VLSI Design for Convolutive Blind Source Separation

Jia Ching Wang, Chien Yao Wang, Tzu Chiang Tai, Min Shih, Shao Chieh Huang, Ying Chuan Chen, Yan Yu Lin, Li Xun Lian

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

This brief presents an efficient very-large-scale integration architecture design for convolutive blind source separation (CBSS). The CBSS separation network derived from the information maximization (Infomax) approach is adopted. The proposed CBSS chip design consists mainly of Infomax filtering modules and scaling factor computation modules. In an Infomax filtering module, input samples are filtered by an Infomax filter with the weights updated by Infomax-driven stochastic learning rules. As for the scaling factor computation module, all operations including logistic sigmoid are integrated and implemented by the circuit design based on a piecewise-linear approximation scheme. The proposed prototype chip is implemented via a semi-custom design using 90-nm CMOS technology on a die size of approximately 0.54×0.54mm2.

Original languageEnglish
Article number7206567
Pages (from-to)196-200
Number of pages5
JournalIEEE Transactions on Circuits and Systems II: Express Briefs
Volume63
Issue number2
DOIs
StatePublished - Feb 2016

Keywords

  • Blind source separation
  • VLSI
  • convolutive blind source separation
  • convolutive mixing
  • information maximization

Fingerprint

Dive into the research topics of 'VLSI Design for Convolutive Blind Source Separation'. Together they form a unique fingerprint.

Cite this