pyACA.FeatureSpectralDecrease Namespace Reference

Functions
	FeatureSpectralDecrease (X, f_s)
	computes the spectral decrease from the magnitude spectrum

Function Documentation

FeatureSpectralDecrease()

FeatureSpectralDecrease	(		X,
			f_s )

computes the spectral decrease from the magnitude spectrum

Parameters

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

Returns

vsd: spectral decrease

Definition at line 12 of file FeatureSpectralDecrease.py.

def FeatureSpectralDecrease(X, f_s):
 
    # compute index vector
    kinv = np.arange(0, X.shape[0])
    kinv[0] = 1
    kinv = 1 / kinv
 
    norm = X[1:].sum(axis=0, keepdims=True)
    norm[norm == 0] = 1
 
    # compute slope
    vsd = np.dot(kinv, X - X[0]) / norm
 
    return np.squeeze(vsd, axis=0)