Dilated CNNs for Periodic Signal Processing: A Low-Complexity Approach

TL;DR

This paper introduces R-DCNN, a low-complexity, resampling-based deep learning method for denoising and waveform estimation of periodic signals, suitable for resource-constrained environments.

Contribution

It presents a novel, efficient DCNN approach that generalizes across signals with different frequencies using lightweight resampling, reducing computational demands.

Findings

R-DCNN achieves performance comparable to classical state-of-the-art methods.

The approach requires only a single observation for training.

It is effective across various signals with different fundamental frequencies.

Abstract

Denoising of periodic signals and accurate waveform estimation are core tasks across many signal processing domains, including speech, music, medical diagnostics, radio, and sonar. Although deep learning methods have recently shown performance improvements over classical approaches, they require substantial computational resources and are usually trained separately for each signal observation. This study proposes a computationally efficient method based on DCNN and Re-sampling, termed R-DCNN, designed for operation under strict power and resource constraints. The approach targets signals with varying fundamental frequencies and requires only a single observation for training. It generalizes to additional signals via a lightweight resampling step that aligns time scales in signals with different frequencies to re-use the same network weights. Despite its low computational complexity, R-DCNN achieves performance comparable to state-of-the-art classical methods, such as autoregressive (AR)-based techniques, as well as conventional DCNNs trained individually for each observation. This combination of efficiency and performance makes the proposed method particularly well suited for deployment in resource-constrained environments without sacrificing denoising or estimation accuracy.