We recently discovered novel discriminative training criteria following a principled approach. In this approach training criteria are developed from error bounds on the classification error for pattern classification tasks that depend on non-trivial loss functions. Automatic speech recognition (ASR) is a prominent example for such a task depending on the non-trivial Levenshtein loss. In this context, the posterior-scaled Minimum Phoneme Error (MPE) training criterion, which is the state-of-the-art discriminative training criterion in ASR, was shown to be an approximation to one of the novel criteria. Here, we describe the implementation of the posterior-scaled MPE criterion in a transducer-based framework, and compare this criterion to other discriminative training criteria on an ASR task. This comparison indicates that the posteriorscaled MPE criterion performs better than other discriminative criteria including MPE.

Index Terms: error bounds, discriminative training criteria, margin, MPE