = new FileInfo(Path.Combine(outputDirectory.FullName, sourceName + ".deciBel.bmp"));
ImageTools.DrawReversedMatrix(MatrixTools.MatrixRotate90Anticlockwise(sonogram.Data), outputImage2.FullName);
image = sonogram.GetImageFullyAnnotated("DECIBEL SPECTROGRAM");
list.Add(image);
Image segmentationImage = ImageTrack.DrawSegmentationTrack(
sonogram,
EndpointDetectionConfiguration.K1Threshold,
EndpointDetectionConfiguration.K2Threshold,
image.Width);
list.Add(segmentationImage);
// keep the sonogram data (NOT noise reduced) for later use
double[,] dbSpectrogramData = (double[, ])sonogram.Data.Clone();
// 4) now draw the noise reduced decibel spectrogram
sonoConfig.NoiseReductionType = NoiseReductionType.Standard;
sonoConfig.NoiseReductionParameter = 3;
////sonoConfig.NoiseReductionType = NoiseReductionType.SHORT_RECORDING;
////sonoConfig.NoiseReductionParameter = 50;
sonogram = new SpectrogramStandard(sonoConfig, recordingSegment.WavReader);
// draw decibel spectrogram unannotated
FileInfo outputImage3 = new FileInfo(Path.Combine(outputDirectory.FullName, sourceName + ".noNoise_dB.bmp"));
ImageTools.DrawReversedMatrix(MatrixTools.MatrixRotate90Anticlockwise(sonogram.Data), outputImage3.FullName);
image = sonogram.GetImageFullyAnnotated("DECIBEL SPECTROGRAM + Lamel noise subtraction");
list.Add(image);
// keep the sonogram data for later use
double[,] nrSpectrogramData = sonogram.Data;
// 5) A FALSE-COLOUR VERSION OF DECIBEL SPECTROGRAM
ridgeThreshold = 2.5;
matrix = ImageTools.WienerFilter(dbSpectrogramData, 3);
hits = RidgeDetection.Sobel5X5RidgeDetectionExperiment(matrix, ridgeThreshold);
image = SpectrogramTools.CreateFalseColourDecibelSpectrogram(dbSpectrogramData, nrSpectrogramData, hits);
image = sonogram.GetImageAnnotatedWithLinearHerzScale(image, "DECIBEL SPECTROGRAM - Colour annotated");
list.Add(image);
// 6) COMBINE THE SPECTROGRAM IMAGES
Image compositeImage = ImageTools.CombineImagesVertically(list);
FileInfo outputImage = new FileInfo(Path.Combine(outputDirectory.FullName, sourceName + ".5spectro.png"));
compositeImage.Save(outputImage.FullName, ImageFormat.Png);
result.SpectrogramFile = outputImage;
// 7) Generate the FREQUENCY x OSCILLATIONS Graphs and csv data
////bool saveData = true;
////bool saveImage = true;
////double[] oscillationsSpectrum = Oscillations2014.GenerateOscillationDataAndImages(sourceRecording, configDict, saveData, saveImage);
return(result);
}
public static void TestMethod_GenerateSignal2()
{
int sampleRate = 64000;
double duration = 30; // signal duration in seconds
int[] harmonics = { 500, 1000, 2000, 4000, 8000 };
var freqScale = new FrequencyScale(FreqScaleType.Linear125Octaves7Tones28Nyquist32000);
string path = @"C:\SensorNetworks\Output\Sonograms\UnitTestSonograms\SineSignal2.png";
var recording = GenerateTestRecording(sampleRate, duration, harmonics, WaveType.Cosine);
// init the default sonogram config
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.2,
SourceFName = "Signal2",
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// pick a row, any row
var oneSpectrum = MatrixTools.GetRow(sonogram.Data, 40);
oneSpectrum = DataTools.normalise(oneSpectrum);
var peaks = DataTools.GetPeaks(oneSpectrum, 0.5);
var peakIds = new List <int>();
for (int i = 5; i < peaks.Length - 5; i++)
{
if (peaks[i])
{
int peakId = freqScale.BinBounds[i, 0];
peakIds.Add(peakId);
LoggedConsole.WriteLine($"Spectral peak located in bin {peakId}, Herz={freqScale.BinBounds[i, 1]}");
}
}
//if (peaks[129] && peaks[257] && peaks[513] && peaks[1025] && peaks[2049])
if (peakIds[0] == 129 && peakIds[1] == 257 && peakIds[2] == 513 && peakIds[3] == 1025 && peakIds[4] == 2049)
{
LoggedConsole.WriteSuccessLine("Spectral Peaks found at correct places");
}
else
{
LoggedConsole.WriteErrorLine("Spectral Peaks found at INCORRECT places");
}
foreach (int h in harmonics)
{
LoggedConsole.WriteLine($"Harmonic {h}Hertz should be in bin {freqScale.GetBinIdForHerzValue(h)}");
}
// spectrogram without framing, annotation etc
var image = sonogram.GetImage();
string title = $"Spectrogram of Harmonics: {DataTools.Array2String(harmonics)} SR={sampleRate} Window={freqScale.WindowSize}";
image = sonogram.GetImageFullyAnnotated(image, title, freqScale.GridLineLocations);
image.Save(path);
}
/// <summary>
/// Generates the FREQUENCY x OSCILLATIONS Graphs and csv
/// </summary>
public static Tuple <Image, double[, ], double[]> GenerateOscillationDataAndImages(FileInfo audioSegment, Dictionary <string, string> configDict, bool drawImage = false)
{
// set two oscillation detection parameters
double sensitivity = DefaultSensitivityThreshold;
if (configDict.ContainsKey(AnalysisKeys.OscilDetection2014SensitivityThreshold))
{
sensitivity = double.Parse(configDict[AnalysisKeys.OscilDetection2014SensitivityThreshold]);
}
// Sample length i.e. number of frames spanned to calculate oscillations per second
int sampleLength = DefaultSampleLength;
if (configDict.ContainsKey(AnalysisKeys.OscilDetection2014SampleLength))
{
sampleLength = int.Parse(configDict[AnalysisKeys.OscilDetection2014SampleLength]);
}
SonogramConfig sonoConfig = new SonogramConfig(configDict); // default values config
if (configDict.ContainsKey(AnalysisKeys.OscilDetection2014FrameSize))
{
sonoConfig.WindowSize = int.Parse(configDict[AnalysisKeys.OscilDetection2014FrameSize]);
}
var recordingSegment = new AudioRecording(audioSegment.FullName);
BaseSonogram sonogram = new AmplitudeSonogram(sonoConfig, recordingSegment.WavReader);
// remove the DC bin if it has not already been removed.
// Assume test of divisible by 2 is good enough.
int binCount = sonogram.Data.GetLength(1);
if (!binCount.IsEven())
{
sonogram.Data = MatrixTools.Submatrix(sonogram.Data, 0, 1, sonogram.FrameCount - 1, binCount - 1);
}
//LoggedConsole.WriteLine("Oscillation Detection: Sample rate = {0}", sonogram.SampleRate);
//LoggedConsole.WriteLine("Oscillation Detection: FramesPerSecond = {0}", sonogram.FramesPerSecond);
// Do LOCAL CONRAST Normalisation first. LCN over frequency bins is better and faster than standard noise removal.
double neighbourhoodSeconds = 0.25;
int neighbourhoodFrames = (int)(sonogram.FramesPerSecond * neighbourhoodSeconds);
double lcnContrastLevel = 0.5; // was previously 0.1
LoggedConsole.WriteLine("LCN: FramesPerSecond (Prior to LCN) = {0}", sonogram.FramesPerSecond);
LoggedConsole.WriteLine("LCN: Neighbourhood of {0} seconds = {1} frames", neighbourhoodSeconds, neighbourhoodFrames);
sonogram.Data = NoiseRemoval_Briggs.NoiseReduction_byLCNDivision(sonogram.Data, neighbourhoodFrames, lcnContrastLevel);
string algorithmName1 = "autocorr-svd-fft";
double[,] freqOscilMatrix1 = GetFrequencyByOscillationsMatrix(sonogram.Data, sensitivity, sampleLength, algorithmName1);
//get the max spectral index - this reduces the matrix to an array
double[] spectralIndex1 = ConvertMatrix2SpectralIndexBySummingFreqColumns(freqOscilMatrix1, 0);
Image compositeImage = null;
if (drawImage)
{
string algorithmName2 = "autocorr-fft";
double[,] freqOscilMatrix2 = GetFrequencyByOscillationsMatrix(sonogram.Data, sensitivity, sampleLength, algorithmName2);
var image1 = GetFreqVsOscillationsImage(freqOscilMatrix1, sonogram.FramesPerSecond, sonogram.FBinWidth, sampleLength, algorithmName1);
var image2 = GetFreqVsOscillationsImage(freqOscilMatrix2, sonogram.FramesPerSecond, sonogram.FBinWidth, sampleLength, algorithmName2);
compositeImage = ImageTools.CombineImagesInLine(new[] { image1, image2 });
}
// Return (1) composite image of oscillations, (2) data matrix from only one algorithm,
// and (3) spectrum of oscillation values for accumulation into data from a multi-hour recording.
return(Tuple.Create(compositeImage, freqOscilMatrix1, spectralIndex1));
}
public void TestFreqScaleOnArtificialSignal2()
{
int sampleRate = 64000;
double duration = 30; // signal duration in seconds
int[] harmonics = { 500, 1000, 2000, 4000, 8000 };
var freqScale = new FrequencyScale(FreqScaleType.Linear125Octaves7Tones28Nyquist32000);
var outputImagePath = Path.Combine(this.outputDirectory.FullName, "Signal2_OctaveFreqScale.png");
var recording = DspFilters.GenerateTestRecording(sampleRate, duration, harmonics, WaveType.Cosine);
// init the default sonogram config
var sonoConfig = new SonogramConfig
{
WindowSize = freqScale.WindowSize,
WindowOverlap = 0.2,
SourceFName = "Signal2",
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var sonogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
sonogram.Data = OctaveFreqScale.ConvertAmplitudeSpectrogramToDecibelOctaveScale(sonogram.Data, freqScale);
// pick a row, any row
var oneSpectrum = MatrixTools.GetRow(sonogram.Data, 40);
oneSpectrum = DataTools.filterMovingAverage(oneSpectrum, 5);
var peaks = DataTools.GetPeaks(oneSpectrum);
var peakIds = new List <int>();
for (int i = 5; i < peaks.Length - 5; i++)
{
if (peaks[i])
{
int peakId = freqScale.BinBounds[i, 0];
peakIds.Add(peakId);
LoggedConsole.WriteLine($"Spectral peak located in bin {peakId}, Herz={freqScale.BinBounds[i, 1]}");
}
}
foreach (int h in harmonics)
{
LoggedConsole.WriteLine($"Harmonic {h}Herz should be in bin {freqScale.GetBinIdForHerzValue(h)}");
}
Assert.AreEqual(5, peakIds.Count);
Assert.AreEqual(129, peakIds[0]);
Assert.AreEqual(257, peakIds[1]);
Assert.AreEqual(513, peakIds[2]);
Assert.AreEqual(1025, peakIds[3]);
Assert.AreEqual(2049, peakIds[4]);
var image = sonogram.GetImage();
string title = $"Spectrogram of Harmonics: {DataTools.Array2String(harmonics)} SR={sampleRate} Window={freqScale.WindowSize}";
image = sonogram.GetImageFullyAnnotated(image, title, freqScale.GridLineLocations);
image.Save(outputImagePath);
// Check that image dimensions are correct
Assert.AreEqual(146, image.Width);
Assert.AreEqual(310, image.Height);
}
public static void Execute(Arguments arguments)
{
if (arguments == null)
{
arguments = Dev();
}
string title = "# FIND OTHER ACOUSTIC EVENTS LIKE THIS";
string date = "# DATE AND TIME: " + DateTime.Now;
Log.WriteLine(title);
Log.WriteLine(date);
Log.Verbosity = 1;
Log.WriteIfVerbose("# Recording =" + arguments.Source); //the recording to be scanned
Log.WriteIfVerbose("# Template list =" + arguments.Config); //the path to a file containing the paths to template locations, one template per line
Log.WriteIfVerbose("# Output folder =" + arguments.Output); //name of output dir
var allEvents = new List <AcousticEvent>();
var scoresList = new List <double[]>();
var thresholdList = new List <double>();
//i: GET RECORDING
AudioRecording recording = new AudioRecording(arguments.Source.FullName);
//if (recording.SampleRate != 22050) recording.ConvertSampleRate22kHz(); // THIS METHOD CALL IS OBSOLETE
int sr = recording.SampleRate;
//ii: MAKE SONOGRAM
Log.WriteLine("Start sonogram.");
SonogramConfig sonoConfig = new SonogramConfig(); //default values config
sonoConfig.SourceFName = recording.BaseName;
sonoConfig.WindowOverlap = FeltFrameOverlap; // set default value
sonoConfig.DoMelScale = false;
sonoConfig.NoiseReductionType = NoiseReductionType.Standard;
AmplitudeSonogram basegram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
SpectrogramStandard sonogram = new SpectrogramStandard(basegram); //spectrogram has dim[N,257]
Log.WriteLine("Signal: Duration={0}, Sample Rate={1}", sonogram.Duration, sr);
Log.WriteLine("Frames: Size={0}, Count={1}, Duration={2:f1}ms, Overlap={5:f0}%, Offset={3:f1}ms, Frames/s={4:f1}",
sonogram.Configuration.WindowSize, sonogram.FrameCount, (sonogram.FrameDuration * 1000),
(sonogram.FrameStep * 1000), sonogram.FramesPerSecond, FeltFrameOverlap * 100);
//iii: Get zip paths and the results Tuple
List <string> zipList = FileTools.ReadTextFile(arguments.Config.FullName);
Tuple <SpectrogramStandard, List <AcousticEvent>, double[]> results = null; //set up the results Tuple
foreach (string zipPath in zipList)
{
if (zipPath.StartsWith("#"))
{
continue; // commented line
}
if (zipPath.Length < 2)
{
continue; // empty line
}
//i: get params file
ZipFile.ExtractToDirectory(arguments.Output.FullName, zipPath);
string zipName = Path.GetFileNameWithoutExtension(zipPath);
string[] parts = zipName.Split('_');
string paramsPath = Path.Combine(arguments.Output.FullName, parts[0] + "_" + parts[1] + "_Params.txt");
string id = parts[0] + "_" + parts[1];
Log.WriteIfVerbose("################################################### " + id + " ########################################################");
//ii: READ PARAMETER VALUES FROM INI FILE
var config = new ConfigDictionary(paramsPath);
Dictionary <string, string> dict = config.GetTable();
//Dictionary<string, string>.KeyCollection keys = dict.Keys;
//int DRAW_SONOGRAMS = Int32.Parse(dict[FeltTemplate_Create.key_DRAW_SONOGRAMS]); //options to draw sonogram
dict[FeltTemplate_Create.key_DECIBEL_THRESHOLD] = "4.0";
dict[FeltTemplate_Create.key_MIN_DURATION] = "0.02";
if (zipName.EndsWith("binaryTemplate"))
{
string templatePath = Path.Combine(arguments.Output.FullName, id + "_binary.bmp");
double[,] templateMatrix = FindMatchingEvents.ReadImage2BinaryMatrixDouble(templatePath);
results = FELTWithBinaryTemplate(sonogram, dict, templateMatrix, TimeSpan.Zero);
}
else
if (zipName.EndsWith("trinaryTemplate"))
{
string templatePath = Path.Combine(arguments.Output.FullName, id + "_trinary.bmp");
double[,] templateMatrix = FindMatchingEvents.ReadImage2TrinaryMatrix(templatePath);
results = FELTWithBinaryTemplate(sonogram, dict, templateMatrix, TimeSpan.Zero);
}
else
if (zipName.EndsWith("syntacticTemplate"))
{
string templatePath = Path.Combine(arguments.Output.FullName, id + "_spr.txt");
char[,] templateMatrix = FindMatchingEvents.ReadTextFile2CharMatrix(templatePath);
results = FELTWithSprTemplate(sonogram, dict, templateMatrix, TimeSpan.Zero);
}
else
{
Log.WriteLine("ERROR! UNKNOWN TEMPLATE: Zip file has unrecognised suffix:" + zipName);
continue;
}
//get results
sonogram = results.Item1;
var matchingEvents = results.Item2;
var scores = results.Item3;
double matchThreshold = double.Parse(dict[FeltTemplate_Create.key_DECIBEL_THRESHOLD]);
Log.WriteLine("# Finished detecting events like target: " + id);
Log.WriteLine("# Matching Event Count = " + matchingEvents.Count);
Log.WriteLine(" @ threshold = {0:f2}", matchThreshold);
// accumulate results
allEvents.AddRange(matchingEvents);
scoresList.Add(scores);
thresholdList.Add(matchThreshold);
//v: write events count to results info file.
double sigDuration = sonogram.Duration.TotalSeconds;
string fname = arguments.Source.Name;
string str = string.Format("{0}\t{1}\t{2}", fname, sigDuration, matchingEvents.Count);
StringBuilder sb = AcousticEvent.WriteEvents(matchingEvents, str);
FileTools.WriteTextFile("opPath", sb.ToString());
} // foreach (string zipPath in zipList)
Log.WriteLine("\n\n\n##########################################################");
Log.WriteLine("# Finished detecting events");
Log.WriteLine("# Event Count = " + allEvents.Count);
foreach (AcousticEvent ae in allEvents)
{
Log.WriteLine("# Event name = {0} ############################", ae.Name);
Log.WriteLine("# Event time = {0:f2} to {1:f2} (frames {2}-{3}).", ae.TimeStart, ae.TimeEnd, ae.Oblong.RowTop, ae.Oblong.RowBottom);
Log.WriteLine("# Event score= {0:f2}.", ae.Score);
}
int percentOverlap = 50;
allEvents = PruneOverlappingEvents(allEvents, percentOverlap);
Log.WriteLine("\n##########################################################");
Log.WriteLine("# Finished pruning events");
Log.WriteLine("# Event Count = " + allEvents.Count);
WriteEventNames(allEvents);
//WriteScoreAverages2Console(scoresList);
//draw images of sonograms
int DRAW_SONOGRAMS = 2;
FileInfo opImagePath = arguments.Output.CombineFile(Path.GetFileNameWithoutExtension(arguments.Source.Name) + "_matchingEvents.png");
if (DRAW_SONOGRAMS == 2)
{
DrawSonogram(sonogram, opImagePath, allEvents, thresholdList, scoresList);
}
else
if ((DRAW_SONOGRAMS == 1) && (allEvents.Count > 0))
{
DrawSonogram(sonogram, opImagePath, allEvents, thresholdList, scoresList);
}
Log.WriteLine("# FINISHED passing all templates over recording:- " + arguments.Source.Name);
}
