Replication Data for: Enhancing Blind Separation of Incoherent Sources in Acoustic Imaging with Deep Learning

This dataset accompanies the preprint “Enhancing blind separation of incoherent sources in acoustic imaging with deep learning” (Wu et al., 2025). It includes microphone array recordings in TDMS format and the corresponding array geometry for validating blind source separation methods in acoustic imaging. Data includes both lab speaker configurations and real-world test rig recordings. Details on usage and loading scripts are provided in the included README.