A simple and general method is described that can combine different knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatically trainable, acquiring information from both positive and negative examples. Experiments are described in which it was tested on a 1000-utterance sample of unseen ATIS data.
@article{arxiv.cmp-lg/9407010,
title = {Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists},
author = {Manny Rayner and David Carter and Vassilios Digalakis and Patti Price},
journal= {arXiv preprint arXiv:cmp-lg/9407010},
year = {2008}
}
Comments
13 pages, Latex source. To appear in Proc. HLT '94