In this paper we describe a method that can be used for Minimum Bayes Risk (MBR) decoding for speech recognition. Our algorithm can take as input either a single lattice, or multiple lattices for system combination. It has similar functionality to the widely used Consensus method, but has a clearer theoretical basis and appears to give better results both for MBR decoding and system combination...

We study the switch distribution, introduced by van Erven, Grünwald and De Rooij (2012), applied to model selection and subsequent estimation. While switching was known to be strongly consistent, here we show that it achieves minimax optimal parametric risk rates up to a log logn factor when comparing two nested exponential families, partially confirming a conjecture by Lauritzen (2012) and Cav...

A modeling approach is presented that incorporates discriminative training procedures within segmental Minimum Bayes-Risk decoding (SMBR). SMBR is used to segment lattices produced by a general automatic speech recognition (ASR) system into sequences of separate decision problems involving small sets of confusable words. Acoustic models specialized to discriminate between the competing words in...

We present Minimum Bayes-Risk (MBR) decoding over translation lattices that compactly encode a huge number of translation hypotheses. We describe conditions on the loss function that will enable efficient implementation of MBR decoders on lattices. We introduce an approximation to the BLEU score (Papineni et al., 2001) that satisfies these conditions. The MBR decoding under this approximate BLE...

Modeling approaches are presented that incorporate discriminative training procedures in segmental Minimum Bayes-Risk decoding (SMBR). SMBR is used to segment lattices produced by a general automatic speech recognition (ASR) system into sequences of separate decision problems involving small sets of confusable words. We discuss two approaches to incorporating these segmented lattices in discrim...