19 citations · 20 across the 4 of their papers we have counts for
4 papers
Differentiable short-time Fourier transform with respect to the hop length
Maxime Leiber, Yosra Marnissi, Axel Barrau +1
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 po…
Differentiable adaptive short-time Fourier transform with respect to the window length
Maxime Leiber, Yosra Marnissi, Axel Barrau +1
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 pr…
Speeding up backpropagation of gradients through the Kalman filter via closed-form expressions
Colin Parellier, Axel Barrau, Silvere Bonnabel
In this paper we provide novel closed-form expressions enabling differentiation of any scalar function of the Kalman filter's outputs with respect to all its tuning parameters and…
A differentiable short-time Fourier transform with respect to the window length
Maxime Leiber, Axel Barrau, Yosra Marnissi +1
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 t…