A Military Audio Dataset for Situational Awareness and Surveillance

We introduce the MAD dataset, an extensive collection of real-world acoustic event recordings associated with military environmental audio, encompassing a diverse range of hazard types and scenarios. This dataset holds the potential to serve as a valuable resource for evaluating the performance of existing audio classification algorithms and for fostering advancements in the field of acoustic hazard situation surveillance systems. To verify the MAD dataset, please download all files and refer our Github repository: https://github.com/kaen2891/military_audio_dataset