Differentiable adaptive short-time Fourier transform with respect to the window length

TL;DR

This paper introduces a gradient-based, differentiable adaptive STFT that optimizes window length dynamically for improved time-frequency analysis, validated in vibration analysis applications.

Contribution

It develops a novel differentiable STFT allowing on-the-fly window length optimization for better time-frequency representation.

Findings

Effective adaptation to transient and stationary components

Enhanced vibration analysis performance

Gradient-based optimization of window length

Abstract

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.