Related papers: MAPSS: Manifold-based Assessment of Perceptual Sou…

Distributed multichannel acoustic sensing (DMAS) enables large-scale sound event classification (SEC), but performance drops when many channels are degraded and when sensor layouts at test time differ from training layouts. We propose a…

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background…

Approximate message passing (AMP) algorithms have shown great promise in sparse signal reconstruction due to their low computational requirements and fast convergence to an exact solution. Moreover, they provide a probabilistic framework…

This paper presents a technique for Informed Source Separation (ISS) of a single channel mixture, based on the Multiple Input Spectrogram Inversion method. The reconstruction of the source signals is iterative, alternating between a time-…

Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive their predictions. Existing robustness benchmarks provide important stress tests, but…

Segmenting objects in images and separating sound sources in audio are challenging tasks, in part because traditional approaches require large amounts of labeled data. In this paper we develop a neural network model for visual object…

A soundscape is defined by the acoustic environment a person perceives at a location. In this work, we propose a framework for mapping soundscapes across the Earth. Since soundscapes involve sound distributions that span varying spatial…

A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn…

Diffusion models have emerged as powerful generative priors for solving inverse imaging problems. However, their practical deployment is hindered by the substantial computational cost of slow, multi-step sampling. Although Consistency…

We present Predictive Sparse Manifold Transform (PSMT), a minimalistic, interpretable and biologically plausible framework for learning and predicting natural dynamics. PSMT incorporates two layers where the first sparse coding layer…

A major source of endoscopic tissue tracking errors during deformations stems from wrong data association between observed sensor measurements with previously tracked scene. To mitigate this issue, we present a surgical perception…

Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biases into the training and sampling of diffusion models to…

Invariant object recognition is one of the most fundamental cognitive tasks performed by the brain. In the neural state space, different objects with stimulus variabilities are represented as different manifolds. In this geometrical…

Many image enhancement or editing operations, such as forward and inverse tone mapping or color grading, do not have a unique solution, but instead a range of solutions, each representing a different style. Despite this, existing…

We present a generative learning framework for probabilistic sampling based on an extension of the Probabilistic Learning on Manifolds (PLoM) approach, which is designed to generate statistically consistent realizations of a random vector…

We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a…

Typical methods for binaural source separation consider only the direct sound as the target signal in a mixture. However, in most scenarios, this assumption limits the source separation performance. It is well known that the early…

Four-dimensional scanning transmission electron microscopy (4D-STEM) of local atomic diffraction patterns is emerging as a powerful technique for probing intricate details of atomic structure and atomic electric fields. However, efficient…

In a mixed generalized linear model, the goal is to learn multiple signals from unlabeled observations: each sample comes from exactly one signal, but it is not known which one. We consider the prototypical problem of estimating two…

Subjective evaluations are critical for assessing the perceptual realism of sounds in audio-synthesis driven technologies like augmented and virtual reality. However, they are challenging to set up, fatiguing for users, and expensive. In…