Time domain blind source separation of non-stationary convolved signals by utilizing geometric beamforming

R. Aichner, S. Araki, S. Makino, T. Nishikawa, H. Saruwatari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Citations (Scopus)

Abstract

We propose a time-domain blind source separation (BSS) algorithm that utilizes geometric information such as sensor positions and assumed locations of sources. The algorithm tackles the problem of convolved mixtures by explicitly exploiting the non-stationarity of the acoustic sources. The learning rule is based on second-order statistics and is derived by natural gradient minimization. The proposed initialization of the algorithm is based on the null beamforming principle. This method leads to improved separation performance, and the algorithm is able to estimate long unmixing FIR filters in the time domain due to the geometric initialization. We also propose a post-filtering method for dewhitening which is based on the scaling technique in frequency-domain BSS. The validity of the proposed method is shown by computer simulations. Our experimental results confirm that the algorithm is capable of separating real-world speech mixtures and can be applied to short learning data sets down to a few seconds. Our results also confirm that the proposed dewhitening post-filtering method maintains the spectral content of the original speech in the separated output.

Original languageEnglish
Title of host publicationNeural Networks for Signal Processing XII - Proceedings of the 2002 IEEE Signal Processing Society Workshop, NNSP 2002
EditorsSamy Bengio, Scott Douglas, Tulay Adali, Jan Larsen, Herve Bourlard
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages445-454
Number of pages10
ISBN (Electronic)0780376161
DOIs
Publication statusPublished - 2002
Externally publishedYes
Event12th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2002 - Martigny, Switzerland
Duration: 2002 Sep 6 → …

Publication series

NameNeural Networks for Signal Processing - Proceedings of the IEEE Workshop
Volume2002-January

Other

Other12th IEEE Workshop on Neural Networks for Signal Processing, NNSP 2002
Country/TerritorySwitzerland
CityMartigny
Period02/9/6 → …

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Software
  • Computer Networks and Communications
  • Signal Processing

Fingerprint

Dive into the research topics of 'Time domain blind source separation of non-stationary convolved signals by utilizing geometric beamforming'. Together they form a unique fingerprint.

Cite this