mgc2mgc#

class diffsptk.MelGeneralizedCepstrumToMelGeneralizedCepstrum(in_order, out_order, in_alpha=0, out_alpha=0, in_gamma=0, out_gamma=0, in_norm=False, out_norm=False, in_mul=False, out_mul=False, n_fft=512)[source]#

See this page for details.

Parameters:

in_orderint >= 0: The order of the input cepstrum, \(M_1\).
out_orderint >= 0: The order of the output cepstrum, \(M_2\).
in_alphafloat in (-1, 1): The input alpha, \(\alpha_1\).
out_alphafloat in (-1, 1): The output alpha, \(\alpha_2\).
in_gammafloat in [-1, 1]: The input gamma, \(\gamma_1\).
out_gammafloat in [-1, 1]: The output gamma, \(\gamma_2\).
in_normbool: If True, the input is assumed to be normalized.
out_normbool: If True, the output is assumed to be normalized.
in_mulbool: If True, the input is assumed to be gamma-multiplied.
out_mulbool: If True, the output is assumed to be gamma-multiplied.
n_fftint >> M1, M2: The number of FFT bins. Accurate conversion requires a large value.

References

[1]

K. Tokuda et al., “Mel-generalized cepstral analysis - A unified approach to speech spectral estimation”, Proceedings of ICSLP, pp. 1043-1046, 1996.

forward(mc)[source]#

Convert mel-generalized cepstrum to mel-generalized cepstrum.

Parameters:

mcTensor [shape=(…, M1+1)]: The input mel-cepstrum.

Returns:

outTensor [shape=(…, M2+1)]: The output mel-cepstrum.

Examples

>>> c1 = diffsptk.ramp(3)
>>> mgc2mgc = diffsptk.MelGeneralizedCepstrumToMelGeneralizedCepstrum(3, 4, 0.1)
>>> c2 = mgc2mgc(c1)
>>> c2
tensor([-0.0830,  0.6831,  1.1464,  3.1334,  0.9063])

diffsptk.functional.mgc2mgc(mc, out_order, in_alpha=0, out_alpha=0, in_gamma=0, out_gamma=0, in_norm=False, out_norm=False, in_mul=False, out_mul=False, n_fft=512)[source]#

Convert mel-generalized cepstrum to mel-generalized cepstrum.

Parameters:

mcTensor [shape=(…, M1+1)]: The input mel-cepstrum.
out_orderint >= 0: The order of the output cepstrum, \(M_2\).
in_alphafloat in (-1, 1): The input alpha, \(\alpha_1\).
out_alphafloat in (-1, 1): The output alpha, \(\alpha_2\).
in_gammafloat in [-1, 1]: The input gamma, \(\gamma_1\).
out_gammafloat in [-1, 1]: The output gamma, \(\gamma_2\).
in_normbool: If True, the input is assumed to be normalized.
out_normbool: If True, the output is assumed to be normalized.
in_mulbool: If True, the input is assumed to be gamma-multiplied.
out_mulbool: If True, the output is assumed to be gamma-multiplied.
n_fftint >> M1, M2: The number of FFT bins.

Returns:

outTensor [shape=(…, M2+1)]: The converted mel-cepstrum.

mgc2mgc#

This Page