Sound field reconstruction aims to estimate pressure fields in areas lacking direct measurements. Existing techniques often rely on strong assumptions or face challenges related to data availability or the explicit modeling of physical properties. To bridge these gaps, this study introduces a zero-shot, physics-informed dictionary learning approach to perform sound field reconstruction. Our method relies only on a few sparse measurements to learn a dictionary, without the need for additional training data. Moreover, by enforcing the Helmholtz equation during the optimization process, the proposed approach ensures that the reconstructed sound field is represented as a linear combination of a few physically meaningful atoms. Evaluations on real-world data show that our approach achieves comparable performance to state-of-the-art dictionary learning techniques, with the advantage of requiring only a few observations of the sound field and no training on a dataset.

Head-Related Transfer Functions (HRTFs) have fundamental applications for realistic rendering in immersive audio scenarios. However, they are strongly subject-dependent as they vary considerably depending on the shape of the ears, head and torso. Thus, personalization procedures are required for accurate binaural rendering. Recently, Denoising Diffusion Probabilistic Models (DDPMs), a class of generative learning techniques, have been applied to solve a variety of signal processing-related problems. In this paper, we propose a first approach for using DDPM conditioned on anthropometric measurements to generate personalized Head-Related Impulse Response (HRIR), the time-domain representation of HRTF. The results show the feasibility of DDPMs for HRTF personalization obtaining performance in line with state-of-the-art models.

Reconstructing the sound field in a room is an important task for several applications, such as sound control and augmented (AR) or virtual reality (VR). In this paper, we propose a data-driven generative model for reconstructing the magnitude of acoustic fields in rooms with a focus on the modal frequency range. We introduce, for the first time, the use of a conditional Denoising Diffusion Probabilistic Model (DDPM) trained in order to reconstruct the sound field (SF-Diff) over an extended domain. The architecture is devised in order to be conditioned on a set of limited available measurements at different frequencies and generate the sound field in target, unknown, locations. The results show that SF-Diff is able to provide accurate reconstructions. We conduct a comparative analysis with two state-of-the-art baseline methods, one relying on kernel interpolation and the other on deep learning.

In this manuscript, we propose a novel method to perform audio inpainting, i.e., the restoration of audio signals presenting multiple missing parts. Audio inpainting can be interpreted in the context of inverse problems as the task of reconstructing an audio signal from its corrupted observation. For this reason, our method is based on a deep prior approach, a recently proposed technique that proved to be effective in the solution of many inverse problems, among which image inpainting. Deep prior allows one to consider the structure of a neural network as an implicit prior and to adopt it as a regularizer. Differently from the classical deep learning paradigm, deep prior performs a single-element training and thus it can be applied to corrupted audio signals independently from the available training data sets. In the context of audio inpainting, a network presenting relevant audio priors will possibly generate a restored version of an audio signal, only provided with its corrupted observation. Our method exploits a time-frequency representation of audio signals and makes use of a multi-resolution convolutional autoencoder, that has been enhanced to perform the harmonic convolution operation. Results show that the proposed technique is able to provide a coherent and meaningful reconstruction of the corrupted audio. It is also able to outperform the methods considered for comparison, in its domain of application.

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.

Acoustic signal processing in the spherical harmonics domain (SHD) is an active research area that exploits the signals acquired by higher order microphone arrays. A very important task is that concerning the localization of active sound sources. In this paper, we propose a simple yet effective method to localize prominent acoustic sources in adverse acoustic scenarios. By using a proper normalization and arrangement of the estimated spherical harmonic coefficients, we exploit low-rank approximations to estimate the far field modal directional pattern of the dominant source at each time-frame. The experiments confirm the validity of the proposed approach, with superior performance compared to other recent SHD-based approaches.

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.

Sound field analysis and reconstruction has been a topic of intense research in the last decades for its multiple applications in spatial audio processing tasks. In this context, the identification of the direct and reverberant sound field components is a problem of great interest, where several solutions exploiting spherical harmonics representations have already been proposed. However, the available techniques demand a large number of high-order microphones (HOMs) and high computational power in order to fulfill the necessary spatial sampling requirements, which can only be reduced by prior information obtained through acoustic measurements. Inspired by compressed sensing approaches, this paper proposes an alternative sparse formulation for estimating the exterior and interior sound field components in the spherical harmonics domain that allows to reduce hardware requirements without the need for additional acoustic measurements. The results show that a considerable reduction in the number of HOMs can be achieved while improving the estimation of the sound field components.

In the field of structural mechanics, classical methods for the vibrational characterization of objects exploit the inherent redundancy of a relevant amount of measurements acquired over regular sampling grids. However, there are cases in which parts of the objects under analysis are not accessible with sensors, leading to irregular sampling grids characterized by holes. Recent works have proved the benefits of adding prior knowledge in these scenarios, either through the definition of a suitable decomposition or using Finite Element modelling. In this paper we propose to use Convolutional Autoencoders (CA) for Frequency Response Function (FRF) interpolation from grids with different subsampling schemes. CA learn a compressed representation from a dataset of FRFs synthetized through Finite Element Analysis. Experiments with numerical and experimental data show the effectiveness of the model with a different amount of missing data and its ability to predict real FRFs characterized by different damping and sampling frequency.

Nonnegative matrix factorization (NMF) has been traditionally considered a promising approach for audio source separation. While standard NMF is only suited for single-channel mixtures, extensions to consider multi-channel data have been also proposed. Among the most popular alternatives, multichannel NMF (MNMF) and further derivations based on constrained spatial covariance models have been successfully employed to separate multi-microphone convolutive mixtures. This letter proposes a MNMF extension by considering a mixture model with Ray-Space-transformed signals, where magnitude data successfully encodes source locations as frequency-independent linear patterns. We show that the MNMF algorithm can be seamlessly adapted to consider Ray-Space-transformed data, providing competitive results with recent state-of-the-art MNMF algorithms in a number of configurations using real recordings.

In this article we propose a methodology for the reconstruction of sound fields in arbitrary locations based on the signals acquired by a spatial distribution of compact microphone arrays (virtual miking). The proposed method is suitable for operating in reverberant environments, thanks to a two-stage analysis process, the former of which aims at separating the direct and the diffuse components of the sound field. The method that we propose is inherently parametric, as the sources of the acoustic scene are characterized by parameters describing location and directivity (spherical harmonics expansion), which are extracted from the exterior model of the direct component of the sound field. Once the parameters of the sources are extracted, the direct sound field at an arbitrary location is reconstructed. The diffuse component is reconstructed from the joint knowledge of the diffuse component at the locations of the distributed microphone arrays, under the assumption of isotropic behavior. Results show that the proposed technique is able to analyze the sound field and reconstruct the parameters of the sources that are active in the scene. In addition, the synthesis of the signals at the virtual microphone locations turns out to accurately match (in terms of spatial cues) the actual sound field, as measured by a microphone places in the desired location.

In this paper we propose a parametric sound field reconstruction approach. In particular, the technique is based on the estimation of three parameters for each acoustic source (source position, radiation pattern and source signal) given the signals acquired by few arbitrarily placed microphone arrays. This allows us to synthesize the signal of a virtual microphone placed in any point of the acoustic scene.