Risk Based Lattice Cutting for Segmental Minimum Bayes-Risk Decoding

Download: poster.

“Risk Based Lattice Cutting for Segmental Minimum Bayes-Risk Decoding” by S. Kumar and W. Byrne. In Proc. of the International Conference on Spoken Language Processing, (Denver, Colorado, USA), 2002.

Abstract

Minimum Bayes-Risk (MBR) speech recognizers have been shown to give improvements over the conventional maximum a-posteriori probability (MAP) decoders through N-best list rescoring and A-star search over word lattices. Segmental MBR (SMBR) decoders simplify the implementation of MBR recognizers by segmenting the N-best lists or lattices over which the recognition is performed. We present a lattice cutting procedure that attempts to minimize the total Bayes-Risk of all word strings in the segmented lattice. We provide experimental results on the Switchboard conversational speech corpus showing that this segmentation procedure, in conjunction with SMBR decoding, gives modest but significant improvements over MAP decoders as well as MBR decoders on unsegmented lattices.

Download: poster.

BibTeX entry:

@inproceedings{riskbasedlattcut_icslp02,
   author = {S. Kumar, and W. Byrne,},
   title = {Risk Based Lattice Cutting for Segmental Minimum {B}ayes-Risk
	Decoding},
   booktitle = {Proc. of the International Conference on Spoken Language
	Processing},
   pages = {(4 pages)},
   address = {Denver, Colorado, USA},
   year = {2002}
}

Back to Bill Byrne publications.