Risk based lattice cutting for segmental minimum Bayes-risk decoding

Abstract

Minimum Bayes Risk (MBR) decoders improve upon MAP decoders by directly optimizing loss function of interest: Word Error Rate MBR decoding is expensive when the search spaces are large Segmental MBR (SMBR) decoding breaks the single utterance-level MBR decoder into a sequence of simpler search problems. – To do this, the N-best lists or lattices need to be segmented We present: A new lattice segmentation strategy based on a risk criterion

Topics

    0 Figures and Tables

      Download Full PDF Version (Non-Commercial Use)