paper-with-me

Papers

Extending GCC-PHAT using Shift Equivariant Neural Networks

2022-08-09 · Axel Berg, Mark O'Connor, Kalle Åström, Magnus Oskarsson

Speaker localization using microphone arrays depends on accurate time delay estimation techniques. For decades, methods based on the generalized cross correlation with phase transform (GCC-PHAT) have been widely adopted for this purpose. Recently, the GCC-PHAT has also been used to provide input features to neural networks in order to remove the effects of noise and reverberation, but at the cost of losing theoretical guarantees in noise-free conditions. We propose a novel approach to extending the GCC-PHAT, where the received signals are filtered using a shift equivariant neural network that preserves the timing information contained in the signals. By extensive experiments we show that our model consistently reduces the error of the GCC-PHAT in adverse environments, with guarantees of exact time delay recovery in ideal conditions.

📄 PDF Abstract BibTeX arXiv:2208.04654

Code (1)

axeber01/ngcc 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics

2022-04-11 · Albert Musaelian, Simon Batzner, Anders Johansson, Lixin Sun 외

A simultaneously accurate and computationally efficient parametrization of the energy and atomic forces of molecules and materials is a long-standing goal in the natural sciences. In pursuit of this goal, neural message …

Atomic Forces

Neural Polarization: Toward Electron Density for Molecules by Extending Equivariant Networks

2024-06-01 · Bumju Kwak, Jeonghee Jo

Recent SO(3)-equivariant models embedded a molecule as a set of single atoms fixed in the three-dimensional space, which is analogous to a ball-and-stick view. This perspective provides a concise view of atom arrangement…

Convolutional layers are equivariant to discrete shifts but not continuous translations

2022-06-10 · Nick McGreivy, Ammar Hakim

The purpose of this short and simple note is to clarify a common misconception about convolutional neural networks (CNNs). CNNs are made up of convolutional layers which are shift equivariant due to weight sharing. Howev…

Translation

Rotation Equivariant Operators for Machine Learning on Scalar and Vector Fields

2021-08-21 · Paul Shen, Michael Herbst, Venkat Viswanathan

We develop theory and software for rotation equivariant operators on scalar and vector fields, with diverse applications in simulation, optimization and machine learning. Rotation equivariance (covariance) means all fiel…

BIG-bench Machine LearningTranslation

Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks

2026-07-04 · Yoshihiro Maruyama arxiv

Symmetry is everywhere in nature and society. Geometric deep learning exploits symmetries in data to improve the performance and efficiency of deep learning systems. In this paper, we extend geometric deep learning to ut…