no code implementations • 10 Apr 2024 • Xenofon Karakonstantis, Efren Fernandez-Grande, Peter Gerstoft
In this study, we introduce a method for estimating sound fields in reverberant environments using a conditional invertible neural network (CINN).
no code implementations • 12 Jan 2024 • Yifan Wu, Michael B. Wakin, Peter Gerstoft
The DOA is retrieved using a Vandermonde decomposition on the Toeplitz matrix obtained from the solution of the SDP.
no code implementations • 17 Oct 2023 • Ruixian Liu, Peter Gerstoft
The physics-informed neural network (PINN) is capable of recovering partial differential equation (PDE) coefficients that remain constant throughout the spatial domain directly from physical measurements.
no code implementations • 17 Oct 2023 • Daniel Romero, Tien Ngoc Ha, Peter Gerstoft
In a spoofing attack, an attacker impersonates a legitimate user to access or modify data belonging to the latter.
1 code implementation • 8 Nov 2022 • Daniel Romero, Peter Gerstoft, Hadi Givehchian, Dinesh Bharadia
In a spoofing attack, an attacker impersonates a legitimate user to access or tamper with data intended for or produced by the legitimate user.
no code implementations • 27 Oct 2022 • Luke Wood, Kevin Anderson, Peter Gerstoft, Richard Bell, Raghab Subbaraman, Dinesh Bharadia
Traditionally source identification is solved using threshold based energy detection algorithms.
1 code implementation • 26 Aug 2022 • Yongsung Park, Florian Meyer, Peter Gerstoft
At each time step, belief propagation predicts the number of DOAs and their DOAs using posterior probability density functions (pdfs) from the previous time and a different Bernoulli-von Mises state transition model.
no code implementations • 13 Jul 2022 • Yifan Wu, Michael B. Wakin, Peter Gerstoft
Direction-of-arrival (DOA) estimation is widely applied in acoustic source localization.
no code implementations • 2 Mar 2021 • Peter Gerstoft, Yihan Hu, Michael J. Bianco, Chaitanya Patil, Ardel Alegre, Yoav Freund, Francois Grondin
The DOAs are fed to a fusion center, concatenated, and used to perform the localization based on two proposed methods, which require only few labeled source locations (anchor points) for training.
no code implementations • 12 Feb 2021 • Yongsung Park, Peter Gerstoft
We present a gridless sparse iterative covariance-based estimation method based on alternating projections for direction-of-arrival (DOA) estimation.
no code implementations • 26 Jan 2021 • Michael J. Bianco, Sharon Gannot, Efren Fernandez-Grande, Peter Gerstoft
As far as we are aware, our paper presents the first approach to modeling the physics of acoustic propagation using deep generative modeling.
no code implementations • 17 Dec 2020 • Emma Ozanich, Aaron Thode, Peter Gerstoft, Lauren A. Freeman, Simon Freeman
DEC, GMM, and conventional clustering were tested on simulated datasets of fish pulse calls (fish) and whale song units (whale) with randomized bandwidth, duration, and SNR.
no code implementations • 27 Oct 2020 • Yifan Wu, Roshan Ayyalasomayajula, Michael J. Bianco, Dinesh Bharadia, Peter Gerstoft
This paper presents SSLIDE, Sound Source Localization for Indoors using DEep learning, which applies deep neural networks (DNNs) with encoder-decoder structure to localize sound sources with random positions in a continuous space.
no code implementations • 27 May 2020 • Michael J. Bianco, Sharon Gannot, Peter Gerstoft
We propose a semi-supervised localization approach based on deep generative modeling with variational autoencoders (VAEs).
no code implementations • 11 May 2019 • Michael J. Bianco, Peter Gerstoft, James Traer, Emma Ozanich, Marie A. Roch, Sharon Gannot, Charles-Alban Deledalle
Acoustic data provide scientific and engineering insights in fields ranging from biology and communications to ocean and Earth science.
no code implementations • 1 Apr 2019 • Jing Chi, Xiaolei Li, Haozhong Wang, Dazhi Gao, Peter Gerstoft
Based on FEAST, when the evaluated range error of the FNN reaches the minimum on test data, stopping training, which will help to improve the ranging accuracy of the FNN on the test data.
no code implementations • 17 Mar 2018 • Jiang Zhu, Qi Zhang, Peter Gerstoft, Mihai-Alin Badiu, Zhiwei Xu
In this paper, the line spectral estimation (LSE) problem with multiple measurement vectors (MMVs) is studied utilizing the Bayesian methods.
Information Theory Information Theory
no code implementations • 16 Dec 2017 • Michael Bianco, Peter Gerstoft
The local model considers small-scale variations using a sparsity constraint and the global model considers larger-scale features constrained using $\ell_2$ regularization.
no code implementations • 29 Jan 2017 • Haiqiang Niu, Emma Reeves, Peter Gerstoft
Source localization in ocean acoustics is posed as a machine learning problem in which data-driven methods learn source ranges directly from observed acoustic data.