A Fast Stereo Audio Source Separation for Moving Sources
Oleg Golokolenko, Gerald Schuller · 2019
In this paper, a novel system for the separation of 2 moving audio source is being presented and evaluated in experiments. The proposed approach works in the time domain, estimating coefficients of IIR filters derived from attenuation factors and fractional delays between microphone signals to minimize cross-talk. A novel objective function derived from the Kullback-Leibler divergence as a substitute of mutual information between the resulting separated signals is used. For optimization we utilize a novel algorithm of "Random Directions", without the need for gradients, which is very fast and robust. The evaluation of proposed approach on convolutive mixtures generated from speech signals taken from the TIMIT data-set using a room impulse response simulator is being presented. Results show that our proposed approach outperforms a state of the art approach in computation time and has a comparable separation performance.