A differentiable short-time Fourier transform with respect to the window length. (arXiv:2208.10886v2 [cs.LG] UPDATED)

In this paper, we revisit the use of spectrograms in neural networks, by
making the window length a continuous parameter optimizable by gradient descent
instead of an empirically tuned integer-valued hyperparameter. The contribution
is mostly theoretical at this point, but plugging the modified STFT into any
existing neural network is straightforward. We first define a differentiable
version of the STFT in the case where local bins centers are fixed and
independent of the window length parameter. We then discuss the …

arxiv lg time