pnorm#

class diffsptk.MelCepstrumPowerNormalization(cep_order, alpha=0, ir_length=128)[source]#

See this page for details.

Parameters:

cep_orderint >= 0: Order of cepstrum, \(M\).
alphafloat in (-1, 1): Frequency warping factor, \(\alpha\).
ir_lengthint >= 1: Length of impulse response.

forward(x)[source]#

Perform cepstrum power normalization.

Parameters:

xTensor [shape=(…, M+1)]: Input cepstrum.

Returns:

outTensor [shape=(…, M+2)]: Power-normalized cepstrum.

Examples

>>> x = diffsptk.ramp(1, 4)
>>> pnorm = diffsptk.MelCepstrumPowerNormalization(3, alpha=0.1)
>>> y = pnorm(x)
>>> y
tensor([ 8.2942, -7.2942,  2.0000,  3.0000,  4.0000])

diffsptk.functional.pnorm(x, alpha=0, ir_length=128)[source]#

Perform cepstrum power normalization.

Parameters:

xTensor [shape=(…, M+1)]: Input cepstrum.
alphafloat in (-1, 1): Frequency warping factor, \(\alpha\).
ir_lengthint >= 1: Length of impulse response.

Returns:

outTensor [shape=(…, M+2)]: Power-normalized cepstrum.