pqmf#

diffsptk.PQMF#: alias of PseudoQuadratureMirrorFilterBanks

class diffsptk.PseudoQuadratureMirrorFilterBanks(n_band, filter_order, alpha=100, learnable=False, **kwargs)[source]#

See this page for details.

Parameters:

n_bandint >= 1 [scalar]: Number of subbands, \(K\).
filter_orderint >= 2 [scalar]: Order of filter, \(M\).
alphafloat > 0 [scalar]: Stopband attenuation in dB.
learnablebool [scalar]: Whether to make filter-bank coefficients learnable.
**kwargsadditional keyword arguments: Parameters to find optimal filter-bank coefficients.

forward(x)[source]#

Decompose waveform into subband waveforms.

Parameters:

xTensor [shape=(B, 1, T) or (B, T) or (T,)]: Original waveform.

Returns:

yTensor [shape=(B, K, T)]: Subband waveforms.

Examples

>>> x = diffsptk.ramp(0, 1, 0.25)
>>> pqmf = diffsptk.PQMF(2, 10)
>>> y = pmqf(x)
>>> y
tensor([[[ 0.1605,  0.4266,  0.6927,  0.9199,  1.0302],
         [-0.0775, -0.0493, -0.0211, -0.0318,  0.0743]]])