pyACA.FeatureSpectralSlope Namespace Reference

Functions
	FeatureSpectralSlope (X, f_s)
	computes the spectral slope from the magnitude spectrum

Function Documentation

FeatureSpectralSlope()

FeatureSpectralSlope	(		X,
			f_s )

computes the spectral slope from the magnitude spectrum

Parameters

X	spectrogram (dimension FFTLength X Observations)
f_s	sample rate of audio data

Returns

vssl: spectral slope

Definition at line 13 of file FeatureSpectralSlope.py.

def FeatureSpectralSlope(X, f_s):
 
    # compute mean
    vsc = FeatureSpectralCentroid(X, f_s) * 2 / f_s * (X.shape[0] - 1)
 
    # compute index vector
    kmu = np.arange(0, X.shape[0]) - (X.shape[0]+1) / 2
 
    # compute slope
    X = X - vsc
    vssl = np.dot(kmu, X) / np.dot(kmu, kmu)
 
    return vssl