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

Download: PDF, slides.

“Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition” by W. Byrne. In Proceedings of the ATR Workshop "Beyond HMMs", (Kyoto, Japan), 2004.

Abstract

Minimum 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 Mark 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.

Download: PDF, slides.

BibTeX entry:

@inproceedings{byrne04:minriskatr,
   author = {W. Byrne},
   title = {Minimum {B}ayes Risk Estimation and Decoding in Large
	Vocabulary Continuous Speech Recognition},
   booktitle = {Proceedings of the {ATR} Workshop "Beyond HMMs"},
   pages = {(6 pages)},
   address = {Kyoto, Japan},
   year = {2004}
}

Back to Bill Byrne publications.