Tampere University of Technology

TUTCRIS Research Portal

Non-negative tensor factorization models for Bayesian audio processing

Research output: Contribution to journalArticleScientificpeer-review

Details

Original languageEnglish
Pages (from-to)178–191
JournalDigital Signal Processing
Volume47
DOIs
Publication statusPublished - 2015
Publication typeA1 Journal article-refereed

Abstract

We provide an overview of matrix and tensor factorization methods from a Bayesian perspective, giving emphasis on both the inference methods and modeling techniques. Factorization based models and their many extensions such as tensor factorizations have proved useful in a broad range of applications, supporting a practical and computationally tractable framework for modeling. Especially in audio processing, tensor models help in a unified manner the use of prior knowledge about signals, the data generation processes as well as available data from different modalities. After a general review of tensor models, we describe the general statistical framework, give examples of several audio applications and describe modeling strategies for key problems such as deconvolution, source separation, and transcription.

Keywords

  • Bayesian audio modeling, Bayesian inference, Coupled factorization, Nonnegative matrix and tensor factorization

Publication forum classification

Field of science, Statistics Finland