Unmanned Aerial Vehicles (UAVs) or drones, are increasingly used in search and rescue missions to detect human presence. Existing systems primarily leverage vision-based methods which are prone to fail under low-visibility or occlusion. Drone-based audio perception offers promise but suffers from extreme ego-noise that masks sounds indicating human presence. Existing datasets are either limited in diversity or synthetic, lacking real acoustic interactions, and there are no standardized setups for drone audition. To this end, we present DroneAudioset (The dataset is publicly available at https://huggingface.co/datasets/ahlab-drone-project/DroneAudioSet/ under the MIT license), a comprehensive drone audition dataset featuring 23.5 hours of annotated recordings, covering a wide range of signal-to-noise ratios (SNRs) from -57.2 dB to -2.5 dB, across various drone types, throttles, microphone configurations as well as environments. The dataset enables development and systematic evaluation of noise suppression and classification methods for human-presence detection under challenging conditions, while also informing practical design considerations for drone audition systems, such as microphone placement trade-offs, and development of drone noise-aware audio processing. This dataset is an important step towards enabling design and deployment of drone-audition systems.

This paper presents StickEar, a system consisting of a network of distributed 'Sticker-like' sound-based sensor nodes to propose a means of enabling sound-based interactions on everyday objects. StickEar encapsulates wireless sensor network technology into a form factor that is intuitive to reuse and redeploy. Each StickEar sensor node consists of a miniature sized microphone and speaker to provide sound-based input/output capabilities. We provide a discussion of interaction design space and hardware design space of StickEar that cuts across domains such as remote sound monitoring, remote triggering of sound, autonomous response to sound events, and controlling of digital devices using sound. We implemented three applications to demonstrate the unique interaction capabilities of StickEar.