Sciweavers

Share
ICASSP
2010
IEEE

An improved consensus-like method for Minimum Bayes Risk decoding and lattice combination

10 years 1 months ago
An improved consensus-like method for Minimum Bayes Risk decoding and lattice combination
In this paper we describe a method for Minimum Bayes Risk decoding for speech recognition. This is a technique similar to Consensus a.k.a. Confusion Network Decoding, in which we attempt to find the hypothesis that minimizes the Bayes’ Risk with respect to the word error rate, based on a lattice of alternative outputs. Our method is an E-M like technique which makes approximations which we believe are less severe than the approximations made in Consensus, and our experimental results show an improvement in WER both for lattice rescoring and lattice-based system combination, versus baselines such as Consensus, Confusion Network Combination and ROVER.
Haihua Xu, Daniel Povey, Lidia Mangu, Jie Zhu
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Haihua Xu, Daniel Povey, Lidia Mangu, Jie Zhu
Comments (0)
books