arXiv research

Paper explores using EEG for better speaker identification, even in noisy environments.

PCA++ improves robustness to background noise in contrastive learning.

Automatically detecting sound units of humpback whales in complex time-varying background noises is a current challenge for scientists. In this paper, we explore the applicability of Convolution Neural Network (CNN) method for this task. In the evaluation stage, we present 6 bi-class classification experimentations of …

Generative Adversarial Networks generate PXD background noise efficiently.

CNNs trained by gradient descent can learn intrinsic image rank robustly to background noises.

BIND removes background noise from binary matrices, improving detection accuracy and fairness.

Study evaluates saliency maps on artificial data with different backgrounds.

Real-time speech enhancement model removes various noises and reverb.

New method designs joint initial noises for diffusion models to improve diversity and alignment.

GDiff tackles blind denoising with Gibbs sampling and Monte Carlo inference.

LAAT detects multiple low-density manifolds in noisy data.

We study an adaptive source seeking problem, in which a mobile robot must identify the strongest emitter(s) of a signal in an environment with background emissions. Background signals may be highly heterogeneous and can mislead algorithms that are based on receding horizon control. We propose AdaSearch, a general algor…

Based on the stochastic model proposed by Patriarca-Kaski-Chakraborti that describes the exchange of wealth between $n$ economic agents, we analyze the evolution of the corresponding economies under the assumption of a Gaussian background, modeling the exchange parameter $ε$. We demonstrate, that within Gaussian noise,…

Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is…

This work presents a novel approach for robust PCA with total variation regularization for foreground-background separation and denoising on noisy, moving camera video. Our proposed algorithm registers the raw (possibly corrupted) frames of a video and then jointly processes the registered frames to produce a decomposi…

Next-generation cosmic microwave background (CMB) experiments will have lower noise and therefore increased sensitivity, enabling improved constraints on fundamental physics parameters such as the sum of neutrino masses and the tensor-to-scalar ratio r. Achieving competitive constraints on these parameters requires hig…

A wide variety of application domains are concerned with data consisting of entities and their relationships or connections, formally represented as graphs. Within these diverse application areas, a common problem of interest is the detection of a subset of entities whose connectivity is anomalous with respect to the r…

FLOPART solves peak detection by creating accurate train and test set predictions.

Recent progress in separating the speech signals from multiple overlapping speakers using a single audio channel has brought us closer to solving the cocktail party problem. However, most studies in this area use a constrained problem setup, comparing performance when speakers overlap almost completely, at artificially…

Proposes ConiVAT for better cluster assessment and clustering with background knowledge.

Standard ChIP-seq peak calling pipelines seek to differentiate biochemically reproducible signals of individual genomic elements from background noise. However, reproducibility alone does not imply functional regulation (e.g., enhancer activation, alternative splicing). Here we present a general-purpose, interpretable …

This paper will describe a novel approach to the cocktail party problem that relies on a fully convolutional neural network (FCN) architecture. The FCN takes noisy audio data as input and performs nonlinear, filtering operations to produce clean audio data of the target speech at the output. Our method learns a model f…

Paper explores supervised learning methods to approximate ideal observer for joint signal detection and localization.

Generative adversarial networks (GANs) are a framework that learns a generative distribution through adversarial training. Recently, their class-conditional extensions (e.g., conditional GAN (cGAN) and auxiliary classifier GAN (AC-GAN)) have attracted much attention owing to their ability to learn the disentangled repr…

In this paper we study the pricing of exchange options under a dynamic described by stochastic correlation with random jumps. In particular, we consider a Ornstein-Uhlenbeck covariance model with Levy Background Noise Process driven by Inverse Gaussian subordinators. We use expansion in terms of Taylor polynomials and …

We consider bosonic supersymmetric backgrounds of ten-dimensional conformal supergravity. Up to local conformal isometry, we classify the maximally supersymmetric backgrounds, determine their conformal symmetry superalgebras and show how they arise as near-horizon geometries of certain half-BPS backgrounds or as a plan…

Derives path-integrals for superstrings on curved backgrounds using string geometry theory.

This paper examines the applicability in realistic scenarios of two deep learning based solutions to the overlapping speaker separation problem. Firstly, we present experiments that show that these methods are applicable for a broad range of languages. Further experimentation indicates limited performance loss for untr…

We present a theoretical analysis of the training process for a single-layer GAN fed by high-dimensional input data. The training dynamics of the proposed model at both microscopic and macroscopic scales can be exactly analyzed in the high-dimensional limit. In particular, we prove that the macroscopic quantities measu…

Derives path integrals for perturbative strings on various backgrounds.

Method generates joint posterior samples of source and foreground mass distributions for gravitational lensing.

We provide a comprehensive review of classical algorithms for compressive sensing of images, focused on Total variation methods, with a view to application in LiDAR systems. Our primary focus is providing a full review for beginners in the field, as well as simulating the kind of noise found in real LiDAR systems. To t…

An explorative data analysis system should be aware of what the user already knows and what the user wants to know of the data: otherwise the system cannot provide the user with the most informative and useful views of the data. We propose a principled way to do exploratory data analysis, where the user's background kn…

We describe the construction of a Lie superalgebra associated to an arbitrary supersymmetric M-theory background, and discuss some examples. We prove that for backgrounds with more than 24 supercharges, the bosonic subalgebra acts locally transitively. In particular, we prove that backgrounds with more than 24 supersym…

New framework uses background knowledge to speed up causal discovery.

SRTC model for background/foreground separation with missing pixels.

A new method avoids noise amplification when subtracting or dividing stochastic signals.

Study optimal reinsurance for insurers with a reinsurer's default risk.

Unsupervised learning techniques in computer vision often require learning latent representations, such as low-dimensional linear and non-linear subspaces. Noise and outliers in the data can frustrate these approaches by obscuring the latent spaces. Our main goal is deeper understanding and new development of robust ap…

We extend the Falceto-Zambon version of Marsden-Ratiu Poisson reduction to Poisson quasi-Nijenhuis structures with background on manifolds. We define gauge transformations of Poisson quasi-Nijenhuis structures with background, study some of their properties and show that they are compatible with reduction procedure. We…

Motivated by the search for new gravity duals to M2 branes with $N>4$ supersymmetry --- equivalently, M-theory backgrounds with Killing superalgebra $\mathfrak{osp}(N|4)$ for $N>4$ --- we classify homogeneous M-theory backgrounds with symmetry Lie algebra $\mathfrak{so}(n) \oplus \mathfrak{so}(3,2)$ for $n=5,6,7$. We f…

Understanding the connectivity in the brain is an important prerequisite for understanding how the brain processes information. In the Brain/MINDS project, a connectivity study on marmoset brains uses two-photon microscopy fluorescence images of axonal projections to collect the neuron connectivity from defined brain r…

We explore all warped $AdS_4\times_w M^{D-4}$ backgrounds with the most general allowed fluxes that preserve more than 16 supersymmetries in $D=10$- and $11$-dimensional supergravities. After imposing the assumption that either the internal space $M^{D-4}$ is compact without boundary or the isometry algebra of the back…

b-LOAD extends local causal discovery with prior knowledge, improving causal effect estimation.

LANCA uses ANM to learn latent causal factors without supervision.

Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional deconvolution techniques are limited in their ability to recover features in imaging da…

Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.

ResUNet-CMB neural network reconstructs CMB effects from noisy data.