Site menu:

Adaptive blind audio signal separation on a DSP

J. van de Laar, E.A.P. Habets, J.D.P.A. Peters and P.A.M. Lokkart

Abstract

Blind Source Separation (BSS) deals with the problem of separating independent sources from their observed mixtures only while both the mixing process and original sources are unknown. Examples of BSS algorithms employed in acoustical applications can be found among others in audio teleconferencing systems. This paper describes the main ideas and implementation of an Adaptive Blind Signal Separation algorithm. In order to make the real-time implementation feasible, the BSS algorithm is based on a simplified mixing model (SMM). The input signals are reconstructed by assuming that they are statistically uncorrelated and imposing this constraint on the signal estimates. The nonstationarity of the input signals is used to restrict the set of solutions. The system is realized on a TI TMS320C6701 DSP and is capable of separating two independent simultaneously occurring audio signals in an ordinary acoustic environment in real-time and in an adaptive way. Finally, the separation performance of the algorithm is evaluated using benchmarks downloaded from the web and own real-world recordings.

Status

Published in the Proc. of the 12th Annual Workshop on Circuits, Systems and Signal Processing (ProRISC 2001), Veldhoven, Netherlands, Nov. 28-30, 2001, ISBN 90-73461-29-4; STW, Technology Foundation, Utrecht, The Netherlands, pp. 475-479.

BibTex Entry

@INPROCEEDINGS{Laar2001,
  author = {J. {van de Laar} and E. A. P. Habets and J. D. P. A. Peters and P.
	A. M. Lokkart},
  title = {Adaptive blind audio signal separation on a {DSP}},
  booktitle = PRORISC,
  year = {2001},
  pages = {475--479},
  address = {Veldhoven, The Netherlands},
  month = nov
}

[Back]