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 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 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 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);
}
/// <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 static void Execute(Arguments arguments)
{
const string Title = "# DETERMINING SIGNAL TO NOISE RATIO IN RECORDING";
string date = "# DATE AND TIME: " + DateTime.Now;
Log.WriteLine(Title);
Log.WriteLine(date);
Log.Verbosity = 1;
var input = arguments.Source;
var sourceFileName = input.Name;
var outputDir = arguments.Output;
var fileNameWithoutExtension = Path.GetFileNameWithoutExtension(input.FullName);
var outputTxtPath = Path.Combine(outputDir.FullName, fileNameWithoutExtension + ".txt").ToFileInfo();
Log.WriteIfVerbose("# Recording file: " + input.FullName);
Log.WriteIfVerbose("# Config file: " + arguments.Config);
Log.WriteIfVerbose("# Output folder =" + outputDir.FullName);
FileTools.WriteTextFile(outputTxtPath.FullName, date + "\n# Recording file: " + input.FullName);
//READ PARAMETER VALUES FROM INI FILE
// load YAML configuration
Config configuration = ConfigFile.Deserialize(arguments.Config);
//ii: SET SONOGRAM CONFIGURATION
SonogramConfig sonoConfig = new SonogramConfig(); //default values config
sonoConfig.SourceFName = input.FullName;
sonoConfig.WindowSize = configuration.GetIntOrNull(AnalysisKeys.KeyFrameSize) ?? 512;
sonoConfig.WindowOverlap = configuration.GetDoubleOrNull(AnalysisKeys.FrameOverlap) ?? 0.5;
sonoConfig.WindowFunction = configuration[AnalysisKeys.KeyWindowFunction];
sonoConfig.NPointSmoothFFT = configuration.GetIntOrNull(AnalysisKeys.KeyNPointSmoothFft) ?? 256;
sonoConfig.NoiseReductionType = SNR.KeyToNoiseReductionType(configuration[AnalysisKeys.NoiseReductionType]);
int minHz = configuration.GetIntOrNull("MIN_HZ") ?? 0;
int maxHz = configuration.GetIntOrNull("MAX_HZ") ?? 11050;
double segK1 = configuration.GetDoubleOrNull("SEGMENTATION_THRESHOLD_K1") ?? 0;
double segK2 = configuration.GetDoubleOrNull("SEGMENTATION_THRESHOLD_K2") ?? 0;
double latency = configuration.GetDoubleOrNull("K1_K2_LATENCY") ?? 0;
double vocalGap = configuration.GetDoubleOrNull("VOCAL_GAP") ?? 0;
double minVocalLength = configuration.GetDoubleOrNull("MIN_VOCAL_DURATION") ?? 0;
//bool DRAW_SONOGRAMS = (bool?)configuration.DrawSonograms ?? true; //options to draw sonogram
//double intensityThreshold = Acoustics.AED.Default.intensityThreshold;
//if (dict.ContainsKey(key_AED_INTENSITY_THRESHOLD)) intensityThreshold = Double.Parse(dict[key_AED_INTENSITY_THRESHOLD]);
//int smallAreaThreshold = Acoustics.AED.Default.smallAreaThreshold;
//if( dict.ContainsKey(key_AED_SMALL_AREA_THRESHOLD)) smallAreaThreshold = Int32.Parse(dict[key_AED_SMALL_AREA_THRESHOLD]);
// COnvert input recording into wav
var convertParameters = new AudioUtilityRequest {
TargetSampleRate = 17640
};
var fileToAnalyse = new FileInfo(Path.Combine(outputDir.FullName, "temp.wav"));
if (File.Exists(fileToAnalyse.FullName))
{
File.Delete(fileToAnalyse.FullName);
}
var convertedFileInfo = AudioFilePreparer.PrepareFile(
input,
fileToAnalyse,
convertParameters,
outputDir);
// (A) ##########################################################################################################################
AudioRecording recording = new AudioRecording(fileToAnalyse.FullName);
int signalLength = recording.WavReader.Samples.Length;
TimeSpan wavDuration = TimeSpan.FromSeconds(recording.WavReader.Time.TotalSeconds);
double frameDurationInSeconds = sonoConfig.WindowSize / (double)recording.SampleRate;
TimeSpan frameDuration = TimeSpan.FromTicks((long)(frameDurationInSeconds * TimeSpan.TicksPerSecond));
int stepSize = (int)Math.Floor(sonoConfig.WindowSize * (1 - sonoConfig.WindowOverlap));
double stepDurationInSeconds = sonoConfig.WindowSize * (1 - sonoConfig.WindowOverlap)
/ recording.SampleRate;
TimeSpan stepDuration = TimeSpan.FromTicks((long)(stepDurationInSeconds * TimeSpan.TicksPerSecond));
double framesPerSecond = 1 / stepDuration.TotalSeconds;
int frameCount = signalLength / stepSize;
// (B) ################################## EXTRACT ENVELOPE and SPECTROGRAM ##################################
var dspOutput = DSP_Frames.ExtractEnvelopeAndFfts(
recording,
sonoConfig.WindowSize,
sonoConfig.WindowOverlap);
//double[] avAbsolute = dspOutput.Average; //average absolute value over the minute recording
// (C) ################################## GET SIGNAL WAVEFORM ##################################
double[] signalEnvelope = dspOutput.Envelope;
double avSignalEnvelope = signalEnvelope.Average();
// (D) ################################## GET Amplitude Spectrogram ##################################
double[,] amplitudeSpectrogram = dspOutput.AmplitudeSpectrogram; // get amplitude spectrogram.
// (E) ################################## Generate deciBel spectrogram from amplitude spectrogram
double epsilon = Math.Pow(0.5, recording.BitsPerSample - 1);
double[,] deciBelSpectrogram = MFCCStuff.DecibelSpectra(
dspOutput.AmplitudeSpectrogram,
dspOutput.WindowPower,
recording.SampleRate,
epsilon);
LoggedConsole.WriteLine("# Finished calculating decibel spectrogram.");
StringBuilder sb = new StringBuilder();
sb.AppendLine("\nSIGNAL PARAMETERS");
sb.AppendLine("Signal Duration =" + wavDuration);
sb.AppendLine("Sample Rate =" + recording.SampleRate);
sb.AppendLine("Min Signal Value =" + dspOutput.MinSignalValue);
sb.AppendLine("Max Signal Value =" + dspOutput.MaxSignalValue);
sb.AppendLine("Max Absolute Ampl =" + signalEnvelope.Max().ToString("F3") + " (See Note 1)");
sb.AppendLine("Epsilon Ampl (1 bit)=" + epsilon);
sb.AppendLine("\nFRAME PARAMETERS");
sb.AppendLine("Window Size =" + sonoConfig.WindowSize);
sb.AppendLine("Frame Count =" + frameCount);
sb.AppendLine("Envelope length=" + signalEnvelope.Length);
sb.AppendLine("Frame Duration =" + frameDuration.TotalMilliseconds.ToString("F3") + " ms");
sb.AppendLine("Frame overlap =" + sonoConfig.WindowOverlap);
sb.AppendLine("Step Size =" + stepSize);
sb.AppendLine("Step duration =" + stepDuration.TotalMilliseconds.ToString("F3") + " ms");
sb.AppendLine("Frames Per Sec =" + framesPerSecond.ToString("F1"));
sb.AppendLine("\nFREQUENCY PARAMETERS");
sb.AppendLine("Nyquist Freq =" + dspOutput.NyquistFreq + " Hz");
sb.AppendLine("Freq Bin Width =" + dspOutput.FreqBinWidth.ToString("F2") + " Hz");
sb.AppendLine("Nyquist Bin =" + dspOutput.NyquistBin);
sb.AppendLine("\nENERGY PARAMETERS");
double val = dspOutput.FrameEnergy.Min();
sb.AppendLine(
"Minimum dB / frame =" + (10 * Math.Log10(val)).ToString("F2") + " (See Notes 2, 3 & 4)");
val = dspOutput.FrameEnergy.Max();
sb.AppendLine("Maximum dB / frame =" + (10 * Math.Log10(val)).ToString("F2"));
sb.AppendLine("\ndB NOISE SUBTRACTION");
double noiseRange = 2.0;
//sb.AppendLine("Noise (estimate of mode) =" + sonogram.SnrData.NoiseSubtracted.ToString("F3") + " dB (See Note 5)");
//double noiseSpan = sonogram.SnrData.NoiseRange;
//sb.AppendLine("Noise range =" + noiseSpan.ToString("F2") + " to +" + (noiseSpan * -1).ToString("F2") + " dB (See Note 6)");
//sb.AppendLine("SNR (max frame-noise) =" + sonogram.SnrData.Snr.ToString("F2") + " dB (See Note 7)");
//sb.Append("\nSEGMENTATION PARAMETERS");
//sb.Append("Segment Thresholds K1: {0:f2}. K2: {1:f2} (See Note 8)", segK1, segK2);
//sb.Append("# Event Count = " + predictedEvents.Count());
FileTools.Append2TextFile(outputTxtPath.FullName, sb.ToString());
FileTools.Append2TextFile(outputTxtPath.FullName, GetSNRNotes(noiseRange).ToString());
// (F) ################################## DRAW IMAGE 1: original spectorgram
Log.WriteLine("# Start drawing noise reduced sonograms.");
TimeSpan X_AxisInterval = TimeSpan.FromSeconds(1);
//int Y_AxisInterval = (int)Math.Round(1000 / dspOutput.FreqBinWidth);
int nyquist = recording.SampleRate / 2;
int hzInterval = 1000;
var image1 = DrawSonogram(deciBelSpectrogram, wavDuration, X_AxisInterval, stepDuration, nyquist, hzInterval);
// (G) ################################## Calculate modal background noise spectrum in decibels
//double SD_COUNT = -0.5; // number of SDs above the mean for noise removal
//NoiseReductionType nrt = NoiseReductionType.MODAL;
//System.Tuple<double[,], double[]> tuple = SNR.NoiseReduce(deciBelSpectrogram, nrt, SD_COUNT);
//double upperPercentileBound = 0.2; // lowest percentile for noise removal
//NoiseReductionType nrt = NoiseReductionType.LOWEST_PERCENTILE;
//System.Tuple<double[,], double[]> tuple = SNR.NoiseReduce(deciBelSpectrogram, nrt, upperPercentileBound);
// (H) ################################## Calculate BRIGGS noise removal from amplitude spectrum
int percentileBound = 20; // low energy percentile for noise removal
//double binaryThreshold = 0.6; //works for higher SNR recordings
double binaryThreshold = 0.4; //works for lower SNR recordings
//double binaryThreshold = 0.3; //works for lower SNR recordings
double[,] m = NoiseRemoval_Briggs.BriggsNoiseFilterAndGetMask(
amplitudeSpectrogram,
percentileBound,
binaryThreshold);
string title = "TITLE";
var image2 = NoiseRemoval_Briggs.DrawSonogram(
m,
wavDuration,
X_AxisInterval,
stepDuration,
nyquist, hzInterval,
title);
//Image image2 = NoiseRemoval_Briggs.BriggsNoiseFilterAndGetSonograms(amplitudeSpectrogram, upperPercentileBound, binaryThreshold,
// wavDuration, X_AxisInterval, stepDuration, Y_AxisInterval);
// (I) ################################## Calculate MEDIAN noise removal from amplitude spectrum
//double upperPercentileBound = 0.8; // lowest percentile for noise removal
//NoiseReductionType nrt = NoiseReductionType.MEDIAN;
//System.Tuple<double[,], double[]> tuple = SNR.NoiseReduce(deciBelSpectrogram, nrt, upperPercentileBound);
//double[,] noiseReducedSpectrogram1 = tuple.Item1; //
//double[] noiseProfile = tuple.Item2; // smoothed modal profile
//SNR.NoiseProfile dBProfile = SNR.CalculateNoiseProfile(deciBelSpectrogram, SD_COUNT); // calculate noise value for each freq bin.
//double[] noiseProfile = DataTools.filterMovingAverage(dBProfile.noiseThresholds, 7); // smooth modal profile
//double[,] noiseReducedSpectrogram1 = SNR.TruncateBgNoiseFromSpectrogram(deciBelSpectrogram, dBProfile.noiseThresholds);
//Image image2 = DrawSonogram(noiseReducedSpectrogram1, wavDuration, X_AxisInterval, stepDuration, Y_AxisInterval);
var combinedImage = ImageTools.CombineImagesVertically(image1, image2);
string imagePath = Path.Combine(outputDir.FullName, fileNameWithoutExtension + ".png");
combinedImage.Save(imagePath);
// (G) ################################## Calculate modal background noise spectrum in decibels
Log.WriteLine("# Finished recording:- " + input.Name);
}
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");
}
