gnorm#
- class diffsptk.GeneralizedCepstrumGainNormalization(cep_order, gamma=0, c=None)[source]#
See this page for details.
- Parameters:
- cep_orderint >= 0
Order of cepstrum, \(M\).
- gammafloat in [-1, 1]
Gamma, \(\gamma\).
- cint >= 1 or None
Number of stages.
References
[1]T. Kobayashi et al., “Spectral analysis using generalized cepstrum,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 32, no. 5, pp. 1087-1089, 1984.
- forward(x)[source]#
Perform cepstrum gain normalization.
- Parameters:
- xTensor [shape=(…, M+1)]
Generalized cepstrum.
- Returns:
- outTensor [shape=(…, M+1)]
Normalized generalized cepstrum.
Examples
>>> x = diffsptk.ramp(1, 4) >>> gnorm = diffsptk.GeneralizedCepstrumGainNormalization(3, c=2) >>> y = gnorm(x) >>> y tensor([2.2500, 1.3333, 2.0000, 2.6667])