In this paper a formerly proposed continuous digit recognition system based on Reservoir Computing (RC) is improved in two respects: (1) the single reservoir is substituted by a stack of reservoirs, and (2) the straightforward mapping of reservoir outputs to state likelihoods is replaced by a trained non-parametric mapping. Furthermore, it is shown that a reservoir-based method can improve a model trained on clean speech to work better in a noisy condition from which it has a number of unknown digit string recordings available. The first two improvements have lead to a system that outperforms a HMM-based system with the same noise robust features as input. The model adaptation offers a significant supplementary gain when the noise level is not too high.

Index Terms: Reservoir Computing, Acoustic Modeling, Model Adaptation, Noise Robustness