Initializer of Conv kernels for Short-term Fourier Transformation (STFT).

Since the formula involves complex numbers, this class compute either the real or the imaginary components of the final output.

Additionally, this initializer supports windowing functions across the time dimension as commonly used in STFT. Windowing functions from the Python module scipy.signal.windows are supported, including the common hann and hamming windowing functions. This layer supports periodic windows and scaling-based normalization.

This is primarily intended for use in the STFTSpectrogram layer.

Usage

initializer_stft(
  side = "real",
  window = "hann",
  scaling = "density",
  periodic = FALSE
)

Arguments

side

String, "real" or "imag" deciding if the kernel will compute the real side or the imaginary side of the output. Defaults to "real".

window

String for the name of the windowing function in the scipy.signal.windows module, or array_like for the window values, or NULL for no windowing.

scaling

String, "density" or "spectrum" for scaling of the window for normalization, either L2 or L1 normalization. NULL for no scaling.

periodic

Boolean, if True, the window function will be treated as periodic. Defaults to FALSE.

Value

An Initializer instance that can be passed to layer or variable constructors, or called directly with a shape to return a Tensor.

Examples

# Standalone usage:
initializer <- initializer_stft("real", "hann", "density", FALSE)
values <- initializer(shape = c(128, 1, 513))

See also

Other initializers:
initializer_constant()
initializer_glorot_normal()
initializer_glorot_uniform()
initializer_he_normal()
initializer_he_uniform()
initializer_identity()
initializer_lecun_normal()
initializer_lecun_uniform()
initializer_ones()
initializer_orthogonal()
initializer_random_normal()
initializer_random_uniform()
initializer_truncated_normal()
initializer_variance_scaling()
initializer_zeros()

Other constant initializers:
initializer_constant()
initializer_identity()
initializer_ones()
initializer_zeros()