Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition

William BYRNE  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E89-D   No.3   pp.900-907
Publication Date: 2006/03/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.3.900
Print ISSN: 0916-8532
Type of Manuscript: INVITED PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: 
Keyword: 
discriminative training,  acoustic modeling,  automatic speech recognition,  maximum mutual information,  

Full Text: PDF>>
Buy this Article




Summary: 
Minimum Bayes risk estimation and decoding strategies based on lattice segmentation techniques can be used to refine large vocabulary continuous speech recognition systems through the estimation of the parameters of the underlying hidden Markov models and through the identification of smaller recognition tasks which provides the opportunity to incorporate novel modeling and decoding procedures in LVCSR. These techniques are discussed in the context of going 'beyond HMMs', showing in particular that this process of subproblem identification makes it possible to train and apply small-domain binary pattern classifiers, such as Support Vector Machines, to large vocabulary continuous speech recognition.