The field of audio signal processing is moving towards more efficient and secure methods for processing and analyzing audio data. Recent developments have focused on improving the performance of blind source separation methods, such as multichannel non-negative matrix factorization, and exploring new approaches for audio representation learning, including multi-view learning and disentanglement techniques. Additionally, there is a growing interest in developing secure and privacy-preserving methods for audio data, including ear canal biometric key extraction and reversible data hiding. Noteworthy papers in this area include:

• A proposed method for accelerated convolutive transfer function-based multichannel NMF using iterative source steering, which achieves comparable or superior separation performance to the original method while reducing computational complexity.
• A novel approach to neural instrument sound synthesis using a two-stage semi-supervised learning framework, which enables expressive and controllable audio generation with reliable pitch conditioning.