Lattice Segmentation and Minimum Bayes Risk Discriminative Training

Download: PDF, slides.

“Lattice Segmentation and Minimum Bayes Risk Discriminative Training” by V. Doumpiotis, S. Tsakalidis, and W. Byrne. In Proc. of the European Conference on Speech Communication and Technology (EUROSPEECH), 2003.

Abstract

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 discriminative training. We investigate the use of acoustic models specialized to discriminate between the competing words in these classes which are then applied in subsequent SMBR rescoring passes. Refinement of the search space that allows the use of specialized discriminative models is shown to be an improvement over rescoring with conventionally trained discriminative models.

Download: PDF, slides.

BibTeX entry:

@inproceedings{smbdt_eurospeech03,
   author = {V. Doumpiotis and S. Tsakalidis and W. Byrne},
   title = {Lattice Segmentation and Minimum {B}ayes Risk Discriminative
	Training},
   booktitle = {Proc. of the European Conference on Speech Communication
	and Technology (EUROSPEECH)},
   pages = {(4 pages)},
   year = {2003}
}

Back to Bill Byrne publications.