广义高斯分布的卷积传递函数多通道非负矩阵分解

Translated title of the contribution: Convolution transfer function-based multi-channel non-negative matrix factorization using generalized Gaussian distributions

Cong Zhang, Feiran Yang*, Xianmei Chen, Jun Yang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The convolution transfer function-based multi-channel non-negative matrix factorization (CTF-MNMF) has been shown to perform well in blind source separation in highly reverberant environments, but its effectiveness may be limited by the source model. An improved version of the CTF-MNMF is proposed, where the generalized Gaussian distribution (GGD) is used as the source model. The domain parameter is introduced into the NMF and the generalized NMF (GNMF) is utilized to model the nonnegative scale factors of the GGD, which enhances the robustness of the source model in capturing signal outliers, and thus improves the accuracy of source estimation. An auxiliary function-based method is used to derive an improved formula for updating the separated matrix and non-negative matrix parameters. Simulation results shows that the proposed algorithm achieves better separation performance than the GGD-ILRMA, WPE-ILRMA, CTF-MNMF algorithms for both speech and music input signals.

Translated title of the contributionConvolution transfer function-based multi-channel non-negative matrix factorization using generalized Gaussian distributions
Original languageChinese (Simplified)
Pages (from-to)598-610
Number of pages13
JournalShengxue Xuebao/Acta Acustica
Volume49
Issue number3
DOIs
Publication statusPublished - May 2024
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2024 Science Press. All rights reserved.

ASJC Scopus Subject Areas

  • Acoustics and Ultrasonics

Keywords

  • Blind source separation
  • Convolution transfer function
  • Generalized Gaussian distribution
  • Non-negative matrix factorization

Cite this