pyACA.NoveltyHainsworth Namespace Reference

Functions
	NoveltyHainsworth (X, f_s)
	computes the novelty measure introduced by Hainsworth

Function Documentation

NoveltyHainsworth()

NoveltyHainsworth	(		X,
			f_s )

computes the novelty measure introduced by Hainsworth

Parameters

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

Returns

d_hai: novelty measure

Definition at line 12 of file NoveltyHainsworth.py.

def NoveltyHainsworth(X, f_s):
 
    epsilon = 1e-5
 
    # difference spectrum (set first diff to zero)
    X = np.c_[X[:, 0], X]
    X[X <= 0] = epsilon
 
    afDiff = np.log2(X[:, np.arange(1, X.shape[1])] / X[:, np.arange(0, X.shape[1] - 1)])
 
    # flux
    d_hai = np.sum(afDiff, axis=0) / X.shape[0]
 
    return d_hai