Class PcaWhitening
Assembly: AudioAnalysisTools.dll
public static class PcaWhitening
Methods
|
Improve this Doc
View Source
Build the Projection Matrix
To do so, we need eigenVectors and the number of columns of the projected data
which is the number of outputs (principle components) used to transform the data.
Declaration
public static double[, ] GetProjectionMatrix(double[, ] eigenVector, int numberOfOutputs)
Parameters
Type |
Name |
Description |
Double[,] |
eigenVector |
|
Int32 |
numberOfOutputs |
|
Returns
|
Improve this Doc
View Source
10-percentile Noise Reduction.
Declaration
public static double[, ] NoiseReduction(double[, ] matrix)
Parameters
Type |
Name |
Description |
Double[,] |
matrix |
|
Returns
|
Improve this Doc
View Source
reconstruct the spectrogram using sequential patches and the projection matrix.
Declaration
public static double[, ] ReconstructSpectrogram(double[, ] projectionMatrix, double[, ] sequentialPatchMatrix, double[, ] eigenVectors, int numberOfComponents)
Parameters
Type |
Name |
Description |
Double[,] |
projectionMatrix |
|
Double[,] |
sequentialPatchMatrix |
|
Double[,] |
eigenVectors |
|
Int32 |
numberOfComponents |
|
Returns
|
Improve this Doc
View Source
revert a set of projected data into its original space
the output of the "Revert(Double[][])" method in Accord did not make sense.
however, we use its API to do so.
Declaration
public static double[, ] Revert(double[, ] projectedData, double[, ] eigenVectors, int numberOfComponents)
Parameters
Type |
Name |
Description |
Double[,] |
projectedData |
|
Double[,] |
eigenVectors |
|
Int32 |
numberOfComponents |
|
Returns
|
Improve this Doc
View Source
Declaration
public static PcaWhitening.Output Whitening(bool doWhitening, double[, ] matrix)
Parameters
Returns