Abstract for witt_still98

Proc. 'Speech Technology in Language Learning' 1998, Marholmen, Sweden, May 1998.


S. M. Witt and S. J. Young

May 1998

This work presents a general development framework for automatic pronunciation assessment within computer-assisted language learning (CALL) together with several refinements of a previously described pronunciation scoring method. This method utilises a likelihood-based `Goodness of Pronunciation' (GOP) measure which in this work has been extended to include individual thresholds for each phone based on both averaged native confidence scores and on rejection statistics provided by human judges.These statistics where provided through a specifically recorded and annotated database of non-native speech. Since pronunciation assessment is highly subjective, a set of four performance measures has been designed, each of them measuring different aspects of how well computer-derived phone-level scores agree with human scores. These performance measures are used to cross-validate the reference annotations and to assess the basic GOP algorithm and its refinements. The experimental results suggest that a likelihood-based pronunciation scoring metric can achieve usable performance, especially after applying the various enhancements.

(ftp:) witt_still98.ps.Z (http:) witt_still98.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) witt_still98.pdf | (http:) witt_still98.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.