Fabio Antonacci

Mirco Pezzoli, Fabio Antonacci, Augusto Sarti

Recently deep learning and machine learning approaches have been widely employed for various applications in acoustics. Nonetheless, in the area of sound field processing and reconstruction classic methods based on the solutions of wave equation are still widespread. Recently, physics-informed neural networks have been proposed as a deep learning paradigm for solving partial differential equations which govern physical phenomena, bridging the gap between purely data-driven and model based methods. Here, we exploit physics-informed neural networks to reconstruct the early part of missing room impulse responses in an uniform linear array. This methodology allows us to exploit the underlying law of acoustics, i.e., the wave equation, forcing the neural network to generate physically meaningful solutions given only a limited number of data points. The results on real measurements show that the proposed model achieves accurate reconstruction and performance in line with respect to state-of-the-art deep-learning and compress sensing techniques while maintaining a lightweight architecture.

Federico Miotello, Ferdinando Terminiello, Mirco Pezzoli et al.

Spherical microphone arrays are convenient tools for capturing the spatial characteristics of a sound field. However, achieving superior spatial resolution requires arrays with numerous capsules, consequently leading to expensive devices. To address this issue, we present a method for spatially upsampling spherical microphone arrays with a limited number of capsules. Our approach exploits a physics-informed neural network with Rowdy activation functions, leveraging physical constraints to provide high-order microphone array signals, starting from low-order devices. Results show that, within its domain of application, our approach outperforms a state of the art method based on signal processing for spherical microphone arrays upsampling.

Sagi Della Torre, Mirco Pezzoli, Fabio Antonacci et al.

Room Impulse Responses estimation is a fundamental problem in spatial audio processing and speech enhancement. In this paper, we build upon our previously introduced diffusion-based inpainting framework for Room Impulse Response interpolation and demonstrate its applicability to enhancing the performance of practical multi-microphone array processing tasks. Furthermore, we validate the robustness of this method in interpolating real-world Room Impulse Responses.

Francisco Messina, Francesca Ronchini, Luca Comanducci et al.

A persistent challenge in generative audio models is data replication, where the model unintentionally generates parts of its training data during inference. In this work, we address this issue in text-to-audio diffusion models by exploring the use of anti-memorization strategies. We adopt Anti-Memorization Guidance (AMG), a technique that modifies the sampling process of pre-trained diffusion models to discourage memorization. Our study explores three types of guidance within AMG, each designed to reduce replication while preserving generation quality. We use Stable Audio Open as our backbone, leveraging its fully open-source architecture and training dataset. Our comprehensive experimental analysis suggests that AMG significantly mitigates memorization in diffusion-based text-to-audio generation without compromising audio fidelity or semantic alignment.

Federico Miotello, Luca Comanducci, Mirco Pezzoli et al.

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, outperforming a state-of-the-art baseline based on kernel interpolation.

Francesca Ronchini, Luca Comanducci, Mirco Pezzoli et al.

Reconstructing the room transfer functions needed to calculate the complex sound field in a room has several important real-world applications. However, an unpractical number of microphones is often required. Recently, in addition to classical signal processing methods, deep learning techniques have been applied to reconstruct the room transfer function starting from a very limited set of measurements at scattered points in the room. In this paper, we employ complex-valued neural networks to estimate room transfer functions in the frequency range of the first room resonances, using a few irregularly distributed microphones. To the best of our knowledge, this is the first time that complex-valued neural networks are used to estimate room transfer functions. To analyze the benefits of applying complex-valued optimization to the considered task, we compare the proposed technique with a state-of-the-art kernel-based signal processing approach for sound field reconstruction, showing that the proposed technique exhibits relevant advantages in terms of phase accuracy and overall quality of the reconstructed sound field. For informative purposes, we also compare the model with a similarly-structured data-driven approach that, however, applies a real-valued neural network to reconstruct only the magnitude of the sound field.

Sagi Della Torre, Mirco Pezzoli, Fabio Antonacci et al.

Room Impulse Responses (RIRs) characterize acoustic environments and are crucial in multiple audio signal processing tasks. High-quality RIR estimates drive applications such as virtual microphones, sound source localization, augmented reality, and data augmentation. However, obtaining RIR measurements with high spatial resolution is resource-intensive, making it impractical for large spaces or when dense sampling is required. This research addresses the challenge of estimating RIRs at unmeasured locations within a room using Denoising Diffusion Probabilistic Models (DDPM). Our method leverages the analogy between RIR matrices and image inpainting, transforming RIR data into a format suitable for diffusion-based reconstruction. Using simulated RIR data based on the image method, we demonstrate our approach's effectiveness on microphone arrays of different curvatures, from linear to semi-circular. Our method successfully reconstructs missing RIRs, even in large gaps between microphones. Under these conditions, it achieves accurate reconstruction, significantly outperforming baseline Spline Cubic Interpolation in terms of Normalized Mean Square Error and Cosine Distance between actual and interpolated RIRs. This research highlights the potential of using generative models for effective RIR interpolation, paving the way for generating additional data from limited real-world measurements.

Riccardo Passoni, Francesca Ronchini, Luca Comanducci et al.

Text-to-audio models have recently emerged as a powerful technology for generating sound from textual descriptions. However, their high computational demands raise concerns about energy consumption and environmental impact. In this paper, we conduct an analysis of the energy usage of 7 state-of-the-art text-to-audio diffusion-based generative models, evaluating to what extent variations in generation parameters affect energy consumption at inference time. We also aim to identify an optimal balance between audio quality and energy consumption by considering Pareto-optimal solutions across all selected models. Our findings provide insights into the trade-offs between performance and environmental impact, contributing to the development of more efficient generative audio models.

Francesca Ronchini, Ho-Hsiang Wu, Wei-Cheng Lin et al.

This paper investigates the design of effective prompt strategies for generating realistic datasets using Text-To-Audio (TTA) models. We also analyze different techniques for efficiently combining these datasets to enhance their utility in sound classification tasks. By evaluating two sound classification datasets with two TTA models, we apply a range of prompt strategies. Our findings reveal that task-specific prompt strategies significantly outperform basic prompt approaches in data generation. Furthermore, merging datasets generated using different TTA models proves to enhance classification performance more effectively than merely increasing the training dataset size. Overall, our results underscore the advantages of these methods as effective data augmentation techniques using synthetic data.

Eleonora Grassucci, Giuliano Galadini, Giordano Cicchetti et al.

Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, and assistive multimedia. Although the excellent results, existing approaches either require costly joint training on large-scale paired datasets or rely on pairwise similarities that may fail to capture global multimodal coherence. In this work, we propose a novel training-free multimodal guidance mechanism for V2A diffusion that leverages the volume spanned by the modality embeddings to enforce unified alignment across video, audio, and text. The proposed multimodal diffusion guidance (MDG) provides a lightweight, plug-and-play control signal that can be applied on top of any pretrained audio diffusion model without retraining. Experiments on VGGSound and AudioCaps demonstrate that our MDG consistently improves perceptual quality and multimodal alignment compared to baselines, proving the effectiveness of a joint multimodal guidance for V2A.

Marco Olivieri, Mirco Pezzoli, Fabio Antonacci et al.

Near-field Acoustic Holography (NAH) is a well-known problem aimed at estimating the vibrational velocity field of a structure by means of acoustic measurements. In this paper, we propose a NAH technique based on Convolutional Neural Network (CNN). The devised CNN predicts the vibrational field on the surface of arbitrary shaped plates (violin plates) with orthotropic material properties from a limited number of measurements. In particular, the architecture, named Super Resolution CNN (SRCNN), is able to estimate the vibrational field with a higher spatial resolution compared to the input pressure. The pressure and velocity datasets have been generated through Finite Element Method simulations. We validate the proposed method by comparing the estimates with the synthesized ground truth and with a state-of-the-art technique. Moreover, we evaluate the robustness of the devised network against noisy input data.

R. Malvermi, S. Gonzalez, M. Quintavalla et al.

Frequency Response Functions (FRFs) are one of the cornerstones of musical acoustic experimental research. They describe the way in which musical instruments vibrate in a wide range of frequencies and are used to predict and understand the acoustic differences between them. In the specific case of stringed musical instruments such as violins, FRFs evaluated at the bridge are known to capture the overall body vibration. These indicators, also called bridge admittances, are widely used in the literature for comparative analyses. However, due to their complex structure they are rather difficult to quantitatively compare and study. In this manuscript we present a way to quantify differences between FRFs, in particular violin bridge admittances, that separates the effects in frequency, amplitude and quality factor of the first resonance peaks characterizing the responses. This approach allows us to define a distance between FRFs and clusterise measurements according to this distance. We use two case studies, one based on Finite Element Analysis and another exploiting measurements on real violins, to prove the effectiveness of such representation. In particular, for simulated bridge admittances the proposed distance is able to highlight the different impact of consecutive simulation `steps' on specific vibrational properties and, for real violins, gives a first insight on similar styles of making, as well as opposite ones.

Davide Salvi, Sebastian Gonzalez, Fabio Antonacci et al.

We recently developed a neural network that receives as input the geometrical and mechanical parameters that define a violin top plate and gives as output its first ten eigenfrequencies computed in free boundary conditions. In this manuscript, we use the network to optimize several error functions, with the goal of analyzing the relationship between the eigenspectrum problem for violin top plates and their geometry. First, we focus on the violin outline. Given a vibratory feature, we find which is the best geometry of the plate to obtain it. Second, we investigate whether, from the vibrational point of view, a change in the outline shape can be compensated by one in the thickness distribution and vice versa. Finally, we analyze how to modify the violin shape to keep its response constant as its material properties vary. This is an original technique in musical acoustics, where artificial intelligence is not widely used yet. It allows us to both compute the vibrational behavior of an instrument from its geometry and optimize its shape for a given response. Furthermore, this method can be of great help to violin makers, who can thus easily understand the effects of the geometry changes in the violins they build, shedding light on one of the most relevant and, at the same time, less understood aspects of the construction process of musical instruments.

Sebastian Gonzalez, Davide Salvi, Daniel Baeza et al.

Of all the characteristics of a violin, those that concern its shape are probably the most important ones, as the violin maker has complete control over them. Contemporary violin making, however, is still based more on tradition than understanding, and a definitive scientific study of the specific relations that exist between shape and vibrational properties is yet to come and sorely missed. In this article, using standard statistical learning tools, we show that the modal frequencies of violin tops can, in fact, be predicted from geometric parameters, and that artificial intelligence can be successfully applied to traditional violin making. We also study how modal frequencies vary with the thicknesses of the plate (a process often referred to as {\em plate tuning}) and discuss the complexity of this dependency. Finally, we propose a predictive tool for plate tuning, which takes into account material and geometric parameters.

Luca Comanducci, Maximo Cobos, Fabio Antonacci et al.

The interest in deep learning methods for solving traditional signal processing tasks has been steadily growing in the last years. Time delay estimation (TDE) in adverse scenarios is a challenging problem, where classical approaches based on generalized cross-correlations (GCCs) have been widely used for decades. Recently, the frequency-sliding GCC (FS-GCC) was proposed as a novel technique for TDE based on a sub-band analysis of the cross-power spectrum phase, providing a structured two-dimensional representation of the time delay information contained across different frequency bands. Inspired by deep-learning-based image denoising solutions, we propose in this paper the use of convolutional neural networks (CNNs) to learn the time-delay patterns contained in FS-GCCs extracted in adverse acoustic conditions. Our experiments confirm that the proposed approach provides excellent TDE performance while being able to generalize to different room and sensor setups.

Marco Compagnoni, Alessia Pini, Antonio Canclini et al.

The curse of outlier measurements in estimation problems is a well known issue in a variety of fields. Therefore, outlier removal procedures, which enables the identification of spurious measurements within a set, have been developed for many different scenarios and applications. In this paper, we propose a statistically motivated outlier removal algorithm for time differences of arrival (TDOAs), or equivalently range differences (RD), acquired at sensor arrays. The method exploits the TDOA-space formalism and works by only knowing relative sensor positions. As the proposed method is completely independent from the application for which measurements are used, it can be reliably used to identify outliers within a set of TDOA/RD measurements in different fields (e.g. acoustic source localization, sensor synchronization, radar, remote sensing, etc.). The proposed outlier removal algorithm is validated by means of synthetic simulations and real experiments.

Marco Compagnoni, Roberto Notari, Fabio Antonacci et al.

In this work we study the statistical model of source localization based on Range Difference measurements. We investigate the case of planar localization of a source using a minimal configuration of three non aligned receivers. Our analysis is based on a previous work of the same authors concerning the localization in a noiseless scenario. As the set of feasible measurements is a semialgebraic variety, this investigation makes use of techniques from Algebraic Statistics and Information Geometry.

Marco Compagnoni, Roberto Notari, Andrea Alessandro Ruggiu et al.

Localizing a radiant source is a widespread problem to many scientific and technological research areas. E.g. localization based on range measurements stays at the core of technologies like radar, sonar and wireless sensors networks. In this manuscript we study in depth the model for source localization based on range measurements obtained from the source signal, from the point of view of algebraic geometry. In the case of three receivers, we find unexpected connections between this problem and the geometry of Kummer's and Cayley's surfaces. Our work gives new insights also on the localization based on range differences.