Abstract for evermann_icassp00

Proc. ICASSP 2000, Istanbul, Turkey

LARGE VOCABULARY DECODING AND CONFIDENCE ESTIMATION USING WORD POSTERIOR PROBABILITIES

G. Evermann and P.C. Woodland

June 2000

This paper investigates the estimation of word posterior probabilities based on word lattices and presents applications of these posteriors in a large vocabulary speech recognition system. A novel approach to integrating these word posterior probability distributions into a conventional Viterbi decoder is presented. The problem of the robust estimation of confidence scores from word posteriors is examined and a method based on decision trees is suggested. The effectiveness of these techniques is demonstrated on the broadcast news and the conversational telephone speech corpora where improvements both in terms of word error rate and normalised cross entropy were achieved compared to the baseline HTK evaluation systems.


| (ftp:) evermann_icassp00.ps.gz | (http:) evermann_icassp00.ps.gz | (ftp:) evermann_icassp00.pdf | (http:) evermann_icassp00.pdf |

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.