Search Results for author:
Found 4 papers, 3 papers with code
Differentiable short-time Fourier transform with respect to the hop length
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.
Differentiable adaptive short-time Fourier transform with respect to the window length
The resulting differentiable adaptive STFT possesses commendable properties, such as the ability to adapt in the same time-frequency representation to both transient and stationary components, while being easily optimized by gradient descent.
A differentiable short-time Fourier transform with respect to the window length
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.
A Variational Bayesian Approach for Image Restoration. Application to Image Deblurring with Poisson-Gaussian Noise
We demonstrate the potential of the proposed approach through comparisons with state-of-the-art techniques that are specifically tailored to signal recovery in the presence of mixed Poisson-Gaussian noise.
