# A Proper version of Synthesis-based Sparse Audio Declipper

arXiv: https://arxiv.org/abs/1810.12204 · HTML: https://mlsanity.com/paper/1810.12204/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2018.

## Built on by (most cited first, 1 of 1)

- [UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model](https://mlsanity.com/paper/2306.00721/) (2023)

## Abstract (arXiv)

Methods based on sparse representation have found great use in the recovery of audio signals degraded by clipping. The state of the art in declipping has been achieved by the SPADE algorithm by Kiti'c et. al. (LVA/ICA2015). Our recent study (LVA/ICA2018) has shown that although the original S-SPADE can be improved such that it converges significantly faster than the A-SPADE, the restoration quality is significantly worse. In the present paper, we propose a new version of S-SPADE. Experiments show that the novel version of S-SPADE outperforms its old version in terms of restoration quality, and that it is comparable with the A-SPADE while being even slightly faster than A-SPADE.