Differentiable adaptive short-time Fourier transform with respect to the window length
This work addresses a domain-specific problem in signal processing, offering an incremental improvement for vibration analysis applications.
The paper tackles the problem of optimizing window length in the short-time Fourier transform (STFT) by introducing a gradient-based method for on-the-fly adaptation, achieving commendable properties like handling both transient and stationary components in vibration analysis.
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 making the window length a continuous parameter. 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. We validate the performance of our method in vibration analysis.