Deep Tensor Factorization for Spatially-Aware Scene Decomposition
We propose a completely unsupervised method to understand audio scenes observed with random microphone arrangements by decomposing the scene into its constituent sources and their relative presence in each microphone. To this end, we formulate a neural network architecture that can be interpreted as a nonnegative tensor factorization of a multi-channel audio recording. By clustering on the learned network parameters corresponding to channel content, we can learn sources' individual spectral dictionaries and their activation patterns over time. Our method allows us to leverage deep learning advances like end-to-end training, while also allowing stochastic minibatch training so that we can feasibly decompose realistic audio scenes that are intractable to decompose using standard methods. This neural network architecture is easily extensible to other kinds of tensor factorizations.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringSimilar Papers 제목 키워드 기반
Time-Aware Tensor Decomposition for Missing Entry Prediction
Given a time-evolving tensor with missing entries, how can we effectively factorize it for precisely predicting the missing entries? Tensor factorization has been extensively utilized for analyzing various multi-dimensio…
PredictionTensor DecompositionStrivec: Sparse Tri-Vector Radiance Fields
We propose Strivec, a novel neural representation that models a 3D scene as a radiance field with sparsely distributed and compactly factorized local tensor feature grids. Our approach leverages tensor decomposition, fol…
Tensor DecompositionTensor Decompositions: A New Concept in Brain Data Analysis?
Matrix factorizations and their extensions to tensor factorizations and decompositions have become prominent techniques for linear and multilinear blind source separation (BSS), especially multiway Independent Component …
blind source separationClassificationClusteringDimensionality Reduction+2SeKron: A Decomposition Method Supporting Many Factorization Structures
While convolutional neural networks (CNNs) have become the de facto standard for most image processing and computer vision applications, their deployment on edge devices remains challenging. Tensor decomposition methods …
Model CompressionTensor DecompositionSparse and Low-Rank Tensor Decomposition
Motivated by the problem of robust factorization of a low-rank tensor, we study the question of sparse and low-rank tensor decomposition. We present an efficient computational algorithm that modifies Leurgans' algoirthm …
Tensor Decomposition