par2lar#

class diffsptk.ParcorCoefficientsToLogAreaRatio(par_order)[source]#

See this page for details.

Parameters:

par_orderint >= 0 [scalar]: Order of PARCOR, \(M\).

forward(k)[source]#

Convert PARCOR to LAR.

Parameters:

kTensor [shape=(…, M+1)]: PARCOR coefficients.

Returns:

ATensor [shape=(…, M+1)]: Log area ratio.

Examples

>>> k = diffsptk.ramp(1, 4) * 0.1
>>> par2lar = diffsptk.ParcorCoefficientsToLogAreaRatio(3)
>>> lar2par = diffsptk.LogAreaRatioToParcorCoefficients(3)
>>> k2 = lar2par(par2lar(k))
>>> k2
tensor([0.1000, 0.2000, 0.3000, 0.4000])