Consistent Iterative Hard Thresholding For Signal Declipping

TL;DR

This paper introduces a new iterative hard thresholding method for signal declipping that maintains consistency with observed data, outperforming existing algorithms in both synthetic and real audio scenarios.

Contribution

The paper presents a novel declipping algorithm based on iterative hard thresholding that enforces signal consistency, improving recovery quality over prior methods.

Findings

Superior performance in synthetic data recovery.

Enhanced subjective audio quality in real data.

Outperforms state-of-the-art declipping algorithms.

Abstract

Clipping or saturation in audio signals is a very common problem in signal processing, for which, in the severe case, there is still no satisfactory solution. In such case, there is a tremendous loss of information, and traditional methods fail to appropriately recover the signal. We propose a novel approach for this signal restoration problem based on the framework of Iterative Hard Thresholding. This approach, which enforces the consistency of the reconstructed signal with the clipped observations, shows superior performance in comparison to the state-of-the-art declipping algorithms. This is confirmed on synthetic and on actual high-dimensional audio data processing, both on SNR and on subjective user listening evaluations.