A Physics-Informed Neural Network-Based Approach for the Spatial Upsampling of Spherical Microphone Arrays
- URL: http://arxiv.org/abs/2407.18732v1
- Date: Fri, 26 Jul 2024 13:35:06 GMT
- Title: A Physics-Informed Neural Network-Based Approach for the Spatial Upsampling of Spherical Microphone Arrays
- Authors: Federico Miotello, Ferdinando Terminiello, Mirco Pezzoli, Alberto Bernardini, Fabio Antonacci, Augusto Sarti,
- Abstract summary: 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.
- Score: 40.98027720342511
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- HARP: A Large-Scale Higher-Order Ambisonic Room Impulse Response Dataset [0.6568378556428859]
This contribution introduces a dataset of 7th-order Ambisonic Room Impulse Responses (HOA-RIRs) created using the Image Source Method.
By employing higher-order Ambisonics, our dataset enables precise spatial audio reproduction.
The presented 64-microphone configuration allows us to capture RIRs directly in the Spherical Harmonics domain.
arXiv Detail & Related papers (2024-11-21T15:16:48Z) - Array2BR: An End-to-End Noise-immune Binaural Audio Synthesis from Microphone-array Signals [31.30005077444649]
This paper proposes a new end-to-end noise-immune synthesis framework from microphone-array signals, abbreviated as Array2BR.
Compared with existing methods, the proposed method achieved better performance in terms of both objective and subjective metric scores.
arXiv Detail & Related papers (2024-10-08T06:55:35Z) - Neural Gaussian Scale-Space Fields [60.668800252986976]
We present an efficient method to learn the continuous, anisotropic Gaussian scale space of an arbitrary signal.
Our approach is trained self-supervised, i.e., training does not require any manual filtering.
Our neural Gaussian scale-space fields faithfully capture multiscale representations across a broad range of modalities.
arXiv Detail & Related papers (2024-05-31T16:26:08Z) - A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications [1.099532646524593]
This paper introduces a micro-Doppler coherence loss, minimized when the normalized power of micro-Doppler oscillatory components between input and output is matched.
Experiments conducted on real data show that the application of the introduced loss results in models more resilient to noise.
arXiv Detail & Related papers (2024-04-12T08:11:07Z) - Adaptive Shells for Efficient Neural Radiance Field Rendering [92.18962730460842]
We propose a neural radiance formulation that smoothly transitions between- and surface-based rendering.
Our approach enables efficient rendering at very high fidelity.
We also demonstrate that the extracted envelope enables downstream applications such as animation and simulation.
arXiv Detail & Related papers (2023-11-16T18:58:55Z) - Bosonic field digitization for quantum computers [62.997667081978825]
We address the representation of lattice bosonic fields in a discretized field amplitude basis.
We develop methods to predict error scaling and present efficient qubit implementation strategies.
arXiv Detail & Related papers (2021-08-24T15:30:04Z) - Neural Network-based Virtual Microphone Estimator [111.79608275698274]
We propose a neural network-based virtual microphone estimator (NN-VME)
The NN-VME estimates virtual microphone signals directly in the time domain, by utilizing the precise estimation capability of the recent time-domain neural networks.
Experiments on the CHiME-4 corpus show that the proposed NN-VME achieves high virtual microphone estimation performance even for real recordings.
arXiv Detail & Related papers (2021-01-12T06:30:24Z) - Scene-Agnostic Multi-Microphone Speech Dereverberation [47.735158037490834]
We present an NN architecture that can cope with microphone arrays whose number and positions are unknown.
Our approach harnesses recent advances in deep learning on set-structured data to design an architecture that enhances the reverberant log-spectrum.
arXiv Detail & Related papers (2020-10-22T17:13:12Z) - Sound field reconstruction in rooms: inpainting meets super-resolution [1.0705399532413618]
Deep-learning method for sound field reconstruction is proposed.
The method is based on a U-net-like neural network with partial convolutions trained solely on simulated data.
Experiments using simulated data together with an experimental validation in a real listening room are shown.
arXiv Detail & Related papers (2020-01-30T11:31:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.