Revisiting some model-based and data-driven denoising algorithms in Aurora 2 context

In this paper we evaluate some model-based and datadriven algorithms for robust speech recognition in noise, using the experimental framework provided by ETSI Aurora 2. Specifically, we focus on statistical linear approximation (SLA), sequential interacting multiple models (SIMM), and histogram normalization (HN). As the baseline for the feature extraction scheme we use the ETSI front-end. Recognition tests on a subset of Aurora 2 show that SLA is approximately 4 % better than HN and that SIMM is worse than HN by almost 3 % in terms of absolute word accuracy. A comparison with the ETSI advanced front-end (AFE) is also presented. While none of these algorithms outperforms AFE, we identify the reasons why this might have happened and point out potential directions for improvement.