Predictedwalk with correlation in particle filter speech feature enhancement for robust automatic speech recognition

Previous particle filter feature enhancement techniques for robust automatic speech recognition have ignored the fact that neighbored spectral bins are correlated. In those cases, the spectral bins have been treated as uncorrelated components in the sampling stage of the particle filter. In this publication we propose to consider the correlation between the individual spectral bins by correlating the random variation after a predicted walk realized by a linear prediction matrix. Experiments on artificially added dynamic noise at different signal to noise ratios as well as on actual recordings with different speaker to microphone distances show reasonable word error rate reduction before and after acoustic model adaptation of the automatic speech recognition system.