Correction of likelihoods for degrees of freedom in robust speech recognition using missing feature theory

In Missing Feature Theory (MFT), noise robustness of speech recognizers is obtained by modifying the likelihood computed by the acoustic model to express that some features extracted from the signal are unreliable or missing. In one implementation of MFT, the acoustic model and bounds on the unreliable feature are used to infer an estimate of the missing data. This paper addresses an observed bias of the likelihood evaluated at the estimate. Theoretical and experimental evidence are provided that an upper bound on the accuracy is improved by applying a computationally simple correction for the number of free variables in the likelihood maximization.