Stft
(Tensor) the input tensor
(int) size of Fourier transform
(int, optional) the distance between neighboring sliding window frames. Default: None (treated as equal to floor(n_fft / 4))
(int, optional) the size of window frame and STFT filter. Default: None (treated as equal to n_fft)
(Tensor, optional) the optional window function. Default: None (treated as window of all \(1\) s)
(bool, optional) whether to pad input on both sides so that the \(t\)-th frame is centered at time \(t \times \mbox{hop\_length}\). Default: True
(string, optional) controls the padding method used when center is True. Default: "reflect"
(bool, optional) controls whether to return the normalized STFT results Default: False
(bool, optional) controls whether to return half of results to avoid redundancy Default: True
Short-time Fourier transform (STFT).
Ignoring the optional batch dimension, this method computes the following expression:
$$
X[m, \omega] = \sum_{k = 0}^{\mbox{win\_length-1}}%
\mbox{window}[k]\ \mbox{input}[m \times \mbox{hop\_length} + k]\ %
\exp\left(- j \frac{2 \pi \cdot \omega k}{\mbox{win\_length}}\right),
$$
where \(m\) is the index of the sliding window, and \(\omega\) is
the frequency that \(0 \leq \omega < \mbox{n\_fft}\). When
onesided is the default value True,
* `input` must be either a 1-D time sequence or a 2-D batch of time sequences.* If `hop_length` is ``None`` (default), it is treated as equal to ``floor(n_fft / 4)``.
* If `win_length` is ``None`` (default), it is treated as equal to `n_fft`.
* `window` can be a 1-D tensor of size `win_length`, e.g., from `torch_hann_window`. If `window` is ``None`` (default), it is treated as if having \eqn{1} everywhere in the window. If \eqn{\mbox{win\_length} < \mbox{n\_fft}}, `window` will be padded on both sides to length `n_fft` before being applied.
* If `center` is ``True`` (default), `input` will be padded on both sides so that the \eqn{t}-th frame is centered at time \eqn{t \times \mbox{hop\_length}}. Otherwise, the \eqn{t}-th frame begins at time \eqn{t \times \mbox{hop\_length}}.
* `pad_mode` determines the padding method used on `input` when `center` is ``True``. See `torch_nn.functional.pad` for all available options. Default is ``"reflect"``.
* If `onesided` is ``True`` (default), only values for \eqn{\omega} in \eqn{\left[0, 1, 2, \dots, \left\lfloor \frac{\mbox{n\_fft}}{2} \right\rfloor + 1\right]} are returned because the real-to-complex Fourier transform satisfies the conjugate symmetry, i.e., \eqn{X[m, \omega] = X[m, \mbox{n\_fft} - \omega]^*}.
* If `normalized` is ``True`` (default is ``False``), the function returns the normalized STFT results, i.e., multiplied by \eqn{(\mbox{frame\_length})^{-0.5}}.
Returns the real and the imaginary parts together as one tensor of size \eqn{(* \times N \times T \times 2)}, where \eqn{*} is the optional batch size of `input`, \eqn{N} is the number of frequencies where STFT is applied, \eqn{T} is the total number of frames used, and each pair in the last dimension represents a complex number as the real part and the imaginary part.
.. warning:: This function changed signature at version 0.4.1. Calling with the previous signature may cause error or return incorrect result.