excite

class diffsptk.ExcitationGeneration(frame_period: int, *, voiced_region: str = 'pulse', unvoiced_region: str = 'gauss', polarity: str = 'auto', init_phase: str = 'zeros')

See this page for details.

Parameters:

frame_periodint >= 1

The frame period in samples, \(P\).

voiced_region[‘pulse’, ‘sinusoidal’, ‘sawtooth’, ‘inverted-sawtooth’, ‘triangle’, ‘square’]

The type of voiced region.

unvoiced_region[‘zeros’, ‘gauss’]

The type of unvoiced region.

polarity[‘auto’, ‘unipolar’, ‘bipolar’]

The polarity.

init_phase[‘zeros’, ‘random’]

The initial phase.

forward(p: Tensor) → Tensor

Generate a simple excitation signal.

Parameters:

pTensor [shape=(…, N)]

The pitch in seconds.

Returns:

outTensor [shape=(…, NxP)]

The excitation signal.

Examples

>>> p = torch.tensor([2.0, 3.0])
>>> excite = diffsptk.ExcitationGeneration(3)
>>> e = excite(p)
>>> e
tensor([1.4142, 0.0000, 1.6330, 0.0000, 0.0000, 1.7321])

diffsptk.functional.excite(p: Tensor, frame_period: int = 80, *, voiced_region: str = 'pulse', unvoiced_region: str = 'gauss', polarity: str = 'auto', init_phase: str = 'zeros') → Tensor

Generate a simple excitation signal.

Parameters:

pTensor [shape=(…, N)]

The pitch in seconds.

frame_periodint >= 1

The frame period in samples, \(P\).

voiced_region[‘pulse’, ‘sinusoidal’, ‘sawtooth’, ‘inverted-sawtooth’, ‘triangle’, ‘square’]

The type of voiced region.

unvoiced_region[‘zeros’, ‘gauss’]

The type of unvoiced region.

polarity[‘auto’, ‘unipolar’, ‘bipolar’]

The polarity.

init_phase[‘zeros’, ‘random’]

The initial phase.

Returns:

outTensor [shape=(…, NxP)]

The excitation signal.

See also

pitch