10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

A Semi-Blind Source Separation Method with a Less Amount of Computation Suitable for Tiny DSP Modules

Kazunobu Kondo, Makoto Yamada, Hideki Kenmochi

Yamaha Corporation, Japan

In this paper, we propose a method of implementing FDICA on tiny DSP modules. Firstly, we show a semi-blind separation matrix initialization step that consists of an estimation method using covariance fitting for a known source and an unknown source. It contributes to the faster convergence and less amount of computation. Secondly, a learning band selection step is shown that consists of the determinant of the covariance matrix as a criteria for selection; This achieves a significant reduction of an amount of computation with practical separation performance. Finally, the effectiveness of the proposed method is evaluated via the source separation simulations in anechoic and reverberant rooms, and also a procedure and a resource presumption for the integrated method which we call tinyICA are shown.

Full Paper

Bibliographic reference.  Kondo, Kazunobu / Yamada, Makoto / Kenmochi, Hideki (2009): "A semi-blind source separation method with a less amount of computation suitable for tiny DSP modules", In INTERSPEECH-2009, 1339-1342.