Blind Source Separation of Acoustic Signals Based on Multistage ICA Combining Frequency-Domain ICA and Time-Domain ICA

• NISHIKAWA Tsuyoki

  Graduate School of Information Science, Nara Institute of Science and Technology

• SARUWATARI Hiroshi

  Graduate School of Information Science, Nara Institute of Science and Technology

• SHIKANO Kiyohiro

  Graduate School of Information Science, Nara Institute of Science and Technology

抄録

We propose a new algorithm for blind source separation (BSS), in which frequency-domain independent component analysis (FDICA) and time-domain ICA (TDICA) are combined to achieve a superior source-separation performance under reverberant conditions. Generally speaking, conventional TDICA fails to separate source signals under heavily reverberant conditions because of the low convergence in the iterative learning of the inverse of the mixing system. On the other hand, the separation performance of conventional FDICA also degrades significantly because the independence assumption of narrow-band signals collapses when the number of subbands increases. In the proposed method, the separated signals of FDICA are regarded as the input signals for TDICA, and we can remove the residual crosstalk components of FDICA by using TDICA. The experimental results obtained under the reverberant condition reveal that the separation performance of the proposed method is superior to those of TDICA- and FDICA-based BSS methods.

収録刊行物

• IEICE transactions on fundamentals of electronics, communications and computer sciences

  IEICE transactions on fundamentals of electronics, communications and computer sciences 86 (4), 846-858, 2003-04-01

  電子情報通信学会

キーワード

• blind source separation
• time-domain independent component analysis
• frequency-domain independent component analysis
• reverberation
• microphone array

詳細情報

• CRID: 1570854177341681280
• NII論文ID: 110003221132
• NII書誌ID: AA10826239
• ISSN: 09168508
• Web Site: http://hdl.handle.net/10061/7788
• 本文言語コード: en
• データソース種別:
  • CiNii Articles