论文信息 - EVALUATION AND REAL-TIME IMPLEMENTATION OF BLIND SOURCE SEPARATION SYSTEM USING TIME-DELAYED DECORRELATION

EVALUATION AND REAL-TIME IMPLEMENTATION OF BLIND SOURCE SEPARATION SYSTEM USING TIME-DELAYED DECORRELATION

Blind source separation based on the time-delayed decor-relation, which had been extended to a convolved mixture problem, is evaluated and implemented in a DSP system. The evaluation is conducted using the data recorded in an anechoic chamber and those in a listening room with moderate reverberation. The crosstalks and the scores of automatic speech recognition are measured. The hardware consists of dual DSPs and a host PC. The results of the benchmark is shown.

Futoshi Asano | Shiro Ikeda | F. Asano | Shiro Ikeda

[1] Andreas Ziehe,et al. An approach to blind source separation based on temporal structure of speech signals , 2001, Neurocomputing.

[2] Noboru Ohnishi,et al. A method of blind separation for convolved non-stationary signals , 1998, Neurocomputing.

[3] Schuster,et al. Separation of a mixture of independent signals using time delayed correlations. , 1994, Physical review letters.

[4] Andrzej Cichocki,et al. Neural networks for blind decorrelation of signals , 1997, IEEE Trans. Signal Process..

[5] Eric Moulines,et al. A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[6] Shiro Ikeda,et al. A Method of Blind Separation Based on Temporal Structure of Signals , 1998, ICONIP.

[7] Lang Tong,et al. Indeterminacy and identifiability of blind identification , 1991 .

[8] Paris Smaragdis,et al. Blind separation of convolved mixtures in the frequency domain , 1998, Neurocomputing.