delta

class diffsptk.Delta(seed: list[list[float] | tuple[float, ...] | ndarray] | tuple[list[float] | tuple[float, ...] | ndarray, ...] | ndarray | list[int] | tuple[int, ...] = [[-0.5, 0, 0.5], [1, -2, 1]], static_out: bool = True)

See this page for details.

Parameters:

seedlist[list[float]] or list[int]

The delta coefficients or the width(s) of 1st (and 2nd) regression coefficients.

static_outbool

If False, outputs only the delta components.

forward(x: Tensor) → Tensor

Compute the delta components.

Parameters:

xTensor [shape=(B, T, D) or (T, D)]

The static components.

Returns:

outTensor [shape=(B, T, DxH) or (T, DxH)]

The delta (and static) components.

Examples

>>> x = diffsptk.ramp(1, 8).view(1, -1, 2)
>>> x
tensor([[[1., 2.],
         [3., 4.],
         [5., 6.],
         [7., 8.]]])
>>> delta = diffsptk.Delta([[-0.5, 0], [0, 0, 0.5]])
>>> y = delta(x)
>>> y
tensor([[[ 1.0000,  2.0000, -0.5000, -1.0000,  1.5000,  2.0000],
         [ 3.0000,  4.0000, -0.5000, -1.0000,  2.5000,  3.0000],
         [ 5.0000,  6.0000, -1.5000, -2.0000,  3.5000,  4.0000],
         [ 7.0000,  8.0000, -2.5000, -3.0000,  3.5000,  4.0000]]])

diffsptk.functional.delta(x: Tensor, seed: list[list[float] | tuple[float, ...] | ndarray] | tuple[list[float] | tuple[float, ...] | ndarray, ...] | ndarray | list[int] | tuple[int, ...] = [[-0.5, 0, 0.5]], static_out: bool = True) → Tensor

Compute the delta components.

Parameters:

xTensor [shape=(B, T, D) or (T, D)]

The static components.

seedlist[list[float]] or list[int]

The delta coefficients or the width(s) of 1st (and 2nd) regression coefficients.

static_outbool

If False, outputs only the delta components.

Returns:

outTensor [shape=(B, T, DxH) or (T, DxH)]

The delta (and static) components.

See also

mlpg