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 room transfer functions measured at scattered points in the room. In this study, 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 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 real-valued neural network method and 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.

The main advantage of deep learning solutions is to adopt more sparse and irregular microphone array setups Reconstructing the sound field in a room is an important task for the sound field reconstruction. The first learningbased for several applications, such as sound control and augmented approach was proposed in [21] and consisted of a U- (AR) or virtual reality (VR). In this paper, we propose a datadriven Net architecture, which was applied in order to reconstruct generative model for reconstructing the magnitude of the magnitude of the sound field with an approach similar to acoustic fields in rooms with a focus on the modal frequency image inpainting. Similarly, in [22], the authors proposed a range. We introduce, for the first time, the use of a conditional deep-prior approach to RIR reconstruction following the deep Denoising Diffusion Probabilistic Model (DDPM) trained in prior paradigm introduced for image inpainting [23]. This approach order to reconstruct the sound field (SF-Diff) over an extended assumes that the structure of the CNN introduces an domain. The architecture is devised in order to be conditioned implicit prior regularizing the estimation of RIRs. Other solutions on a set of limited available measurements at different frequencies instead [24-26], rely on the physical equation governing and generate the sound field in target, unknown, locations.

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.

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.