acr2csm#

class diffsptk.AutocorrelationToCompositeSinusoidalModelCoefficients(acr_order: int, device: device | None = None, dtype: dtype | None = None)[source]#

See this page for details.

Parameters:

acr_orderint >= 0: The order of the autocorrelation, \(M\).
devicetorch.device or None: The device of this module.
dtypetorch.dtype or None: The data type of this module.

References

[1]

S. Sagayama et al., “Duality theory of composite sinusoidal modeling and linear prediction,” Proceedings of ICASSP, pp. 1261-1264, 1986.

forward(r: Tensor) → Tensor[source]#

Convert autocorrelation to CSM coefficients.

Parameters:

rTensor [shape=(…, M+1)]: The autocorrelation.

Returns:

outTensor [shape=(…, M+1)]: The CSM coefficients.

Examples

>>> import diffsptk
>>> acorr = diffsptk.Autocorrelation(5, 3)
>>> acr2csm = diffsptk.AutocorrelationToCompositeSinusoidalModelCoefficients(3)
>>> x = diffsptk.ramp(4)
>>> c = acr2csm(acorr(x))
>>> c
tensor([ 0.5261,  2.1403, 25.7668,  4.2332])

diffsptk.functional.acr2csm(r: Tensor) → Tensor[source]#

Convert autocorrelation to CSM coefficients.

Parameters:

rTensor [shape=(…, M+1)]: The autocorrelation.

Returns:

outTensor [shape=(…, M+1)]: The CSM coefficients.