Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Leiber, Maxime"'
This paper presents a gradient-based method for on-the-fly optimization for both per-frame and per-frequency window length of the short-time Fourier transform (STFT), related to previous work in which we developed a differentiable version of STFT by
Externí odkaz:
http://arxiv.org/abs/2308.02418
In this paper, we propose a differentiable version of the short-time Fourier transform (STFT) that allows for gradient-based optimization of the hop length or the frame temporal position by making these parameters continuous. Our approach provides im
Externí odkaz:
http://arxiv.org/abs/2308.02421
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 theoret
Externí odkaz:
http://arxiv.org/abs/2208.10886