Learnable Time-Frequency Transform and Ridge Separation

Pingping Pan

doi:10.1109/LSP.2025.3643359

Learnable Time-Frequency Transform and Ridge Separation

2025-12-26

0

PRE

AI

DOI：10.1109/LSP.2025.3643359

Original

Original request for help

Save

Abstract

En 中文

Time-frequency analysis (TFA) and ridge separation of non-stationary signals have long been research topics in signal processing. They are mutually dependent: informative time-frequency representations (TFRs) enable reliable ridge estimation, while accurate ridges refine TFRs by outlining component-wise time-frequency (TF) trajectories. However, the uncertainty principle limits TF resolution and ridge discriminability, and existing ridge tracking or optimization-based methods rely on empirical tuning and degrade with weak or closely spaced components, highlighting the need for a more robust and unified solution. This letter proposes a unified network that jointly performs TFA and ridge separation. It features a knowledge-guided short-time transform module for extracting discriminative TF features, coupled with an instance segmentation module with learnable queries that interacts with the extracted TF features to achieve ridge separation. This knowledge- and data-integrated framework enables fine-grained TFR construction and high-accuracy ridge separation, while eliminating manual parameter tuning and enhancing adaptability. Finally, experiments on simulated and real-world data validate its effectiveness.

Keywords:

Intelligent signal processing

time-frequency analysis

ridge separation

Learnable Time-Frequency Transform and Ridge Separation

Abstract

Journal

Organization