Class SpectralClustering

Inheritance

Object

SpectralClustering

Inherited Members

Object.Equals(Object)

Object.Equals(Object, Object)

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Object.ReferenceEquals(Object, Object)

Object.ToString()

Namespace: AudioAnalysisTools

Assembly: AudioAnalysisTools.dll

Syntax

public static class SpectralClustering

Fields

DefaultBinaryThreshold

Declaration

public const double DefaultBinaryThreshold = 0.12

Field Value

Type	Description
Double

DefaultBinaryThresholdInDecibels

Declaration

public const double DefaultBinaryThresholdInDecibels = 6

Field Value

Type	Description
Double

DefaultHitThreshold

Declaration

public const int DefaultHitThreshold = 3

Field Value

Type	Description
Int32

DefaultReductionFactor

Declaration

public const int DefaultReductionFactor = 3

Field Value

Type	Description
Int32

DefaultRowSumThreshold

Declaration

public const double DefaultRowSumThreshold = 2

Field Value

Type	Description
Double

Methods

AssembleClusterSpectrogram(Double[,], Int32, ClusterInfo, SpectralClustering.TrainingDataInfo)

this method is used only to visualize the clusters and which frames they hit. Create a new spectrogram of same size as the passed spectrogram. Later on it is superimposed on a detailed spectrogram.

Declaration

public static int[, ] AssembleClusterSpectrogram(double[, ] spectrogram, int lowerBinBound, ClusterInfo clusterInfo, SpectralClustering.TrainingDataInfo data)

Parameters

Type	Name	Description
Double[,]	spectrogram	spectrogram used to derive spectral richness indices. Orientation is row=frame.
Int32	lowerBinBound	bottom N freq bins are excluded because likely to contain traffic and wind noise.
ClusterInfo	clusterInfo	information about accumulated clusters.
SpectralClustering.TrainingDataInfo	data	training data.

Returns

Type	Description
Int32[,]

ClusterAnalysis(List<Double[]>, Double, Int32, Boolean[])

Clusters the spectra in a spectrogram. USED to determine the spectral diversity and persistence of spectral types. The spectrogram is passed as a matrix. Note that the spectrogram is in amplitude values in [0, 1].

Declaration

public static ClusterInfo ClusterAnalysis(List<double[]> trainingData, double wtThreshold, int hitThreshold, bool[] selectedFrames)

Parameters

Type	Name	Description
List<Double[]>	trainingData
Double	wtThreshold
Int32	hitThreshold
Boolean[]	selectedFrames

Returns

Type	Description
ClusterInfo

ClusterTheSpectra(Double[,], Int32, Int32, Double)

This CLUSTERING method is called only from IndexCalculate.cs and TESTMETHOD_SpectralClustering(string wavFilePath, string outputDir, int frameSize) It estimates the number of spectral clusters in a spectrogram, and outputs two summary indices: cluster count (also called spectral diversity) and the threegram count. IMPORTANT NOTE: The passed spectrogram MUST be already noise reduced. This clustering algorithm is a highly reduced version of binary ART, Adaptive resonance Theory, designed for speed.

Declaration

public static ClusterInfo ClusterTheSpectra(double[, ] spectrogram, int lowerBinBound, int upperBinBound, double binaryThreshold)

Parameters

Type	Name	Description
Double[,]	spectrogram	a collection of spectra that are to be clustered.
Int32	lowerBinBound	lower end of the bird-band.
Int32	upperBinBound	upper end of the bird-band.
Double	binaryThreshold	used to convert real value spectrum to binary.

Returns

Type	Description
ClusterInfo

ConvertOverlayToSpectrogramSize(Double[,], Int32, Int32, Int32)

Declaration

public static double[, ] ConvertOverlayToSpectrogramSize(double[, ] dataMatrix, int lowerBinBound, int newRowCount, int newColumnCount)

Parameters

Type	Name	Description
Double[,]	dataMatrix
Int32	lowerBinBound
Int32	newRowCount
Int32	newColumnCount

Returns

Type	Description
Double[,]

DrawClusterSpectrogram(BaseSonogram, ClusterInfo, SpectralClustering.TrainingDataInfo, Int32)

Overlays the spectral cluster IDs on a spectrogram from which the clusters derived.

Declaration

public static Image DrawClusterSpectrogram(BaseSonogram sonogram, ClusterInfo clusterInfo, SpectralClustering.TrainingDataInfo data, int lowerBinBound)

Parameters

Type	Name	Description
BaseSonogram	sonogram
ClusterInfo	clusterInfo
SpectralClustering.TrainingDataInfo	data
Int32	lowerBinBound

Returns

Type	Description
SixLabors.ImageSharp.Image

DrawSonogram(BaseSonogram, Plot, List<AcousticEvent>, Double, Double[,])

Declaration

public static Image DrawSonogram(BaseSonogram sonogram, Plot scores, List<AcousticEvent> poi, double eventThreshold, double[, ] overlay)

Parameters

Type	Name	Description
BaseSonogram	sonogram
Plot	scores
List<AcousticEvent>	poi
Double	eventThreshold
Double[,]	overlay

Returns

Type	Description
SixLabors.ImageSharp.Image

GetAmplitudeSpectrogramNoiseReduced(AudioRecording, Int32)

Declaration

public static double[, ] GetAmplitudeSpectrogramNoiseReduced(AudioRecording recording, int frameSize)

Parameters

Type	Name	Description
AudioRecording	recording
Int32	frameSize

Returns

Type	Description
Double[,]

GetDecibelSpectrogramNoiseReduced(AudioRecording, Int32)

Declaration

public static double[, ] GetDecibelSpectrogramNoiseReduced(AudioRecording recording, int frameSize)

Parameters

Type	Name	Description
AudioRecording	recording
Int32	frameSize

Returns

Type	Description
Double[,]

GetStandardSpectrogram(AudioRecording, Int32)

Declaration

public static SpectrogramStandard GetStandardSpectrogram(AudioRecording recording, int frameSize)

Parameters

Type	Name	Description
AudioRecording	recording
Int32	frameSize

Returns

Type	Description
SpectrogramStandard

GetTrainingDataForClustering(Double[,], SpectralClustering.ClusteringParameters)

First convert spectrogram to Binary using threshold. An amplitude threshold of 0.03 = -30 dB. An amplitude threhold of 0.05 = -26dB.

Declaration

public static SpectralClustering.TrainingDataInfo GetTrainingDataForClustering(double[, ] spectrogram, SpectralClustering.ClusteringParameters cp)

Parameters

Type	Name	Description
Double[,]	spectrogram
SpectralClustering.ClusteringParameters	cp

Returns

Type	Description
SpectralClustering.TrainingDataInfo

IncludeSpectrumInSpectrogram(Double[,], Int32, Double[], Int32)

Declaration

public static void IncludeSpectrumInSpectrogram(double[, ] trainingDataAsBinarySpectrogram, int row, double[] binarySpectrum, int reductionFactor)

Parameters

Type	Name	Description
Double[,]	trainingDataAsBinarySpectrogram
Int32	row
Double[]	binarySpectrum
Int32	reductionFactor

OutputClusterAndWeightInfo(Int32[], List<Double[]>, String)

displays a histogram of cluster counts. the argument clusters is an array of integer. Indicates cluster assigned to each binary frame.

Declaration

public static void OutputClusterAndWeightInfo(int[] clusters, List<double[]> wts, string imagePath)

Parameters

Type	Name	Description
Int32[]	clusters
List<Double[]>	wts
String	imagePath

RestoreFullLengthSpectrum(Double[], Int32, Int32)

Declaration

public static double[] RestoreFullLengthSpectrum(double[] ipSpectrum, int fullLength, int lowOffset)

Parameters

Type	Name	Description
Double[]	ipSpectrum
Int32	fullLength
Int32	lowOffset

Returns

Type	Description
Double[]

SaveAndViewSpectrogramImage(Image, String, String, String)

Declaration

public static void SaveAndViewSpectrogramImage(Image image, string opDir, string fName, string imageViewer)

Parameters

Type	Name	Description
SixLabors.ImageSharp.Image	image
String	opDir
String	fName
String	imageViewer

SuperImposeHitsOnSpectrogram(Double[,], Int32, Double[,])

Declaration

public static double[, ] SuperImposeHitsOnSpectrogram(double[, ] spectrogram, int lowBinBound, double[, ] trainingDataAsSpectrogram)

Parameters

Type	Name	Description
Double[,]	spectrogram
Int32	lowBinBound
Double[,]	trainingDataAsSpectrogram

Returns

Type	Description
Double[,]

TESTMETHOD_SpectralClustering()

Declaration

public static void TESTMETHOD_SpectralClustering()

TESTMETHOD_SpectralClustering(String, String, Int32)

This method was set up as a TESTMETHOD in May 2017 but has not yet been debugged. It was transferred from Sandpit.cls. It is several years old. Updated May 2017.

Declaration

public static void TESTMETHOD_SpectralClustering(string wavFilePath, string outputDir, int frameSize)

Parameters

Type	Name	Description
String	wavFilePath
String	outputDir
Int32	frameSize