IMPROVEMENTS IN ACCURACY AND SPEED IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM
P.C. Woodland, J.J. Odell, T. Hain, G.L. Moore, T.R. Niesler, A. Tuerk and E.W.D. Whittaker.
This paper describes a number of recent improvements to the HTK Broadcast News Transcription System. Changes to the system include the use of more acoustic training data; use of cluster-based variance normalisation and vocal tract length normalisation; the use of interpolated language models and enhanced adaptation using a full variance transform. These changes produce a reduction in word error rate of 13%. A simplified version of the system has also been constructed that runs in less than 10 times real-time and gives a 2.3% absolute higher error rate than the 300xRT full system.
If you have difficulty viewing files that end
which are gzip compressed, then you may be able to find
tools to uncompress them at the gzip
If you have difficulty viewing files that are in PostScript, (ending
'.ps.gz'), then you may be able to
find tools to view them at
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.