Law Enforcement Agencies (LEAs) heavily rely on Lawful Interception (LI) tools to investigate criminal and terrorist activities. The growing frequency of cybercrime, terrorism-related offenses, and illegal trades in the European Union (EU) has driven LEAs to explore novel LI techniques that align with the developing 5G and Beyond 5G network architectures. Moreover, the emergence of extremely dynamic and distributed networks, the increased usage of end-to-end encryption applications, and privacy protections present limitations for traditional LI approaches. In order to provide a technological solution capable of extending the 3GPP LI standard, this paper presents a novel LI framework designed on top of the standardized 3GPP LI architecture, leveraging an inspection-friendly end-to-end cryptography mechanism (e.g., a Key Escrow algorithm) at the application layer. Moreover, the proposed Lawful Interception (LI) framework enables authorized LEAs to decrypt intercepted end-to-end encrypted data within the core network. Firstly, a security proof validates the security of the proposed LI framework under two attack scenarios. Subsequently, a proof-of-concept workstation implementation that emulates a 5G network for end-to-end data exchange and cloud-based deployment validates the suggested LI framework by affirming the LEA capabilities in decrypting intercepted data. Additionally, the system performance has been studied through experimental tests, ensuring the scalability of the conceived solution and revealing the possibility of intercepting data with mainly real-time latency without affecting the Quality of Service (QoS) experienced by the user.

Acoustic imaging is powerful in collecting spatial information of acoustic sources into a visual representation. In this paper, we focus on the analysis of the exterior acoustic field captured by a circular array of microphones. With a proper parametrization based on angles, we map the directions of arrival of sources as a function of the microphone locations, thus obtaining an acoustic image called “angular space”. Therefore, we introduce a linear transform to enable analysis and synthesis operations for mapping the microphone pressures onto the angular space using local space-time Fourier analysis. We prove the ability of this representation to combine global information coming from multiple arrays in a single acoustic image that can be processed and manipulated. Examples of source localization applications in simulated and measured scenarios show the effectiveness of the proposed method obtaining results comparable with state-of-the-art methods.

The interpretation and explanation of decision-making processes of neural networks are becoming a key factor in the deep learning field. Although several approaches have been presented for classification problems, the application to regression models needs to be further investigated. In this manuscript we propose a Grad-CAM-inspired approach for the visual explanation of neural network architecture for regression problems. We apply this methodology to a recent physics-informed approach for Nearfield Acoustic Holography, called Kirchhoff-Helmholtz-based Convolutional Neural Network (KHCNN) architecture. We focus on the interpretation of KHCNN using vibrating rectangular plates with different boundary conditions and violin top plates with complex shapes. Results highlight the more informative regions of the input that the network exploits to correctly predict the desired output. The devised approach has been validated in terms of NCC and NMSE using the original input and the filtered one coming from the algorithm.

The problems of speech separation and enhancement concern the extraction of the speech emitted by a target speaker when placed in a scenario where multiple interfering speakers or noise are present, respectively. A plethora of practical applications such as home assistants and teleconferencing require some sort of speech separation and enhancement pre-processing before applying Automatic Speech Recognition (ASR) systems. In the recent years, most techniques have focused on the application of deep learning to either time-frequency or time-domain representations of the input audio signals. In this paper we propose a real-time multichannel speech separation and enhancement technique, which is based on the combination of a directional representation of the sound field, denoted as beamspace, with a lightweight Convolutional Neural Network (CNN). We consider the case where the Direction-Of-Arrival (DOA) of the target speaker is approximately known, a scenario where the power of the beamspace-based representation can be fully exploited, while we make no assumption regarding the identity of the talker. We present experiments where the model is trained on simulated data and tested on real recordings and we compare the proposed method with a similar state-of-the-art technique.