Abstract for knill_icslp96

Proc. ICSLP 96, Philadelphia, October 1996, pp470-473.


Kate Knill, Mark Gales and Steve Young

October 1996

This paper investigates the use of Gaussian Selection (GS) to reduce the state likelihood computation in HMM-based systems. These likelihood calculations contribute significantly (30 to 70%) to the computational load. Previously, it has been reported that when GS is used on large systems the recognition accuracy tends to degrade above a x3 reduction in likelihood computation. To explain this degradation, this paper investigates the trade-offs necessary between achieving good state likelihoods and low computation. In addition, the problem of unseen states in a cluster is examined. It is shown that further improvements are possible. For example, using a different assignment measure, with a constraint on the number of components per state per cluster, enabled the recognition accuracy on a 5k speaker-independent task to be maintained up to a x5 reduction in likelihood computation.

(ftp:) knill_icslp96.ps.Z (http:) knill_icslp96.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) knill_icslp96.pdf | (http:) knill_icslp96.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.