// OTHER CONSTANTS
//private const string ImageViewer = @"C:\Windows\system32\mspaint.exe";
/// <summary>
/// Do your analysis. This method is called once per segment (typically one-minute segments).
/// </summary>
public override RecognizerResults Recognize(AudioRecording recording, Config configuration, TimeSpan segmentStartOffset, Lazy <IndexCalculateResult[]> getSpectralIndexes, DirectoryInfo outputDirectory, int?imageWidth)
{
var recognizerConfig = new LitoriaBicolorConfig();
recognizerConfig.ReadConfigFile(configuration);
if (recording.WavReader.SampleRate != 22050)
{
throw new InvalidOperationException("Requires a 22050Hz file");
}
TimeSpan recordingDuration = recording.WavReader.Time;
//// ignore oscillations below this threshold freq
//int minOscilFreq = (int)configuration[AnalysisKeys.MinOscilFreq];
//// ignore oscillations above this threshold freq
int maxOscilRate = (int)Math.Ceiling(1 / recognizerConfig.MinPeriod);
// this default framesize seems to work
const int frameSize = 128;
double windowOverlap = Oscillations2012.CalculateRequiredFrameOverlap(
recording.SampleRate,
frameSize,
maxOscilRate);
// i: MAKE SONOGRAM
var sonoConfig = new SonogramConfig
{
SourceFName = recording.BaseName,
//set default values - ignore those set by user
WindowSize = frameSize,
WindowOverlap = windowOverlap,
// the default window is HAMMING
//WindowFunction = WindowFunctions.HANNING.ToString(),
//WindowFunction = WindowFunctions.NONE.ToString(),
// if do not use noise reduction can get a more sensitive recogniser.
//NoiseReductionType = NoiseReductionType.NONE,
NoiseReductionType = SNR.KeyToNoiseReductionType("STANDARD"),
};
//#############################################################################################################################################
//DO THE ANALYSIS AND RECOVER SCORES OR WHATEVER
var results = Analysis(recording, sonoConfig, recognizerConfig, MainEntry.InDEBUG, segmentStartOffset);
//######################################################################
if (results == null)
{
return(null); //nothing to process
}
var sonogram = results.Item1;
var hits = results.Item2;
var scoreArray = results.Item3;
var predictedEvents = results.Item4;
var debugImage = results.Item5;
//#############################################################################################################################################
var debugPath = outputDirectory.Combine(FilenameHelpers.AnalysisResultName(Path.GetFileNameWithoutExtension(recording.BaseName), this.SpeciesName, "png", "DebugSpectrogram"));
debugImage.Save(debugPath.FullName);
// Prune events here if erquired i.e. remove those below threshold score if this not already done. See other recognizers.
foreach (AcousticEvent ae in predictedEvents)
{
// add additional info
ae.Name = recognizerConfig.AbbreviatedSpeciesName;
ae.SpeciesName = recognizerConfig.SpeciesName;
ae.SegmentStartSeconds = segmentStartOffset.TotalSeconds;
ae.SegmentDurationSeconds = recordingDuration.TotalSeconds;
}
var plot = new Plot(this.DisplayName, scoreArray, recognizerConfig.EventThreshold);
return(new RecognizerResults()
{
Sonogram = sonogram,
Hits = hits,
Plots = plot.AsList(),
Events = predictedEvents,
});
}
/// <summary>
/// THE KEY ANALYSIS METHOD.
/// </summary>
public static Tuple <BaseSonogram, double[, ], double[], List <AcousticEvent>, Image> Analysis(
AudioRecording recording,
SonogramConfig sonoConfig,
LitoriaBicolorConfig lbConfig,
bool drawDebugImage,
TimeSpan segmentStartOffset)
{
double decibelThreshold = lbConfig.DecibelThreshold; //dB
double intensityThreshold = lbConfig.IntensityThreshold;
//double eventThreshold = lbConfig.EventThreshold; //in 0-1
if (recording == null)
{
LoggedConsole.WriteLine("AudioRecording == null. Analysis not possible.");
return(null);
}
//i: MAKE SONOGRAM
//TimeSpan tsRecordingtDuration = recording.Duration();
int sr = recording.SampleRate;
double freqBinWidth = sr / (double)sonoConfig.WindowSize;
double framesPerSecond = freqBinWidth;
// duration of DCT in seconds - want it to be about 3X or 4X the expected maximum period
double dctDuration = 3 * lbConfig.MaxPeriod;
// duration of DCT in frames
int dctLength = (int)Math.Round(framesPerSecond * dctDuration);
// set up the cosine coefficients
double[,] cosines = MFCCStuff.Cosines(dctLength, dctLength);
int upperBandMinBin = (int)Math.Round(lbConfig.UpperBandMinHz / freqBinWidth) + 1;
int upperBandMaxBin = (int)Math.Round(lbConfig.UpperBandMaxHz / freqBinWidth) + 1;
int lowerBandMinBin = (int)Math.Round(lbConfig.LowerBandMinHz / freqBinWidth) + 1;
int lowerBandMaxBin = (int)Math.Round(lbConfig.LowerBandMaxHz / freqBinWidth) + 1;
BaseSonogram sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
int rowCount = sonogram.Data.GetLength(0);
int colCount = sonogram.Data.GetLength(1);
double[] lowerArray = MatrixTools.GetRowAveragesOfSubmatrix(sonogram.Data, 0, lowerBandMinBin, rowCount - 1, lowerBandMaxBin);
double[] upperArray = MatrixTools.GetRowAveragesOfSubmatrix(sonogram.Data, 0, upperBandMinBin, rowCount - 1, upperBandMaxBin);
//lowerArray = DataTools.filterMovingAverage(lowerArray, 3);
//upperArray = DataTools.filterMovingAverage(upperArray, 3);
double[] amplitudeScores = DataTools.SumMinusDifference(lowerArray, upperArray);
double[] differenceScores = DspFilters.PreEmphasis(amplitudeScores, 1.0);
// Could smooth here rather than above. Above seemed slightly better?
amplitudeScores = DataTools.filterMovingAverage(amplitudeScores, 7);
differenceScores = DataTools.filterMovingAverage(differenceScores, 7);
//iii: CONVERT decibel sum-diff SCORES TO ACOUSTIC EVENTS
var predictedEvents = AcousticEvent.ConvertScoreArray2Events(
amplitudeScores,
lbConfig.LowerBandMinHz,
lbConfig.UpperBandMaxHz,
sonogram.FramesPerSecond,
freqBinWidth,
decibelThreshold,
lbConfig.MinDuration,
lbConfig.MaxDuration,
segmentStartOffset);
for (int i = 0; i < differenceScores.Length; i++)
{
if (differenceScores[i] < 1.0)
{
differenceScores[i] = 0.0;
}
}
// init the score array
double[] scores = new double[rowCount];
//iii: CONVERT SCORES TO ACOUSTIC EVENTS
// var hits = new double[rowCount, colCount];
double[,] hits = null;
// init confirmed events
var confirmedEvents = new List <AcousticEvent>();
// add names into the returned events
foreach (var ae in predictedEvents)
{
//rowtop, rowWidth
int eventStart = ae.Oblong.RowTop;
int eventWidth = ae.Oblong.RowWidth;
int step = 2;
double maximumIntensity = 0.0;
// scan the event to get oscillation period and intensity
for (int i = eventStart - (dctLength / 2); i < eventStart + eventWidth - (dctLength / 2); i += step)
{
// Look for oscillations in the difference array
double[] differenceArray = DataTools.Subarray(differenceScores, i, dctLength);
Oscillations2014.GetOscillationUsingDct(differenceArray, framesPerSecond, cosines, out var oscilFreq, out var period, out var intensity);
bool periodWithinBounds = period > lbConfig.MinPeriod && period < lbConfig.MaxPeriod;
//Console.WriteLine($"step={i} period={period:f4}");
if (!periodWithinBounds)
{
continue;
}
// lay down score for sample length
for (int j = 0; j < dctLength; j++)
{
if (scores[i + j] < intensity)
{
scores[i + j] = intensity;
}
}
if (maximumIntensity < intensity)
{
maximumIntensity = intensity;
}
}
// add abbreviatedSpeciesName into event
if (maximumIntensity >= intensityThreshold)
{
ae.Name = "L.b";
ae.Score_MaxInEvent = maximumIntensity;
confirmedEvents.Add(ae);
}
}
//######################################################################
// calculate the cosine similarity scores
var scorePlot = new Plot(lbConfig.SpeciesName, scores, intensityThreshold);
//DEBUG IMAGE this recognizer only. MUST set false for deployment.
Image debugImage = null;
if (drawDebugImage)
{
// display a variety of debug score arrays
//DataTools.Normalise(scores, eventDecibelThreshold, out normalisedScores, out normalisedThreshold);
//var debugPlot = new Plot("Score", normalisedScores, normalisedThreshold);
//DataTools.Normalise(upperArray, eventDecibelThreshold, out normalisedScores, out normalisedThreshold);
//var upperPlot = new Plot("Upper", normalisedScores, normalisedThreshold);
//DataTools.Normalise(lowerArray, eventDecibelThreshold, out normalisedScores, out normalisedThreshold);
//var lowerPlot = new Plot("Lower", normalisedScores, normalisedThreshold);
DataTools.Normalise(amplitudeScores, decibelThreshold, out var normalisedScores, out var normalisedThreshold);
var sumDiffPlot = new Plot("SumMinusDifference", normalisedScores, normalisedThreshold);
DataTools.Normalise(differenceScores, 3.0, out normalisedScores, out normalisedThreshold);
var differencePlot = new Plot("Difference", normalisedScores, normalisedThreshold);
var debugPlots = new List <Plot> {
scorePlot, sumDiffPlot, differencePlot
};
// other debug plots
//var debugPlots = new List<Plot> { scorePlot, upperPlot, lowerPlot, sumDiffPlot, differencePlot };
debugImage = DisplayDebugImage(sonogram, confirmedEvents, debugPlots, hits);
}
// return new sonogram because it makes for more easy interpretation of the image
var returnSonoConfig = new SonogramConfig
{
SourceFName = recording.BaseName,
WindowSize = 512,
WindowOverlap = 0,
// the default window is HAMMING
//WindowFunction = WindowFunctions.HANNING.ToString(),
//WindowFunction = WindowFunctions.NONE.ToString(),
// if do not use noise reduction can get a more sensitive recogniser.
//NoiseReductionType = NoiseReductionType.NONE,
NoiseReductionType = SNR.KeyToNoiseReductionType("STANDARD"),
};
BaseSonogram returnSonogram = new SpectrogramStandard(returnSonoConfig, recording.WavReader);
return(Tuple.Create(returnSonogram, hits, scores, confirmedEvents, debugImage));
} //Analysis()
