def interval_histogram_comb(activations, alpha, min_tau=1, max_tau=None):
"""
Compute the interval histogram of the given (beat) activation function via
a bank of resonating comb filters as in [1]_.
Parameters
----------
activations : numpy array
Beat activation function.
alpha : float or numpy array
Scaling factor for the comb filter; if only a single value is given,
the same scaling factor for all delays is assumed.
min_tau : int, optional
Minimal delay for the comb filter [frames].
max_tau : int, optional
Maximal delta for comb filter [frames].
Returns
-------
histogram_bins : numpy array
Bins of the tempo histogram.
histogram_delays : numpy array
Corresponding delays [frames].
References
----------
.. [1] Sebastian Böck, Florian Krebs and Gerhard Widmer,
"Accurate Tempo Estimation based on Recurrent Neural Networks and
Resonating Comb Filters",
Proceedings of the 16th International Society for Music Information
Retrieval Conference (ISMIR), 2015.
"""
# import comb filter
from madmom.audio.comb_filters import CombFilterbankProcessor
# set the maximum delay
if max_tau is None:
max_tau = len(activations) - min_tau
# get the range of taus
taus = np.arange(min_tau, max_tau + 1)
# create a comb filter bank instance
cfb = CombFilterbankProcessor('backward', taus, alpha)
if activations.ndim in (1, 2):
# apply a bank of comb filters
act = cfb.process(activations)
# determine the tau with the highest value for each time step
act_max = act == np.max(act, axis=-1)[..., np.newaxis]
# sum up these maxima weighted by the activation value to yield the
# histogram bin values
histogram_bins = np.sum(act * act_max, axis=0)
else:
raise NotImplementedError('too many dimensions for comb filter '
'interval histogram calculation.')
# return the histogram
return histogram_bins, taus
def interval_histogram_comb(activations, alpha, min_tau=1, max_tau=None):
"""
Compute the interval histogram of the given activation function via a
bank of comb filters.
:param activations: the activation function
:param alpha: scaling factor for the comb filter
:param min_tau: minimal delta for correlation function [frames]
:param max_tau: maximal delta for correlation function [frames]
:return: histogram
"Accurate Tempo Estimation based on Recurrent Neural Networks and
Resonating Comb Filters"
Sebastian Böck, Florian Krebs and Gerhard Widmer
Proceedings of the 16th International Society for Music Information
Retrieval Conference (ISMIR), 2015.
"""
# import comb filter
from madmom.audio.comb_filters import CombFilterbankProcessor
# set the maximum delay
if max_tau is None:
max_tau = len(activations) - min_tau
# get the range of taus
taus = np.arange(min_tau, max_tau + 1)
# create a comb filter bank instance
cfb = CombFilterbankProcessor('backward', taus, alpha)
# activations = np.minimum(0.9, activations)
if activations.ndim == 1:
# apply a bank of comb filters
act = cfb.process(activations)
# determine the tau with the highest value for each time step
# sum up the maxima to yield the histogram bin values
histogram_bins = np.sum(act * (act == np.max(act, axis=0)), axis=1)
elif activations.ndim == 2:
histogram_bins = np.zeros_like(taus)
# do the same as above for all bands
for i in range(activations.shape[1]):
# apply a bank of comb filters
act = cfb.process(activations[:, i])
# determine the tau with the highest value for each time step
# sum up the maxima to yield the histogram bin values
histogram_bins += np.sum(act * (act == np.max(act, axis=0)),
axis=1)
else:
raise NotImplementedError('too many dimensions for comb filter tempo '
'detection.')
# return the histogram
return histogram_bins, taus
