Files in this item



application/pdfTRAA-DISSERTATION-2016.pdf (12MB)
(no description provided)PDF


Title:Phase difference and tensor factorization models for audio source separation
Author(s):Traa, Johannes
Director of Research:Smaragdis, Paris
Doctoral Committee Chair(s):Smaragdis, Paris
Doctoral Committee Member(s):Hasegawa-Johnson, Mark; Bresler, Yoram; Stein, Noah
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Nonnegative matrix factorization
Nonnegative tensor factorization
Interchannel phase differences
Audio Source Separation
Abstract:Audio source separation is a well-known problem in the speech community. Many methods have been proposed to isolate speech signals from a multichannel mixture. In this thesis, we will explore a number of techniques involving interchannel phase difference (IPD) features within a tensor factorization framework. IPD features can be extracted on a time-frequency (TF) grid and are a function of the phase characteristics of the mixing process. Thus, the ultimate goal is to form a clustering of these features and produce TF masks that can be used to perform the separation. We discuss various non-tensor-based methods that are capable of modeling linear and nonlinear IPD trends. Then, we discuss generalizations to both nonnegative and complex tensor factorizations (NTF, CTF). We show that each method performs best in certain circumstances and we conclude by saying that more work is needed to devise a generally superior approach.
Issue Date:2016-10-10
Rights Information:Copyright 2016 Johannes Traa
Date Available in IDEALS:2017-03-01
Date Deposited:2016-12

This item appears in the following Collection(s)

Item Statistics