Differentiable short-time Fourier transform with respect to the hop length
This work addresses a specific issue in signal processing for researchers and practitioners, but it appears incremental as it extends existing STFT methods with differentiability.
The authors tackled the problem of optimizing the hop length in the short-time Fourier transform by making it differentiable, enabling gradient-based optimization and more precise temporal frame positioning. They demonstrated the approach with a simulated illustration, though no concrete performance numbers were provided.
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 improved control over the temporal positioning of frames, as the continuous nature of the hop length allows for a more finely-tuned optimization. Furthermore, our contribution enables the use of optimization methods such as gradient descent, which are more computationally efficient than conventional discrete optimization methods. Our differentiable STFT can also be easily integrated into existing algorithms and neural networks. We present a simulated illustration to demonstrate the efficacy of our approach and to garner interest from the research community.