This paper presents a model compensation approach based on Bayesian predictive classification (BPC). In order to obtain effective prior distributions for BPC, our approach uses parallel model combination (PMC) to set the prior mean, and a likelihood ratio to set a scaled frame-specific prior variance. Experiments on the Aurora 2 database show that the proposed approach results in improved average performance compared to PMC.
Bibliographic reference. Pettersen, Svein Gunnar (2008): "Joint Bayesian predictive classification and parallel model combination with prior scaling for robust ASR", In INTERSPEECH-2008, 1273-1276.