Create a spectrogram or a batch of spectrograms from a raw audio signal. The spectrogram can be either magnitude-only or complex.
transform_spectrogram( n_fft = 400, win_length = NULL, hop_length = NULL, pad = 0L, window_fn = torch::torch_hann_window, power = 2, normalized = FALSE, ... )
(integer): Size of FFT
(integer): Window size
(integer): Length of hop between STFT windows
(integer): Two sided padding of signal
(tensor or function): Window tensor that is applied/multiplied to each frame/window or a function that generates the window tensor.
(numeric): Exponent for the magnitude spectrogram, (must be > 0) e.g., 1 for energy, 2 for power, etc. If NULL, then the complex spectrum is returned instead.
(logical): Whether to normalize by magnitude after stft
(optional) Arguments for window function.
tensor: Dimension (..., freq, time), freq is n_fft %/% 2 + 1 and n_fft is the number of Fourier bins, and time is the number of window hops (n_frame).
forward param: waveform (tensor): Tensor of audio of dimension (..., time)