This is our sixth and final issue of 2024. It is hard to believe that a year has gone by since our term as the new editorial team started in January. In our first year, in addition to our usual array of technical overviews and Society news, we addressed a number of topics of significance for our community in the hopes of starting a discussion.

I am writing this short note as I am about to board a plane to Abu Dhabi to join those of you who are attending the 2024 edition of the International Conference on Image Processing (ICIP 2024). The team organizing ICIP 2024 has put together an outstanding technical program that includes world-class plenary speakers discussing research and industrial trends.

Multichannel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and nontarget or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire.

“All models are wrong, but some are useful” - understanding “models” as analytical mathematical models, this aphorism, originating from George Box in 1976, motivates the synthesis of model-based and data-driven audio signal processing as the leitmotif of this special issue.

Multichannel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and nontarget or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire.