Editorial: Reconstruction of Audio From Incomplete or Highly Degraded Observations

The papers from this special section focus on the restoration of udio content, in particular speech and music from degraded observations. This is a challenging and long-standing problem in audio processing. In particular this holds for severe degradations and incomplete observations, which are regularly encountered in practice. The papers in this section have been organized to gather contributions that would serve both as a comprehensive primer on the stateof- the-art, and a showcase of current developments within the field. The restoration of audio content, in particular speech and music from degraded observations, is a challenging and long-standing problem in audio processing. In particular this holds for severe degradations and incomplete observations, which are regularly encountered in practice. Traditional restoration techniques, such as interpolation or filtering, are often not applicable or perform poorly in this case. The advent of sparse signal processing in the very beginning of this century and, even more recently, of (deep) machine learning has opened wide new research and design opportunities for audio restoration, among many other signal processing problems. With the aid of such contemporary tools, researchers have recently been able to achieve unprecedented success in recovering or significantly improving the quality of severely degraded audio. As the field advances very quickly, the potential for improvement, as well as exploration, is hardly exhausted.