csm2acr#
- class diffsptk.CompositeSinusoidalModelCoefficientsToAutocorrelation(csm_order)[source]#
See this page for details.
- Parameters:
- csm_orderint >= 0
Order of CSM coefficients, \(M\).
References
[1]S. Sagayama et al., “Duality theory of composite sinusoidal modeling and linear prediction,” Proceedings of ICASSP, pp. 1261-1264, 1986.
- forward(c)[source]#
Convert CSM coefficients to autocorrelation.
- Parameters:
- cTensor [shape=(…, M+1)]
Composite sinusoidal model coefficients.
- Returns:
- outTensor [shape=(…, M+1)]
Autocorrelation.
Examples
>>> x = diffsptk.nrand(4) >>> acorr = diffsptk.Autocorrelation(5, 3) >>> acr2csm = diffsptk.AutocorrelationToCompositeSinusoidalModelCoefficients(3) >>> csm2acr = diffsptk.CompositeSinusoidalModelCoefficientsToAutocorrelation(3) >>> r = acorr(x) >>> r tensor([ 8.8894, -0.1102, -4.1748, 0.7501]) >>> r2 = csm2acr(acr2csm(r)) >>> r2 tensor([ 8.8894, -0.1102, -4.1748, 0.7501])