Affordable Access

Access to the full text

Underdetermined Reverberant Audio-Source Separation Through Improved Expectation–Maximization Algorithm

Authors
  • Xie, Yuan1
  • Xie, Kan1
  • Yang, Junjie1
  • Wu, Zongze1
  • Xie, Shengli1
  • 1 Guangdong University of Technology, Guangzhou, 510006, China , Guangzhou (China)
Type
Published Article
Journal
Circuits, Systems, and Signal Processing
Publisher
Springer US
Publication Date
Jan 02, 2019
Volume
38
Issue
6
Pages
2877–2889
Identifiers
DOI: 10.1007/s00034-018-1011-5
Source
Springer Nature
Keywords
License
Yellow

Abstract

Underdetermined reverberant audio-source separation is an important issue in speech and audio processing. To solve this problem, many separation algorithms have been proposed, in which model parameter estimation is performed in the time–frequency domain, leading to permutation ambiguity and poor separation performance. Additionally, in the existing expectation–maximization (EM) algorithms, one of the crucial problem is that updating the model parameters at each iterative step is time-consuming. In this paper, we present an improved EM algorithm that combines nonnegative matrix factorization (NMF) and time differences of arrival (TDOA) estimation, avoiding the time consumption by properly selecting initial values of the EM algorithm. In the proposed algorithm, NMF source model is used to avoid the permutation ambiguity problem, and acoustic localization can be achieved by transforming the TDOA. Then, model parameters are updated to obtain better separation results. Finally, the source signals are separated using Wiener filters. The experimental results show that compared with existing blind separation methods, the proposed algorithm achieves better performance on source separation.

Report this publication

Statistics

Seen <100 times