Confidence based lattice segmentation and minimum bayes-risk decoding

Abstract

Minimum Bayes Risk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum a-posteriori probability (MAP) decoders in the context of Nbest list rescoring and A search over recognition lattices. Segmental MBR (SMBR) procedures have been developed to simplify implementation of MBR recognizers, by segmenting the N-best list or lattice, to reduce the size of the search space over which MBR recognition is carried out. In this paper we describe lattice cutting as a method to segment recognition word lattices into regions of low confidence and high confidence. We present two SMBR decoding procedures that can be applied on low confidence segment sets. Results obtained on the Switchboard conversational telephone speech corpus show modest but significant improvements relative to MAP decoders.