private static Image DrawSonogram(double[,] data, TimeSpan xInterval, TimeSpan xAxisPixelDuration, int nyquist, int herzInterval, string title)
{
var image = ImageTools.GetMatrixImage(data);
var titleBar = BaseSonogram.DrawTitleBarOfGrayScaleSpectrogram(title, image.Width);
var minuteOffset = TimeSpan.Zero;
var labelInterval = TimeSpan.FromSeconds(5);
image = BaseSonogram.FrameSonogram(image, titleBar, minuteOffset, xInterval, xAxisPixelDuration, labelInterval, nyquist, herzInterval);
return(image);
}
public static Image GetCepstralSpectrogram(SonogramConfig sonoConfig, AudioRecording recording, string sourceRecordingName)
{
// TODO at present noise reduction type must be set = Standard.
sonoConfig.NoiseReductionType = NoiseReductionType.Standard;
sonoConfig.NoiseReductionParameter = 3.0;
var cepgram = new SpectrogramCepstral(sonoConfig, recording.WavReader);
var image = cepgram.GetImage();
var titleBar = BaseSonogram.DrawTitleBarOfGrayScaleSpectrogram("CEPSTRO-GRAM " + sourceRecordingName, image.Width);
var startTime = TimeSpan.Zero;
var xAxisTicInterval = TimeSpan.FromSeconds(1);
TimeSpan xAxisPixelDuration = TimeSpan.FromSeconds(sonoConfig.WindowStep / (double)sonoConfig.SampleRate);
var labelInterval = TimeSpan.FromSeconds(5);
image = BaseSonogram.FrameSonogram(image, titleBar, startTime, xAxisTicInterval, xAxisPixelDuration, labelInterval);
return(image);
}
private static Image <Rgb24> DrawSonogram(
double[,] data,
TimeSpan recordingDuration,
TimeSpan xInterval,
TimeSpan xAxisPixelDuration,
int nyquist,
int hzInterval)
{
var image = ImageTools.GetMatrixImage(data);
string title = string.Format("TITLE");
var titleBar = BaseSonogram.DrawTitleBarOfGrayScaleSpectrogram(title, image.Width);
var minuteOffset = TimeSpan.Zero;
var labelInterval = TimeSpan.FromSeconds(5);
image = BaseSonogram.FrameSonogram(
image,
titleBar,
minuteOffset,
xInterval,
xAxisPixelDuration,
labelInterval,
nyquist,
hzInterval);
return(image);
//USE THIS CODE TO RETURN COMPRESSED SONOGRAM
//int factor = 10; //compression factor
//using (var image3 = new Image_MultiTrack(sonogram.GetImage_ReducedSonogram(factor)))
//{
//image3.AddTrack(ImageTrack.GetTimeTrack(sonogram.Duration));
//image3.AddTrack(ImageTrack.GetWavEnvelopeTrack(recording, image3.Image.Width));
//image3.AddTrack(ImageTrack.GetDecibelTrack(sonogram));
//image3.AddTrack(ImageTrack.GetSegmentationTrack(sonogram));
//path = outputFolder + wavFileName + "_reduced.png"
//image3.Save(path);
//}
//DISPLAY IMAGE SUB BAND HIGHLIGHT and SNR DATA
//doHighlightSubband = true;
//var image4 = new Image_MultiTrack(sonogram.GetImage(doHighlightSubband, add1kHzLines));
//image4.AddTrack(ImageTrack.GetTimeTrack(sonogram.Duration));
////image4.AddTrack(ImageTrack.GetWavEnvelopeTrack(recording, image4.SonoImage.Width));
//image4.AddTrack(ImageTrack.GetSegmentationTrack(sonogram));
////path = outputFolder + wavFileName + "_subband.png"
//image4.Save(path);
}
public static Image <Rgb24> DrawSonogram(double[,] data, TimeSpan recordingDuration, TimeSpan X_interval, TimeSpan xAxisPixelDuration,
int nyquist, int herzInterval, string title)
{
// the next two variables determine how the greyscale sonogram image is normalised.
// The low normalisation bound is min value of the average spectrogram derived from the lowest percent of frames
// The high normalisation bound is max value of the average spectrogram derived from the highest percent of frames
int minPercentile = 5;
int maxPercentile = 10;
var image = BaseSonogram.GetSonogramImage(data, minPercentile, maxPercentile);
var titleBar = BaseSonogram.DrawTitleBarOfGrayScaleSpectrogram(title, image.Width);
TimeSpan minuteOffset = TimeSpan.Zero;
TimeSpan labelInterval = TimeSpan.FromSeconds(5);
image = BaseSonogram.FrameSonogram(image, titleBar, minuteOffset, X_interval, xAxisPixelDuration, labelInterval, nyquist, herzInterval);
return(image);
}
/// <summary>
/// Calculates the following spectrograms as per settings in the Images array in the config file: Towsey.SpectrogramGenerator.yml:
/// Waveform.
/// DecibelSpectrogram.
/// DecibelSpectrogramNoiseReduced.
/// CepstralSpectrogram.
/// DifferenceSpectrogram.
/// AmplitudeSpectrogramLocalContrastNormalization.
/// Experimental.
/// Comment the config.yml file with a hash, those spectrograms that are not required.
/// </summary>
/// <param name="sourceRecording">The name of the original recording.</param>
/// <param name="config">Contains parameter info to make spectrograms.</param>
/// <param name="sourceRecordingName">.Name of source recording. Required only spectrogram labels.</param>
public static AudioToSonogramResult GenerateSpectrogramImages(
FileInfo sourceRecording,
SpectrogramGeneratorConfig config,
string sourceRecordingName)
{
//int signalLength = recordingSegment.WavReader.GetChannel(0).Length;
var recordingSegment = new AudioRecording(sourceRecording.FullName);
int sampleRate = recordingSegment.WavReader.SampleRate;
var result = new AudioToSonogramResult();
var requestedImageTypes = config.Images ?? new[] { SpectrogramImageType.DecibelSpectrogram };
var @do = requestedImageTypes.ToHashSet();
int frameSize = config.GetIntOrNull("FrameLength") ?? 512;
int frameStep = config.GetIntOrNull("FrameStep") ?? 441;
// must calculate this because used later on.
double frameOverlap = (frameSize - frameStep) / (double)frameSize;
// Default noiseReductionType = Standard
var bgNoiseThreshold = config.BgNoiseThreshold;
// threshold for drawing the difference spectrogram
var differenceThreshold = config.DifferenceThreshold;
// EXTRACT ENVELOPE and SPECTROGRAM FROM RECORDING SEGMENT
var dspOutput1 = DSP_Frames.ExtractEnvelopeAndFfts(recordingSegment, frameSize, frameStep);
var sonoConfig = new SonogramConfig()
{
epsilon = recordingSegment.Epsilon,
SampleRate = sampleRate,
WindowSize = frameSize,
WindowStep = frameStep,
WindowOverlap = frameOverlap,
WindowPower = dspOutput1.WindowPower,
Duration = recordingSegment.Duration,
NoiseReductionType = NoiseReductionType.Standard,
NoiseReductionParameter = bgNoiseThreshold,
};
var images = new Dictionary <SpectrogramImageType, Image <Rgb24> >(requestedImageTypes.Length);
// IMAGE 1) draw the WAVEFORM
if (@do.Contains(Waveform))
{
var minValues = dspOutput1.MinFrameValues;
var maxValues = dspOutput1.MaxFrameValues;
int height = config.WaveformHeight;
var waveformImage = GetWaveformImage(minValues, maxValues, height);
// add in the title bar and time scales.
string title =
$"WAVEFORM - {sourceRecordingName} (min value={dspOutput1.MinSignalValue:f3}, max value={dspOutput1.MaxSignalValue:f3})";
var titleBar = BaseSonogram.DrawTitleBarOfGrayScaleSpectrogram(
title,
waveformImage.Width,
ImageTags[Waveform]);
var startTime = TimeSpan.Zero;
var xAxisTicInterval = TimeSpan.FromSeconds(1);
TimeSpan xAxisPixelDuration = TimeSpan.FromSeconds(frameStep / (double)sampleRate);
var labelInterval = TimeSpan.FromSeconds(5);
waveformImage = BaseSonogram.FrameSonogram(
waveformImage,
titleBar,
startTime,
xAxisTicInterval,
xAxisPixelDuration,
labelInterval);
images.Add(Waveform, waveformImage);
}
// Draw various decibel spectrograms
var decibelTypes = new[] { SpectrogramImageType.DecibelSpectrogram, DecibelSpectrogramNoiseReduced, DifferenceSpectrogram, Experimental };
if (@do.Overlaps(decibelTypes))
{
// disable noise removal for first two spectrograms
var disabledNoiseReductionType = sonoConfig.NoiseReductionType;
sonoConfig.NoiseReductionType = NoiseReductionType.None;
//Get the decibel spectrogram
var decibelSpectrogram = new SpectrogramStandard(sonoConfig, dspOutput1.AmplitudeSpectrogram);
result.DecibelSpectrogram = decibelSpectrogram;
double[,] dbSpectrogramData = (double[, ])decibelSpectrogram.Data.Clone();
// IMAGE 2) Display the DecibelSpectrogram
if (@do.Contains(SpectrogramImageType.DecibelSpectrogram))
{
images.Add(
SpectrogramImageType.DecibelSpectrogram,
decibelSpectrogram.GetImageFullyAnnotated(
$"DECIBEL SPECTROGRAM ({sourceRecordingName})",
ImageTags[SpectrogramImageType.DecibelSpectrogram]));
}
if (@do.Overlaps(new[] { DecibelSpectrogramNoiseReduced, Experimental, CepstralSpectrogram }))
{
sonoConfig.NoiseReductionType = disabledNoiseReductionType;
sonoConfig.NoiseReductionParameter = bgNoiseThreshold;
double[] spectralDecibelBgn = NoiseProfile.CalculateBackgroundNoise(decibelSpectrogram.Data);
decibelSpectrogram.Data =
SNR.TruncateBgNoiseFromSpectrogram(decibelSpectrogram.Data, spectralDecibelBgn);
decibelSpectrogram.Data =
SNR.RemoveNeighbourhoodBackgroundNoise(decibelSpectrogram.Data, nhThreshold: bgNoiseThreshold);
// IMAGE 3) DecibelSpectrogram - noise reduced
if (@do.Contains(DecibelSpectrogramNoiseReduced))
{
images.Add(
DecibelSpectrogramNoiseReduced,
decibelSpectrogram.GetImageFullyAnnotated(
$"DECIBEL SPECTROGRAM + Lamel noise subtraction. ({sourceRecordingName})",
ImageTags[DecibelSpectrogramNoiseReduced]));
}
// IMAGE 4) EXPERIMENTAL Spectrogram
if (@do.Contains(Experimental))
{
sonoConfig.NoiseReductionType = disabledNoiseReductionType;
images.Add(
Experimental,
GetDecibelSpectrogram_Ridges(
dbSpectrogramData,
decibelSpectrogram,
sourceRecordingName));
}
}
// IMAGE 5) draw difference spectrogram. This is derived from the original decibel spectrogram
if (@do.Contains(DifferenceSpectrogram))
{
//var differenceThreshold = configInfo.GetDoubleOrNull("DifferenceThreshold") ?? 3.0;
var differenceImage = GetDifferenceSpectrogram(dbSpectrogramData, differenceThreshold);
differenceImage = BaseSonogram.GetImageAnnotatedWithLinearHertzScale(
differenceImage,
sampleRate,
frameStep,
$"DECIBEL DIFFERENCE SPECTROGRAM ({sourceRecordingName})",
ImageTags[DifferenceSpectrogram]);
images.Add(DifferenceSpectrogram, differenceImage);
}
}
// IMAGE 6) Cepstral Spectrogram
if (@do.Contains(CepstralSpectrogram))
{
images.Add(
CepstralSpectrogram,
GetCepstralSpectrogram(sonoConfig, recordingSegment, sourceRecordingName));
}
// IMAGE 7) AmplitudeSpectrogram_LocalContrastNormalization
if (@do.Contains(AmplitudeSpectrogramLocalContrastNormalization))
{
var neighborhoodSeconds = config.NeighborhoodSeconds;
var lcnContrastParameter = config.LcnContrastLevel;
images.Add(
AmplitudeSpectrogramLocalContrastNormalization,
GetLcnSpectrogram(
sonoConfig,
recordingSegment,
sourceRecordingName,
neighborhoodSeconds,
lcnContrastParameter));
}
// now pick and combine images in order user specified
var sortedImages = requestedImageTypes.Select(x => images[x]);
// COMBINE THE SPECTROGRAM IMAGES
result.CompositeImage = ImageTools.CombineImagesVertically(sortedImages.ToArray());
return(result);
}
/// <summary>
/// Calculates the following spectrograms as per content of config.yml file:
/// Waveform: true.
/// DifferenceSpectrogram: true.
/// DecibelSpectrogram: true.
/// DecibelSpectrogram_NoiseReduced: true.
/// DecibelSpectrogram_Ridges: true.
/// AmplitudeSpectrogram_LocalContrastNormalization: true.
/// SoxSpectrogram: false.
/// Experimental: true.
/// </summary>
/// <param name="sourceRecording">The name of the original recording.</param>
/// <param name="configInfo">Contains parameter info to make spectrograms.</param>
/// <param name="sourceRecordingName">.Name of source recording. Required only spectrogram labels.</param>
public static AudioToSonogramResult GenerateSpectrogramImages(
FileInfo sourceRecording,
AnalyzerConfig configInfo,
string sourceRecordingName)
{
//int signalLength = recordingSegment.WavReader.GetChannel(0).Length;
var recordingSegment = new AudioRecording(sourceRecording.FullName);
int sampleRate = recordingSegment.WavReader.SampleRate;
var result = new AudioToSonogramResult();
// init the image stack
var list = new List <Image>();
bool doWaveForm = configInfo.GetBoolOrNull("Waveform") ?? false;
bool doDecibelSpectrogram = configInfo.GetBoolOrNull("DecibelSpectrogram") ?? false;
bool doNoiseReducedSpectrogram = configInfo.GetBoolOrNull("DecibelSpectrogram_NoiseReduced") ?? true;
bool doDifferenceSpectrogram = configInfo.GetBoolOrNull("DifferenceSpectrogram") ?? false;
bool doLcnSpectrogram = configInfo.GetBoolOrNull("AmplitudeSpectrogram_LocalContrastNormalization") ?? false;
bool doCepstralSpectrogram = configInfo.GetBoolOrNull("CepstralSpectrogram") ?? false;
bool doExperimentalSpectrogram = configInfo.GetBoolOrNull("Experimental") ?? false;
//Don't do SOX spectrogram.
//bool doSoxSpectrogram = configInfo.GetBool("SoxSpectrogram");
int frameSize = configInfo.GetIntOrNull("FrameLength") ?? 512;
int frameStep = configInfo.GetIntOrNull("FrameStep") ?? 0;
// must calculate this because used later on.
double frameOverlap = (frameSize - frameStep) / (double)frameSize;
// Default noiseReductionType = Standard
var bgNoiseThreshold = configInfo.GetDoubleOrNull("BgNoiseThreshold") ?? 3.0;
// EXTRACT ENVELOPE and SPECTROGRAM FROM RECORDING SEGMENT
var dspOutput1 = DSP_Frames.ExtractEnvelopeAndFfts(recordingSegment, frameSize, frameStep);
var sonoConfig = new SonogramConfig()
{
epsilon = recordingSegment.Epsilon,
SampleRate = sampleRate,
WindowSize = frameSize,
WindowStep = frameStep,
WindowOverlap = frameOverlap,
WindowPower = dspOutput1.WindowPower,
Duration = recordingSegment.Duration,
NoiseReductionType = NoiseReductionType.Standard,
NoiseReductionParameter = bgNoiseThreshold,
};
// IMAGE 1) draw the WAVEFORM
if (doWaveForm)
{
var minValues = dspOutput1.MinFrameValues;
var maxValues = dspOutput1.MaxFrameValues;
int height = configInfo.GetIntOrNull("WaveformHeight") ?? 180;
var waveformImage = GetWaveformImage(minValues, maxValues, height);
// add in the title bar and time scales.
string title = $"WAVEFORM - {sourceRecordingName} (min value={dspOutput1.MinSignalValue:f3}, max value={dspOutput1.MaxSignalValue:f3})";
var titleBar = BaseSonogram.DrawTitleBarOfGrayScaleSpectrogram(title, waveformImage.Width);
var startTime = TimeSpan.Zero;
var xAxisTicInterval = TimeSpan.FromSeconds(1);
TimeSpan xAxisPixelDuration = TimeSpan.FromSeconds(frameStep / (double)sampleRate);
var labelInterval = TimeSpan.FromSeconds(5);
waveformImage = BaseSonogram.FrameSonogram(waveformImage, titleBar, startTime, xAxisTicInterval, xAxisPixelDuration, labelInterval);
list.Add(waveformImage);
}
// Draw various decibel spectrograms
if (doDecibelSpectrogram || doNoiseReducedSpectrogram || doDifferenceSpectrogram || doExperimentalSpectrogram)
{
// disable noise removal for first spectrogram
var disabledNoiseReductionType = sonoConfig.NoiseReductionType;
sonoConfig.NoiseReductionType = NoiseReductionType.None;
//Get the decibel spectrogram
var decibelSpectrogram = new SpectrogramStandard(sonoConfig, dspOutput1.AmplitudeSpectrogram);
result.DecibelSpectrogram = decibelSpectrogram;
double[,] dbSpectrogramData = (double[, ])decibelSpectrogram.Data.Clone();
// IMAGE 2) DecibelSpectrogram
if (doDecibelSpectrogram)
{
var image3 = decibelSpectrogram.GetImageFullyAnnotated($"DECIBEL SPECTROGRAM ({sourceRecordingName})");
list.Add(image3);
}
if (doNoiseReducedSpectrogram || doExperimentalSpectrogram || doDifferenceSpectrogram)
{
sonoConfig.NoiseReductionType = disabledNoiseReductionType;
sonoConfig.NoiseReductionParameter = bgNoiseThreshold;
double[] spectralDecibelBgn = NoiseProfile.CalculateBackgroundNoise(decibelSpectrogram.Data);
decibelSpectrogram.Data = SNR.TruncateBgNoiseFromSpectrogram(decibelSpectrogram.Data, spectralDecibelBgn);
decibelSpectrogram.Data = SNR.RemoveNeighbourhoodBackgroundNoise(decibelSpectrogram.Data, nhThreshold: bgNoiseThreshold);
// IMAGE 3) DecibelSpectrogram - noise reduced
if (doNoiseReducedSpectrogram)
{
var image4 = decibelSpectrogram.GetImageFullyAnnotated($"DECIBEL SPECTROGRAM + Lamel noise subtraction. ({sourceRecordingName})");
list.Add(image4);
}
// IMAGE 4) EXPERIMENTAL Spectrogram
if (doExperimentalSpectrogram)
{
sonoConfig.NoiseReductionType = disabledNoiseReductionType;
var image5 = GetDecibelSpectrogram_Ridges(dbSpectrogramData, decibelSpectrogram, sourceRecordingName);
list.Add(image5);
}
// IMAGE 5) draw difference spectrogram
if (doDifferenceSpectrogram)
{
var differenceThreshold = configInfo.GetDoubleOrNull("DifferenceThreshold") ?? 3.0;
var image6 = GetDifferenceSpectrogram(dbSpectrogramData, differenceThreshold);
image6 = BaseSonogram.GetImageAnnotatedWithLinearHertzScale(image6, sampleRate, frameStep, $"DECIBEL DIFFERENCE SPECTROGRAM ({sourceRecordingName})");
list.Add(image6);
}
}
}
// IMAGE 6) Cepstral Spectrogram
if (doCepstralSpectrogram)
{
var image6 = GetCepstralSpectrogram(sonoConfig, recordingSegment, sourceRecordingName);
list.Add(image6);
}
// 7) AmplitudeSpectrogram_LocalContrastNormalization
if (doLcnSpectrogram)
{
var neighbourhoodSeconds = configInfo.GetDoubleOrNull("NeighbourhoodSeconds") ?? 0.5;
var lcnContrastParameter = configInfo.GetDoubleOrNull("LcnContrastLevel") ?? 0.4;
var image8 = GetLcnSpectrogram(sonoConfig, recordingSegment, sourceRecordingName, neighbourhoodSeconds, lcnContrastParameter);
list.Add(image8);
}
// 8) SOX SPECTROGRAM
//if (doSoxSpectrogram)
//{
//Log.Warn("SoX spectrogram set to true but is ignored when running as an IAnalyzer");
// The following parameters were once used to implement a sox spectrogram.
//bool makeSoxSonogram = configuration.GetBoolOrNull(AnalysisKeys.MakeSoxSonogram) ?? false;
//configDict[AnalysisKeys.SonogramTitle] = configuration[AnalysisKeys.SonogramTitle] ?? "Sonogram";
//configDict[AnalysisKeys.SonogramComment] = configuration[AnalysisKeys.SonogramComment] ?? "Sonogram produced using SOX";
//configDict[AnalysisKeys.SonogramColored] = configuration[AnalysisKeys.SonogramColored] ?? "false";
//configDict[AnalysisKeys.SonogramQuantisation] = configuration[AnalysisKeys.SonogramQuantisation] ?? "128";
//configDict[AnalysisKeys.AddTimeScale] = configuration[AnalysisKeys.AddTimeScale] ?? "true";
//configDict[AnalysisKeys.AddAxes] = configuration[AnalysisKeys.AddAxes] ?? "true";
//configDict[AnalysisKeys.AddSegmentationTrack] = configuration[AnalysisKeys.AddSegmentationTrack] ?? "true";
// var soxFile = new FileInfo(Path.Combine(output.FullName, sourceName + "SOX.png"));
// SpectrogramTools.MakeSonogramWithSox(sourceRecording, configDict, path2SoxSpectrogram);
// list.Add(image7);
//}
// COMBINE THE SPECTROGRAM IMAGES
result.CompositeImage = ImageTools.CombineImagesVertically(list);
return(result);
}