Sparsity and cosparsity for audio declipping: a flexible non-convex approach
This work addresses audio declipping for signal processing applications, offering incremental improvements in real-time capability and performance for saturated signals.
The paper tackled the audio declipping problem by comparing sparse synthesis and sparse analysis regularization, finding that both models perform similarly for signal enhancement but the analysis version enables real-time processing with certain operators, and both outperform state-of-the-art methods, especially for severely saturated signals.
This work investigates the empirical performance of the sparse synthesis versus sparse analysis regularization for the ill-posed inverse problem of audio declipping. We develop a versatile non-convex heuristics which can be readily used with both data models. Based on this algorithm, we report that, in most cases, the two models perform almost similarly in terms of signal enhancement. However, the analysis version is shown to be amenable for real time audio processing, when certain analysis operators are considered. Both versions outperform state-of-the-art methods in the field, especially for the severely saturated signals.