Increasing interest in unmanned aerial vehicles (UAVs), commonly referred to as drones, has occurred in recent years. Search and rescue scenarios where humans in emergency situations need to be quickly found in difficult-toaccess areas constitute an important field of application for this technology. Drones have already been used by humanitarian organizations in countries such as Haiti and the Philippines to map areas after a natural disaster using high-resolution embedded cameras, as documented in a recent United Nations report [1]. Although research efforts have focused mostly on developing video-based solutions for this task [2], UAV-embedded audio-based localization has received relatively less attention [3]?[7]. However, UAVs equipped with a microphone array could be of critical help to localize people in emergency situations, especially when video sensors are limited by a lack of visual feedback due to bad lighting conditions (such as at night or in fog) or obstacles limiting the field of view (Figure 1).

In the context of building acoustics and the acoustic diagnosis of an existing room, it introduces and investigates a new approach to estimate the mean absorption coefficients solely from a room impulse response (RIR). This inverse problem is tackled via virtually supervised learning, namely, the RIR-to-absorption mapping is implicitly learned by regression on a simulated dataset using artificial neural networks. Simple models based on well-understood architectures are the focus of this work. The critical choices of geometric, acoustic, and simulation parameters, which are used to train the models, are extensively discussed and studied while keeping in mind the conditions that are representative of the field of building acoustics. Estimation errors from the learned neural models are compared to those obtained with classical formulas that require knowledge of the room's geometry and reverberation times. Extensive comparisons made on a variety of simulated test sets highlight different conditions under which the learned models can overcome the well-known limitations of the diffuse sound field hypothesis underlying these formulas. Results obtained on real RIRs measured in an acoustically configurable room show that at 1 kHz and above, the proposed approach performs comparably to classical models when reverberation times can be reliably estimated and continues to work even when they cannot.

Given a sound field generated by a sparse distribution of impulse image sources, can the continuous 3D positions and amplitudes of these sources be recovered from discrete, band-limited measurements of the field at a finite set of locations, e.g. , a multichannel room impulse response? Borrowing from recent advances in super-resolution imaging, it is shown that this non-linear, non-convex inverse problem can be efficiently relaxed into a convex linear inverse problem over the space of Radon measures in $\mathbb {R}^{3}$ . The new linear operator introduced here stems from the fundamental solution of the wave equation combined with the receivers' responses. An adaptation of the Sliding Frank-Wolfe algorithm is proposed to numerically solve the problem off-the-grid , i.e. , in continuous 3D space. Idealized simulated experiments show that the approach can recover hundreds of image sources at a rate and accuracy that are not achievable by previous methods, using a compact microphone array and source placed at random in random-sized shoe-box rooms. The impact of noise, sampling rate and array diameter on these results is also examined.